The PEBS TSC-based timestamps do not appear correctly in the final
perf.data output file from perf record.
The data->time field setup by PEBS in the setup_pebs_fixed_sample_data()
is later overwritten by perf_events generic code in
perf_prepare_sample(). There is an ordering problem.
Set the sample flags when the data->time is updated by PEBS.
The data->time field will not be overwritten anymore.
Reported-by: Andreas Kogler <andreas.kogler.0x@gmail.com>
Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220901130959.1285717-3-kan.liang@linux.intel.com
When a guest PEBS counter is cross-mapped by a host counter, software
will remove the corresponding bit in the arr[global_ctrl].guest and
expect hardware to perform a change of state "from enable to disable"
via the msr_slot[] switch during the vmx transaction.
The real world is that if user adjust the counter overflow value small
enough, it still opens a tiny race window for the previously PEBS-enabled
counter to write cross-mapped PEBS records into the guest's PEBS buffer,
when arr[global_ctrl].guest has been prioritised (switch_msr_special stuff)
to switch into the enabled state, while the arr[pebs_enable].guest has not.
Close this window by clearing invalid bits in the arr[global_ctrl].guest.
Cc: linux-perf-users@vger.kernel.org
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Fixes: 854250329c ("KVM: x86/pmu: Disable guest PEBS temporarily in two rare situations")
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220831033524.58561-1-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When a guest PEBS counter is cross-mapped by a host counter, software
will remove the corresponding bit in the arr[global_ctrl].guest and
expect hardware to perform a change of state "from enable to disable"
via the msr_slot[] switch during the vmx transaction.
The real world is that if user adjust the counter overflow value small
enough, it still opens a tiny race window for the previously PEBS-enabled
counter to write cross-mapped PEBS records into the guest's PEBS buffer,
when arr[global_ctrl].guest has been prioritised (switch_msr_special stuff)
to switch into the enabled state, while the arr[pebs_enable].guest has not.
Close this window by clearing invalid bits in the arr[global_ctrl].guest.
Fixes: 854250329c ("KVM: x86/pmu: Disable guest PEBS temporarily in two rare situations")
Signed-off-by: Like Xu <likexu@tencent.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220831033524.58561-1-likexu@tencent.com
For some Alder Lake N machine, the below unchecked MSR access error may be
triggered.
[ 0.088017] rcu: Hierarchical SRCU implementation.
[ 0.088017] unchecked MSR access error: WRMSR to 0x38f (tried to write
0x0001000f0000003f) at rIP: 0xffffffffb5684de8 (native_write_msr+0x8/0x30)
[ 0.088017] Call Trace:
[ 0.088017] <TASK>
[ 0.088017] __intel_pmu_enable_all.constprop.46+0x4a/0xa0
The Alder Lake N only has e-cores. The X86_FEATURE_HYBRID_CPU flag is
not set. The perf cannot retrieve the correct CPU type via
get_this_hybrid_cpu_type(). The model specific get_hybrid_cpu_type() is
hardcode to p-core. The wrong CPU type is given to the PMU of the
Alder Lake N.
Since Alder Lake N isn't in fact a hybrid CPU, remove ALDERLAKE_N from
the rest of {ALDER,RAPTOP}LAKE and create a non-hybrid PMU setup.
The differences between Gracemont and the previous Tremont are,
- Number of GP counters
- Load and store latency Events
- PEBS event_constraints
- Instruction Latency support
- Data source encoding
- Memory access latency encoding
Fixes: c2a960f7c5 ("perf/x86: Add new Alder Lake and Raptor Lake support")
Reported-by: Jianfeng Gao <jianfeng.gao@intel.com>
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/20220831142702.153110-1-kan.liang@linux.intel.com
This expands generic branch type classification by adding two more entries
there in i.e system error and not in transaction. This also updates the x86
implementation to process X86_BR_NO_TX records as appropriate. This changes
branch types reported to user space on x86 platform but it should not be a
problem. The possible scenarios and impacts are enumerated here.
--------------------------------------------------------------------------
| kernel | perf tool | Impact |
--------------------------------------------------------------------------
| old | old | Works as before |
--------------------------------------------------------------------------
| old | new | PERF_BR_UNKNOWN is processed |
--------------------------------------------------------------------------
| new | old | PERF_BR_NO_TX is blocked via old PERF_BR_MAX |
--------------------------------------------------------------------------
| new | new | PERF_BR_NO_TX is recognized |
--------------------------------------------------------------------------
When PERF_BR_NO_TX is blocked via old PERF_BR_MAX (new kernel with old perf
tool) the user space might throw up an warning complaining about an
unrecognized branch types being reported, but it's expected. PERF_BR_SERROR
& PERF_BR_NO_TX branch types will be used for BRBE implementation on arm64
platform.
PERF_BR_NO_TX complements 'abort' and 'in_tx' elements in perf_branch_entry
which represent other transaction states for a given branch record. Because
this completes the transaction state classification.
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: James Clark <james.clark@arm.com>
Link: https://lkml.kernel.org/r/20220824044822.70230-2-anshuman.khandual@arm.com
Provide branch speculation information captured via AMD Last Branch Record
Extension Version 2 (LbrExtV2) by setting the speculation info in branch
records. The info is based on the "valid" and "spec" bits in the Branch To
registers.
Suggested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/ddc02f6320464cad0e3ff5bdb2314531568a91bc.1660211399.git.sandipan.das@amd.com
AMD Last Branch Record Extension Version 2 (LbrExtV2) can report a branch
from address that points to an instruction preceding the actual branch by
several bytes due to branch fusion and further optimizations in Zen4
processors.
In such cases, software should move forward sequentially in the instruction
stream from the reported address and the address of the first branch
encountered should be used instead. Hence, use the fusion-aware branch
classifier to determine the correct branch type and get the offset for
adjusting the branch from address.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/c324d2d0a9c3976da30b9563d09e50bfee0f264d.1660211399.git.sandipan.das@amd.com
With branch fusion and other optimizations, branch sampling hardware in
some processors can report a branch from address that points to an
instruction preceding the actual branch by several bytes.
In such cases, the classifier cannot determine the branch type which leads
to failures such as with the recently added test from commit b55878c90a
("perf test: Add test for branch stack sampling"). Branch information is
also easier to consume and annotate if branch from addresses always point
to branch instructions.
Add a new variant of the branch classifier that can account for instruction
fusion. If fusion is expected and the current branch from address does not
point to a branch instruction, it attempts to find the first branch within
the next (MAX_INSN_SIZE - 1) bytes and if found, additionally provides the
offset between the reported branch from address and the address of the
expected branch instruction.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/b6bb0abaa8a54c0b6d716344700ee11a1793d709.1660211399.git.sandipan.das@amd.com
With AMD Last Branch Record Extension Version 2 (LbrExtV2), it is necessary
to process the branch records further as hardware filtering is not granular
enough for identifying certain types of branches. E.g. to record system
calls, one should record far branches. The filter captures both far calls
and far returns but the irrelevant records are filtered out based on the
branch type as seen by the branch classifier.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/e51de057517f77788abd393c832e8dea616d489c.1660211399.git.sandipan.das@amd.com
Commit 3e702ff6d1 ("perf/x86: Add LBR software filter support for Intel
CPUs") introduces a software branch filter which complements the hardware
branch filter and adds an x86 branch classifier.
Move the branch classifier to arch/x86/events/ so that it can be utilized
by other vendors for branch record filtering.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/bae5b95470d6bd49f40954bd379f414f5afcb965.1660211399.git.sandipan.das@amd.com
If AMD Last Branch Record Extension Version 2 (LbrExtV2) is detected,
convert the requested branch filter (PERF_SAMPLE_BRANCH_* flags) to the
corresponding hardware filter value and stash it in the event data when
a branch stack is requested. The hardware filter value is also saved in
per-CPU areas for use during event scheduling.
Hardware filtering is provided by the LBR Branch Select register. It has
bits which when set, suppress recording of the following types of branches:
* CPL = 0 (Kernel only)
* CPL > 0 (Userspace only)
* Conditional Branches
* Near Relative Calls
* Near Indirect Calls
* Near Returns
* Near Indirect Jumps (excluding Near Indirect Calls and Near Returns)
* Near Relative Jumps (excluding Near Relative Calls)
* Far Branches
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/9336af5c9785b8e14c62220fc0e6cfb10ab97de3.1660211399.git.sandipan.das@amd.com
If AMD Last Branch Record Extension Version 2 (LbrExtV2) is detected,
enable it alongside LBR Freeze on PMI when an event requests branch stack
i.e. PERF_SAMPLE_BRANCH_STACK.
Each branch record is represented by a pair of registers, LBR From and LBR
To. The freeze feature prevents any updates to these registers once a PMC
overflows. The contents remain unchanged until the freeze bit is cleared by
the PMI handler.
The branch records are read and copied to sample data before unfreezing.
However, only valid entries are copied. There is no additional register to
denote which of the register pairs represent the top of the stack (TOS)
since internal register renaming always ensures that the first pair (i.e.
index 0) is the one representing the most recent branch and so on.
The LBR registers are per-thread resources and are cleared explicitly
whenever a new task is scheduled in. There are no special implications on
the contents of these registers when transitioning to deep C-states.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/d3b8500a3627a0d4d0259b005891ee248f248d91.1660211399.git.sandipan.das@amd.com
AMD Last Branch Record Extension Version 2 (LbrExtV2) is driven by Core PMC
overflows. It records recently taken branches up to the moment when the PMC
overflow occurs.
Detect the feature during PMU initialization and set the branch stack depth
using CPUID leaf 0x80000022 EBX.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/fc6e45378ada258f1bab79b0de6e05c393a8f1dd.1660211399.git.sandipan.das@amd.com
AMD processors that are capable of recording branches support either Branch
Sampling (BRS) or Last Branch Record (LBR). In preparation for adding Last
Branch Record Extension Version 2 (LbrExtV2) support, introduce new static
calls which act as gateways to call into the feature-dependent functions
based on what is available on the processor.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/b75dbc32663cb395f0d701167e952c6a6b0445a3.1660211399.git.sandipan.das@amd.com
AMD processors that are capable of recording branches support either Branch
Sampling (BRS) or Last Branch Record (LBR). In preparation for adding Last
Branch Record Extension Version 2 (LbrExtV2) support, reuse the "branches"
capability to advertise information about both BRS and LBR but make the
"branch-brs" event exclusive to Family 19h processors that support BRS.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/ba4a4cde6db79b1c65c49834027bbdb8a915546b.1660211399.git.sandipan.das@amd.com
Existing code was generating bogus counts for the SNB IMC bandwidth counters:
$ perf stat -a -I 1000 -e uncore_imc/data_reads/,uncore_imc/data_writes/
1.000327813 1,024.03 MiB uncore_imc/data_reads/
1.000327813 20.73 MiB uncore_imc/data_writes/
2.000580153 261,120.00 MiB uncore_imc/data_reads/
2.000580153 23.28 MiB uncore_imc/data_writes/
The problem was introduced by commit:
07ce734dd8 ("perf/x86/intel/uncore: Clean up client IMC")
Where the read_counter callback was replace to point to the generic
uncore_mmio_read_counter() function.
The SNB IMC counters are freerunnig 32-bit counters laid out contiguously in
MMIO. But uncore_mmio_read_counter() is using a readq() call to read from
MMIO therefore reading 64-bit from MMIO. Although this is okay for the
uncore_perf_event_update() function because it is shifting the value based
on the actual counter width to compute a delta, it is not okay for the
uncore_pmu_event_start() which is simply reading the counter and therefore
priming the event->prev_count with a bogus value which is responsible for
causing bogus deltas in the perf stat command above.
The fix is to reintroduce the custom callback for read_counter for the SNB
IMC PMU and use readl() instead of readq(). With the change the output of
perf stat is back to normal:
$ perf stat -a -I 1000 -e uncore_imc/data_reads/,uncore_imc/data_writes/
1.000120987 296.94 MiB uncore_imc/data_reads/
1.000120987 138.42 MiB uncore_imc/data_writes/
2.000403144 175.91 MiB uncore_imc/data_reads/
2.000403144 68.50 MiB uncore_imc/data_writes/
Fixes: 07ce734dd8 ("perf/x86/intel/uncore: Clean up client IMC")
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20220803160031.1379788-1-eranian@google.com
According to the latest event list, the LOAD_LATENCY PEBS event only
works on the GP counter 0 and 1 for ADL and RPL.
Update the pebs event constraints table.
Fixes: f83d2f91d2 ("perf/x86/intel: Add Alder Lake Hybrid support")
Reported-by: Ammy Yi <ammy.yi@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20220818184429.2355857-1-kan.liang@linux.intel.com
With the existing code in store_latency_data(), the memory operation (mem_op)
returned to the user is always OP_LOAD where in fact, it should be OP_STORE.
This comes from the fact that the function is simply grabbing the information
from a data source map which covers only load accesses. Intel 12th gen CPU
offers precise store sampling that captures both the data source and latency.
Therefore it can use the data source mapping table but must override the
memory operation to reflect stores instead of loads.
Fixes: 61b985e3e7 ("perf/x86/intel: Add perf core PMU support for Sapphire Rapids")
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220818054613.1548130-1-eranian@google.com
The SDM explicitly states that PEBS Baseline implies Extended PEBS.
For cpu model forward compatibility (e.g. on ICX, SPR, ADL), it's
safe to stop doing FMS table thing such as setting pebs_capable and
PMU_FL_PEBS_ALL since it's already set in the intel_ds_init().
The Goldmont Plus is the only platform which supports extended PEBS
but doesn't have Baseline. Keep the status quo.
Reported-by: Like Xu <likexu@tencent.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lkml.kernel.org/r/20220816114057.51307-1-likexu@tencent.com
On the platform with Arch LBR, the HW raw branch type encoding may leak
to the perf tool when the SAVE_TYPE option is not set.
In the intel_pmu_store_lbr(), the HW raw branch type is stored in
lbr_entries[].type. If the SAVE_TYPE option is set, the
lbr_entries[].type will be converted into the generic PERF_BR_* type
in the intel_pmu_lbr_filter() and exposed to the user tools.
But if the SAVE_TYPE option is NOT set by the user, the current perf
kernel doesn't clear the field. The HW raw branch type leaks.
There are two solutions to fix the issue for the Arch LBR.
One is to clear the field if the SAVE_TYPE option is NOT set.
The other solution is to unconditionally convert the branch type and
expose the generic type to the user tools.
The latter is implemented here, because
- The branch type is valuable information. I don't see a case where
you would not benefit from the branch type. (Stephane Eranian)
- Not having the branch type DOES NOT save any space in the
branch record (Stephane Eranian)
- The Arch LBR HW can retrieve the common branch types from the
LBR_INFO. It doesn't require the high overhead SW disassemble.
Fixes: 47125db27e ("perf/x86/intel/lbr: Support Architectural LBR")
Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20220816125612.2042397-1-kan.liang@linux.intel.com
* Unwinder implementations for both nVHE modes (classic and
protected), complete with an overflow stack
* Rework of the sysreg access from userspace, with a complete
rewrite of the vgic-v3 view to allign with the rest of the
infrastructure
* Disagregation of the vcpu flags in separate sets to better track
their use model.
* A fix for the GICv2-on-v3 selftest
* A small set of cosmetic fixes
RISC-V:
* Track ISA extensions used by Guest using bitmap
* Added system instruction emulation framework
* Added CSR emulation framework
* Added gfp_custom flag in struct kvm_mmu_memory_cache
* Added G-stage ioremap() and iounmap() functions
* Added support for Svpbmt inside Guest
s390:
* add an interface to provide a hypervisor dump for secure guests
* improve selftests to use TAP interface
* enable interpretive execution of zPCI instructions (for PCI passthrough)
* First part of deferred teardown
* CPU Topology
* PV attestation
* Minor fixes
x86:
* Permit guests to ignore single-bit ECC errors
* Intel IPI virtualization
* Allow getting/setting pending triple fault with KVM_GET/SET_VCPU_EVENTS
* PEBS virtualization
* Simplify PMU emulation by just using PERF_TYPE_RAW events
* More accurate event reinjection on SVM (avoid retrying instructions)
* Allow getting/setting the state of the speaker port data bit
* Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls are inconsistent
* "Notify" VM exit (detect microarchitectural hangs) for Intel
* Use try_cmpxchg64 instead of cmpxchg64
* Ignore benign host accesses to PMU MSRs when PMU is disabled
* Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior
* Allow NX huge page mitigation to be disabled on a per-vm basis
* Port eager page splitting to shadow MMU as well
* Enable CMCI capability by default and handle injected UCNA errors
* Expose pid of vcpu threads in debugfs
* x2AVIC support for AMD
* cleanup PIO emulation
* Fixes for LLDT/LTR emulation
* Don't require refcounted "struct page" to create huge SPTEs
* Miscellaneous cleanups:
** MCE MSR emulation
** Use separate namespaces for guest PTEs and shadow PTEs bitmasks
** PIO emulation
** Reorganize rmap API, mostly around rmap destruction
** Do not workaround very old KVM bugs for L0 that runs with nesting enabled
** new selftests API for CPUID
Generic:
* Fix races in gfn->pfn cache refresh; do not pin pages tracked by the cache
* new selftests API using struct kvm_vcpu instead of a (vm, id) tuple
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmLnyo4UHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroMtQQf/XjVWiRcWLPR9dqzRM/vvRXpiG+UL
jU93R7m6ma99aqTtrxV/AE+kHgamBlma3Cwo+AcWk9uCVNbIhFjv2YKg6HptKU0e
oJT3zRYp+XIjEo7Kfw+TwroZbTlG6gN83l1oBLFMqiFmHsMLnXSI2mm8MXyi3dNB
vR2uIcTAl58KIprqNNsYJ2dNn74ogOMiXYx9XzoA9/5Xb6c0h4rreHJa5t+0s9RO
Gz7Io3PxumgsbJngjyL1Ve5oxhlIAcZA8DU0PQmjxo3eS+k6BcmavGFd45gNL5zg
iLpCh4k86spmzh8CWkAAwWPQE4dZknK6jTctJc0OFVad3Z7+X7n0E8TFrA==
=PM8o
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"Quite a large pull request due to a selftest API overhaul and some
patches that had come in too late for 5.19.
ARM:
- Unwinder implementations for both nVHE modes (classic and
protected), complete with an overflow stack
- Rework of the sysreg access from userspace, with a complete rewrite
of the vgic-v3 view to allign with the rest of the infrastructure
- Disagregation of the vcpu flags in separate sets to better track
their use model.
- A fix for the GICv2-on-v3 selftest
- A small set of cosmetic fixes
RISC-V:
- Track ISA extensions used by Guest using bitmap
- Added system instruction emulation framework
- Added CSR emulation framework
- Added gfp_custom flag in struct kvm_mmu_memory_cache
- Added G-stage ioremap() and iounmap() functions
- Added support for Svpbmt inside Guest
s390:
- add an interface to provide a hypervisor dump for secure guests
- improve selftests to use TAP interface
- enable interpretive execution of zPCI instructions (for PCI
passthrough)
- First part of deferred teardown
- CPU Topology
- PV attestation
- Minor fixes
x86:
- Permit guests to ignore single-bit ECC errors
- Intel IPI virtualization
- Allow getting/setting pending triple fault with
KVM_GET/SET_VCPU_EVENTS
- PEBS virtualization
- Simplify PMU emulation by just using PERF_TYPE_RAW events
- More accurate event reinjection on SVM (avoid retrying
instructions)
- Allow getting/setting the state of the speaker port data bit
- Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls
are inconsistent
- "Notify" VM exit (detect microarchitectural hangs) for Intel
- Use try_cmpxchg64 instead of cmpxchg64
- Ignore benign host accesses to PMU MSRs when PMU is disabled
- Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior
- Allow NX huge page mitigation to be disabled on a per-vm basis
- Port eager page splitting to shadow MMU as well
- Enable CMCI capability by default and handle injected UCNA errors
- Expose pid of vcpu threads in debugfs
- x2AVIC support for AMD
- cleanup PIO emulation
- Fixes for LLDT/LTR emulation
- Don't require refcounted "struct page" to create huge SPTEs
- Miscellaneous cleanups:
- MCE MSR emulation
- Use separate namespaces for guest PTEs and shadow PTEs bitmasks
- PIO emulation
- Reorganize rmap API, mostly around rmap destruction
- Do not workaround very old KVM bugs for L0 that runs with nesting enabled
- new selftests API for CPUID
Generic:
- Fix races in gfn->pfn cache refresh; do not pin pages tracked by
the cache
- new selftests API using struct kvm_vcpu instead of a (vm, id)
tuple"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (606 commits)
selftests: kvm: set rax before vmcall
selftests: KVM: Add exponent check for boolean stats
selftests: KVM: Provide descriptive assertions in kvm_binary_stats_test
selftests: KVM: Check stat name before other fields
KVM: x86/mmu: remove unused variable
RISC-V: KVM: Add support for Svpbmt inside Guest/VM
RISC-V: KVM: Use PAGE_KERNEL_IO in kvm_riscv_gstage_ioremap()
RISC-V: KVM: Add G-stage ioremap() and iounmap() functions
KVM: Add gfp_custom flag in struct kvm_mmu_memory_cache
RISC-V: KVM: Add extensible CSR emulation framework
RISC-V: KVM: Add extensible system instruction emulation framework
RISC-V: KVM: Factor-out instruction emulation into separate sources
RISC-V: KVM: move preempt_disable() call in kvm_arch_vcpu_ioctl_run
RISC-V: KVM: Make kvm_riscv_guest_timer_init a void function
RISC-V: KVM: Fix variable spelling mistake
RISC-V: KVM: Improve ISA extension by using a bitmap
KVM, x86/mmu: Fix the comment around kvm_tdp_mmu_zap_leafs()
KVM: SVM: Dump Virtual Machine Save Area (VMSA) to klog
KVM: x86/mmu: Treat NX as a valid SPTE bit for NPT
KVM: x86: Do not block APIC write for non ICR registers
...
- Fix Intel Alder Lake PEBS memory access latency & data source profiling info bugs.
- Use Intel large-PEBS hardware feature in more circumstances, to reduce
PMI overhead & reduce sampling data.
- Extend the lost-sample profiling output with the PERF_FORMAT_LOST ABI variant,
which tells tooling the exact number of samples lost.
- Add new IBS register bits definitions.
- AMD uncore events: Add PerfMonV2 DF (Data Fabric) enhancements.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=DqaA
-----END PGP SIGNATURE-----
Merge tag 'perf-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf events updates from Ingo Molnar:
- Fix Intel Alder Lake PEBS memory access latency & data source
profiling info bugs.
- Use Intel large-PEBS hardware feature in more circumstances, to
reduce PMI overhead & reduce sampling data.
- Extend the lost-sample profiling output with the PERF_FORMAT_LOST ABI
variant, which tells tooling the exact number of samples lost.
- Add new IBS register bits definitions.
- AMD uncore events: Add PerfMonV2 DF (Data Fabric) enhancements.
* tag 'perf-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/ibs: Add new IBS register bits into header
perf/x86/intel: Fix PEBS data source encoding for ADL
perf/x86/intel: Fix PEBS memory access info encoding for ADL
perf/core: Add a new read format to get a number of lost samples
perf/x86/amd/uncore: Add PerfMonV2 RDPMC assignments
perf/x86/amd/uncore: Add PerfMonV2 DF event format
perf/x86/amd/uncore: Detect available DF counters
perf/x86/amd/uncore: Use attr_update for format attributes
perf/x86/amd/uncore: Use dynamic events array
x86/events/intel/ds: Enable large PEBS for PERF_SAMPLE_WEIGHT_TYPE
KVM/s390, KVM/x86 and common infrastructure changes for 5.20
x86:
* Permit guests to ignore single-bit ECC errors
* Fix races in gfn->pfn cache refresh; do not pin pages tracked by the cache
* Intel IPI virtualization
* Allow getting/setting pending triple fault with KVM_GET/SET_VCPU_EVENTS
* PEBS virtualization
* Simplify PMU emulation by just using PERF_TYPE_RAW events
* More accurate event reinjection on SVM (avoid retrying instructions)
* Allow getting/setting the state of the speaker port data bit
* Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls are inconsistent
* "Notify" VM exit (detect microarchitectural hangs) for Intel
* Cleanups for MCE MSR emulation
s390:
* add an interface to provide a hypervisor dump for secure guests
* improve selftests to use TAP interface
* enable interpretive execution of zPCI instructions (for PCI passthrough)
* First part of deferred teardown
* CPU Topology
* PV attestation
* Minor fixes
Generic:
* new selftests API using struct kvm_vcpu instead of a (vm, id) tuple
x86:
* Use try_cmpxchg64 instead of cmpxchg64
* Bugfixes
* Ignore benign host accesses to PMU MSRs when PMU is disabled
* Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior
* x86/MMU: Allow NX huge pages to be disabled on a per-vm basis
* Port eager page splitting to shadow MMU as well
* Enable CMCI capability by default and handle injected UCNA errors
* Expose pid of vcpu threads in debugfs
* x2AVIC support for AMD
* cleanup PIO emulation
* Fixes for LLDT/LTR emulation
* Don't require refcounted "struct page" to create huge SPTEs
x86 cleanups:
* Use separate namespaces for guest PTEs and shadow PTEs bitmasks
* PIO emulation
* Reorganize rmap API, mostly around rmap destruction
* Do not workaround very old KVM bugs for L0 that runs with nesting enabled
* new selftests API for CPUID
The fuzzer triggers the below trace.
[ 7763.384369] unchecked MSR access error: WRMSR to 0x689
(tried to write 0x1fffffff8101349e) at rIP: 0xffffffff810704a4
(native_write_msr+0x4/0x20)
[ 7763.397420] Call Trace:
[ 7763.399881] <TASK>
[ 7763.401994] intel_pmu_lbr_restore+0x9a/0x1f0
[ 7763.406363] intel_pmu_lbr_sched_task+0x91/0x1c0
[ 7763.410992] __perf_event_task_sched_in+0x1cd/0x240
On a machine with the LBR format LBR_FORMAT_EIP_FLAGS2, when the TSX is
disabled, a TSX quirk is required to access LBR from registers.
The lbr_from_signext_quirk_needed() is introduced to determine whether
the TSX quirk should be applied. However, the
lbr_from_signext_quirk_needed() is invoked before the
intel_pmu_lbr_init(), which parses the LBR format information. Without
the correct LBR format information, the TSX quirk never be applied.
Move the lbr_from_signext_quirk_needed() into the intel_pmu_lbr_init().
Checking x86_pmu.lbr_has_tsx in the lbr_from_signext_quirk_needed() is
not required anymore.
Both LBR_FORMAT_EIP_FLAGS2 and LBR_FORMAT_INFO have LBR_TSX flag, but
only the LBR_FORMAT_EIP_FLAGS2 requirs the quirk. Update the comments
accordingly.
Fixes: 1ac7fd8159 ("perf/x86/intel/lbr: Support LBR format V7")
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20220714182630.342107-1-kan.liang@linux.intel.com
The PEBS data source encoding for the e-core is different from the
p-core.
Add the pebs_data_source[] in the struct x86_hybrid_pmu to store the
data source encoding for each type of the core.
Add intel_pmu_pebs_data_source_grt() for the e-core.
There is nothing changed for the data source encoding of the p-core,
which still reuse the intel_pmu_pebs_data_source_skl().
Fixes: f83d2f91d2 ("perf/x86/intel: Add Alder Lake Hybrid support")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20220629150840.2235741-2-kan.liang@linux.intel.com
The PEBS memory access latency encoding for the e-core is slightly
different from the p-core. The bit 4 is Lock, while the bit 5 is TLB
access.
Add a new flag to indicate the load/store latency event on a hybrid
platform.
Add a new function pointer to retrieve the latency data for a hybrid
platform. Only implement the new flag and function for the e-core on
ADL. Still use the existing PERF_X86_EVENT_PEBS_LDLAT/STLAT flag for the
p-core on ADL.
Factor out pebs_set_tlb_lock() to set the generic memory data source
information of the TLB access and lock for both load and store latency.
Move the intel_get_event_constraints() to ahead of the :ppp check,
otherwise the new flag never gets a chance to be set for the :ppp
events.
Fixes: f83d2f91d2 ("perf/x86/intel: Add Alder Lake Hybrid support")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20220629150840.2235741-1-kan.liang@linux.intel.com
The current RDPMC assignment scheme maps four DF PMCs and
six L3 PMCs from index 6 to 15.
If AMD Performance Monitoring Version 2 (PerfMonV2) is
supported, there may be additional DF counters available
which are mapped starting from index 16 i.e. just after
the L3 counters. Update the RDPMC assignments accordingly.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/1359379ef34da760f108b075ac138ab082caa3ba.1652954372.git.sandipan.das@amd.com
If AMD Performance Monitoring Version 2 (PerfMonV2) is
supported, use CPUID leaf 0x80000022 EBX to detect the
number of Data Fabric (DF) PMCs. This offers more
flexibility if the counts change in later processor
families.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/bac7b2806561e03f2acc7fdc9db94f102df80e1d.1652954372.git.sandipan.das@amd.com
Use the update_attrs attribute group introduced by commit
f3a3a8257e ("perf/core: Add attr_groups_update into struct
pmu") and the is_visible() callback to populate the family
specifc attributes for uncore events.
The changes apply to attributes that are unique to families
such as slicemask for Family 17h and coreid for Family 19h.
The addition of common attributes such as event and umask,
whose formats change across families, remain unchanged.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/a5e4f4dd5c459199fc497e82b858ba09dc91c064.1652954372.git.sandipan.das@amd.com
If AMD Performance Monitoring Version 2 (PerfMonV2) is
supported, the number of available counters for a given
uncore PMU may not be fixed across families and models
and has to be determined at runtime.
The per-cpu uncore PMU data currently uses a fixed-sized
array for event information. Make it dynamic based on the
number of available counters.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/21eea0cb6de9d14f78d52d1d62637ae02bc900f5.1652954372.git.sandipan.das@amd.com
All the information required by the PERF_SAMPLE_WEIGHT is
available in the pebs record. Thus large PEBS could be enabled
for PERF_SAMPLE_WEIGHT sample type to save PMIs overhead until
other non-compatible flags such as PERF_SAMPLE_DATA_PAGE_SIZE
(due to lack of munmap tracking) stop it.
To cover new weight extension, add PERF_SAMPLE_WEIGHT_TYPE
to the guardian LARGE_PEBS_FLAGS.
Tested it with:
$ perf mem record -c 1000 workload
Before: Captured and wrote 0.126 MB perf.data (958 samples) [958 PMIs]
After: Captured and wrote 0.313 MB perf.data (4859 samples) [3 PMIs]
Reported-by: Yongchao Duan <yongduan@tencent.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220519151913.80545-1-likexu@tencent.com
If the PMU is broken due to firmware issues, check_hw_exists() will return
false but perf_get_x86_pmu_capability() will still return data from x86_pmu.
Likewise if some of the hotplug callbacks cannot be installed the contents
of x86_pmu will not be reverted.
Handle the failure in both cases by clearing x86_pmu if init_hw_perf_events()
or reverts to software events only.
Co-developed-by: Like Xu <likexu@tencent.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Starting from v5.12, KVM reports guest LBR and extra_regs support
when the host has relevant support. Just delete this part of the
comment and fix a typo incidentally.
Cc: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
Message-Id: <20220517154100.29983-2-weijiang.yang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently, we have [intel|knc|p4|p6]_perfmon_event_map on the Intel
platforms and amd_[f17h]_perfmon_event_map on the AMD platforms.
Early clumsy KVM code or other potential perf_event users may have
hard-coded these perfmon_maps (e.g., arch/x86/kvm/svm/pmu.c), so
it would not make sense to program a common hardware event based
on the generic "enum perf_hw_id" once the two tables do not match.
Let's provide an interface for callers outside the perf subsystem to get
the counter config based on the perfmon_event_map currently in use,
and it also helps to save bytes.
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Like Xu <likexu@tencent.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220518132512.37864-10-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The guest PEBS will be disabled when some users try to perf KVM and
its user-space through the same PEBS facility OR when the host perf
doesn't schedule the guest PEBS counter in a one-to-one mapping manner
(neither of these are typical scenarios).
The PEBS records in the guest DS buffer are still accurate and the
above two restrictions will be checked before each vm-entry only if
guest PEBS is deemed to be enabled.
Suggested-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-15-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If IA32_PERF_CAPABILITIES.PEBS_BASELINE [bit 14] is set, the adaptive
PEBS is supported. The PEBS_DATA_CFG MSR and adaptive record enable
bits (IA32_PERFEVTSELx.Adaptive_Record and IA32_FIXED_CTR_CTRL.
FCx_Adaptive_Record) are also supported.
Adaptive PEBS provides software the capability to configure the PEBS
records to capture only the data of interest, keeping the record size
compact. An overflow of PMCx results in generation of an adaptive PEBS
record with state information based on the selections specified in
MSR_PEBS_DATA_CFG.By default, the record only contain the Basic group.
When guest adaptive PEBS is enabled, the IA32_PEBS_ENABLE MSR will
be added to the perf_guest_switch_msr() and switched during the VMX
transitions just like CORE_PERF_GLOBAL_CTRL MSR.
According to Intel SDM, software is recommended to PEBS Baseline
when the following is true. IA32_PERF_CAPABILITIES.PEBS_BASELINE[14]
&& IA32_PERF_CAPABILITIES.PEBS_FMT[11:8] ≥ 4.
Co-developed-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220411101946.20262-12-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When CPUID.01H:EDX.DS[21] is set, the IA32_DS_AREA MSR exists and points
to the linear address of the first byte of the DS buffer management area,
which is used to manage the PEBS records.
When guest PEBS is enabled, the MSR_IA32_DS_AREA MSR will be added to the
perf_guest_switch_msr() and switched during the VMX transitions just like
CORE_PERF_GLOBAL_CTRL MSR. The WRMSR to IA32_DS_AREA MSR brings a #GP(0)
if the source register contains a non-canonical address.
Originally-by: Andi Kleen <ak@linux.intel.com>
Co-developed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-11-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The PEBS-PDIR facility on Ice Lake server is supported on IA31_FIXED0 only.
If the guest configures counter 32 and PEBS is enabled, the PEBS-PDIR
facility is supposed to be used, in which case KVM adjusts attr.precise_ip
to 3 and request host perf to assign the exactly requested counter or fail.
The CPU model check is also required since some platforms may place the
PEBS-PDIR facility in another counter index.
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-10-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If IA32_PERF_CAPABILITIES.PEBS_BASELINE [bit 14] is set, the
IA32_PEBS_ENABLE MSR exists and all architecturally enumerated fixed
and general-purpose counters have corresponding bits in IA32_PEBS_ENABLE
that enable generation of PEBS records. The general-purpose counter bits
start at bit IA32_PEBS_ENABLE[0], and the fixed counter bits start at
bit IA32_PEBS_ENABLE[32].
When guest PEBS is enabled, the IA32_PEBS_ENABLE MSR will be
added to the perf_guest_switch_msr() and atomically switched during
the VMX transitions just like CORE_PERF_GLOBAL_CTRL MSR.
Based on whether the platform supports x86_pmu.pebs_ept, it has also
refactored the way to add more msrs to arr[] in intel_guest_get_msrs()
for extensibility.
Originally-by: Andi Kleen <ak@linux.intel.com>
Co-developed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Co-developed-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-8-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The value of pebs_counter_mask will be accessed frequently
for repeated use in the intel_guest_get_msrs(). So it can be
optimized instead of endlessly mucking about with branches.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-7-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Splitting the logic for determining the guest values is unnecessarily
confusing, and potentially fragile. Perf should have full knowledge and
control of what values are loaded for the guest.
If we change .guest_get_msrs() to take a struct kvm_pmu pointer, then it
can generate the full set of guest values by grabbing guest ds_area and
pebs_data_cfg. Alternatively, .guest_get_msrs() could take the desired
guest MSR values directly (ds_area and pebs_data_cfg), but kvm_pmu is
vendor agnostic, so we don't see any reason to not just pass the pointer.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-4-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
With PEBS virtualization, the guest PEBS records get delivered to the
guest DS, and the host pmi handler uses perf_guest_cbs->is_in_guest()
to distinguish whether the PMI comes from the guest code like Intel PT.
No matter how many guest PEBS counters are overflowed, only triggering
one fake event is enough. The fake event causes the KVM PMI callback to
be called, thereby injecting the PEBS overflow PMI into the guest.
KVM may inject the PMI with BUFFER_OVF set, even if the guest DS is
empty. That should really be harmless. Thus guest PEBS handler would
retrieve the correct information from its own PEBS records buffer.
Cc: linux-perf-users@vger.kernel.org
Originally-by: Andi Kleen <ak@linux.intel.com>
Co-developed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220411101946.20262-3-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add support for EPT-Friendly PEBS, a new CPU feature that enlightens PEBS
to translate guest linear address through EPT, and facilitates handling
VM-Exits that occur when accessing PEBS records. More information can
be found in the December 2021 release of Intel's SDM, Volume 3,
18.9.5 "EPT-Friendly PEBS". This new hardware facility makes sure the
guest PEBS records will not be lost, which is available on Intel Ice Lake
Server platforms (and later).
KVM will check this field through perf_get_x86_pmu_capability() instead
of hard coding the CPU models in the KVM code. If it is supported, the
guest PEBS capability will be exposed to the guest. Guest PEBS can be
enabled when and only when "EPT-Friendly PEBS" is supported and
EPT is enabled.
Cc: linux-perf-users@vger.kernel.org
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20220411101946.20262-2-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
- Make the ICL event constraints match reality
- Remove a unused local variable
-----BEGIN PGP SIGNATURE-----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=ZK+2
-----END PGP SIGNATURE-----
Merge tag 'perf-urgent-2022-06-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Thomas Gleixner:
- Make the ICL event constraints match reality
- Remove a unused local variable
* tag 'perf-urgent-2022-06-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/core: Remove unused local variable
perf/x86/intel: Fix event constraints for ICL
According to the latest event list, the event encoding 0x55
INST_DECODED.DECODERS and 0x56 UOPS_DECODED.DEC0 are only available on
the first 4 counters. Add them into the event constraints table.
Fixes: 6017608936 ("perf/x86/intel: Add Icelake support")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20220525133952.1660658-1-kan.liang@linux.intel.com
The convention for indentation seems to be a single tab. Help text is
further indented by an additional two whitespaces. Fix the lines that
violate these rules.
Signed-off-by: Juerg Haefliger <juerg.haefliger@canonical.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20220525133949.53730-1-juerg.haefliger@canonical.com
Commit 1018faa6cf ("perf/x86/kvm: Fix Host-Only/Guest-Only
counting with SVM disabled") addresses an issue in which the
Host-Only bit in the counter control registers needs to be
masked off when SVM is not enabled.
The events need to be reloaded whenever SVM is enabled or
disabled for a CPU and this requires the PERF_CTL registers
to be reprogrammed using {enable,disable}_all(). However,
PerfMonV2 variants of these functions do not reprogram the
PERF_CTL registers. Hence, the legacy enable_all() function
should also be called.
Fixes: 9622e67e39 ("perf/x86/amd/core: Add PerfMonV2 counter control")
Reported-by: Like Xu <likexu@tencent.com>
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220518084327.464005-1-sandipan.das@amd.com
There's two problems with the current amd_brs_adjust_period() code:
- it isn't in fact AMD specific and wil always adjust the period;
- it adjusts the period, while it should only adjust the event count,
resulting in repoting a short period.
Fix this by using x86_pmu.limit_period, this makes it specific to the
AMD BRS case and ensures only the event count is adjusted while the
reported period is unmodified.
Fixes: ba2fe75008 ("perf/x86/amd: Add AMD branch sampling period adjustment")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
PMU driver can advertise certain feature via capability attribute('caps'
sysfs directory) which can be consumed by userspace tools like perf. Add
zen4_ibs_extensions capability attribute for IBS pmus. This attribute
will be enabled when CPUID_Fn8000001B_EAX[11] is set.
With patch on Zen4:
$ ls /sys/bus/event_source/devices/ibs_op/caps
zen4_ibs_extensions
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220509044914.1473-5-ravi.bangoria@amd.com
IBS L3 miss filtering works by tagging an instruction on IBS counter
overflow and generating an NMI if the tagged instruction causes an L3
miss. Samples without an L3 miss are discarded and counter is reset
with random value (between 1-15 for fetch pmu and 1-127 for op pmu).
This helps in reducing sampling overhead when user is interested only
in such samples. One of the use case of such filtered samples is to
feed data to page-migration daemon in tiered memory systems.
Add support for L3 miss filtering in IBS driver via new pmu attribute
"l3missonly". Example usage:
# perf record -a -e ibs_op/l3missonly=1/ --raw-samples sleep 5
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220509044914.1473-4-ravi.bangoria@amd.com
Currently, some attributes are added at build time whereas others
at boot time depending on IBS pmu capabilities. Instead, we can
just add all attribute groups at build time but hide individual
group at boot time using more appropriate ->is_visible() callback.
Also, struct perf_ibs has bunch of fields for pmu attributes which
just pass on the pointer, does not do anything else. Remove them.
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220509044914.1473-3-ravi.bangoria@amd.com
IBS pmu initialization code ignores return value provided by
callee functions. Fix it.
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220509044914.1473-2-ravi.bangoria@amd.com
From the perspective of the uncore PMU, there is nothing changed for the
new Alder Lake N and Raptor Lake P.
Add new PCIIDs of IMC.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220504194413.1003071-5-kan.liang@linux.intel.com
The initialization code to assign PCI IDs for different platforms is
similar. Add the new macros to reduce the redundant code.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220504194413.1003071-4-kan.liang@linux.intel.com
From the perspective of Intel cstate residency counters, there is nothing
changed for the new Alder Lake N and Raptor Lake P.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220504194413.1003071-3-kan.liang@linux.intel.com
IbsOpRip is recorded when IBS interrupt is triggered. But there is
a skid from the time IBS interrupt gets triggered to the time the
interrupt is presented to the core. Meanwhile processor would have
moved ahead and thus IbsOpRip will be inconsistent with rsp and rbp
recorded as part of the interrupt regs. This causes issues while
unwinding stack using the ORC unwinder as it needs consistent rip,
rsp and rbp. Fix this by using rip from interrupt regs instead of
IbsOpRip for stack unwinding.
Fixes: ee9f8fce99 ("x86/unwind: Add the ORC unwinder")
Reported-by: Dmitry Monakhov <dmtrmonakhov@yandex-team.ru>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220429051441.14251-1-ravi.bangoria@amd.com
If AMD Performance Monitoring Version 2 (PerfMonV2) is
supported, use a new scheme to process Core PMC overflows
in the NMI handler using the new global control and status
registers. This will be bypassed on unsupported hardware
(x86_pmu.version < 2).
In x86_pmu_handle_irq(), overflows are detected by testing
the contents of the PERF_CTR register for each active PMC in
a loop. The new scheme instead inspects the overflow bits of
the global status register.
The Performance Counter Global Status (PerfCntrGlobalStatus)
register has overflow (PerfCntrOvfl) bits for each PMC. This
is, however, a read-only MSR. To acknowledge that overflows
have been processed, the NMI handler must clear the bits by
writing to the PerfCntrGlobalStatusClr register.
In x86_pmu_handle_irq(), PMCs counting the same event that
are started and stopped at the same time record slightly
different counts due to delays in between reads from the
PERF_CTR registers. This is fixed by stopping and starting
the PMCs at the same before and with a single write to the
Performance Counter Global Control (PerfCntrGlobalCtl) upon
entering and before exiting the NMI handler.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/f20b7e4da0b0a83bdbe05857f354146623bc63ab.1650515382.git.sandipan.das@amd.com
If AMD Performance Monitoring Version 2 (PerfMonV2) is
supported, use a new scheme to manage the Core PMCs using
the new global control and status registers. This will be
bypassed on unsupported hardware (x86_pmu.version < 2).
Currently, all PMCs have dedicated control (PERF_CTL) and
counter (PERF_CTR) registers. For a given PMC, the enable
(En) bit of its PERF_CTL register is used to start or stop
counting.
The Performance Counter Global Control (PerfCntrGlobalCtl)
register has enable (PerfCntrEn) bits for each PMC. For a
PMC to start counting, both PERF_CTL and PerfCntrGlobalCtl
enable bits must be set. If either of those are cleared,
the PMC stops counting.
In x86_pmu_{en,dis}able_all(), the PERF_CTL registers of
all active PMCs are written to in a loop. Ideally, PMCs
counting the same event that were started and stopped at
the same time should record the same counts. Due to delays
in between writes to the PERF_CTL registers across loop
iterations, the PMCs cannot be enabled or disabled at the
same instant and hence, record slightly different counts.
This is fixed by enabling or disabling all active PMCs at
the same time with a single write to the PerfCntrGlobalCtl
register.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/dfe8e934074aaabc6ba748dfaccd0a77c974bb82.1650515382.git.sandipan.das@amd.com
If AMD Performance Monitoring Version 2 (PerfMonV2) is
supported, use CPUID leaf 0x80000022 EBX to detect the
number of Core PMCs. This offers more flexibility if the
counts change in later processor families.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/68a6d9688df189267db26530378870edd34f7b06.1650515382.git.sandipan.das@amd.com
AMD Performance Monitoring Version 2 (PerfMonV2) introduces
some new Core PMU features such as detection of the number
of available PMCs and managing PMCs using global registers
namely, PerfCntrGlobalCtl and PerfCntrGlobalStatus.
Clearing PerfCntrGlobalCtl and PerfCntrGlobalStatus ensures
that all PMCs are inactive and have no pending overflows
when CPUs are onlined or offlined.
The PMU version (x86_pmu.version) now indicates PerfMonV2
support and will be used to bypass the new features on
unsupported processors.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/dc8672ecbddff394e088ca8abf94b089b8ecc2e7.1650515382.git.sandipan.das@amd.com
From the perspective of Intel cstate residency counters,
SAPPHIRERAPIDS_X is the same as ICELAKE_X.
Share the code with it. And update the comments for SAPPHIRERAPIDS_X.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lkml.kernel.org/r/20220415104520.2737004-1-rui.zhang@intel.com
Sysfs show formats of files in /sys/devices/cpu/events/ are not unified,
some end with "\n", and some do not. Modify sysfs show format of events
defined by EVENT_ATTR_STR to end with "\n".
Before:
$ ls /sys/devices/cpu/events/* | xargs -i sh -c 'echo -n "{}: "; cat -A {}; echo'
branch-instructions: event=0xc4$
branch-misses: event=0xc5$
bus-cycles: event=0x3c,umask=0x01$
cache-misses: event=0x2e,umask=0x41$
cache-references: event=0x2e,umask=0x4f$
cpu-cycles: event=0x3c$
instructions: event=0xc0$
ref-cycles: event=0x00,umask=0x03$
slots: event=0x00,umask=0x4
topdown-bad-spec: event=0x00,umask=0x81
topdown-be-bound: event=0x00,umask=0x83
topdown-fe-bound: event=0x00,umask=0x82
topdown-retiring: event=0x00,umask=0x80
After:
$ ls /sys/devices/cpu/events/* | xargs -i sh -c 'echo -n "{}: "; cat -A {}; echo'
/sys/devices/cpu/events/branch-instructions: event=0xc4$
/sys/devices/cpu/events/branch-misses: event=0xc5$
/sys/devices/cpu/events/bus-cycles: event=0x3c,umask=0x01$
/sys/devices/cpu/events/cache-misses: event=0x2e,umask=0x41$
/sys/devices/cpu/events/cache-references: event=0x2e,umask=0x4f$
/sys/devices/cpu/events/cpu-cycles: event=0x3c$
/sys/devices/cpu/events/instructions: event=0xc0$
/sys/devices/cpu/events/ref-cycles: event=0x00,umask=0x03$
/sys/devices/cpu/events/slots: event=0x00,umask=0x4$
Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220324031957.135595-1-yangjihong1@huawei.com
On AMD Fam19h Zen3, the branch sampling (BRS) feature must be disabled before
entering low power and re-enabled (if was active) when returning from low
power. Otherwise, the NMI interrupt may be held up for too long and cause
problems. Stopping BRS will cause the NMI to be delivered if it was held up.
Define a perf_amd_brs_lopwr_cb() callback to stop/restart BRS. The callback
is protected by a jump label which is enabled only when AMD BRS is detected.
In all other cases, the callback is never called.
Signed-off-by: Stephane Eranian <eranian@google.com>
[peterz: static_call() and build fixes]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-10-eranian@google.com
Add a kernel config option CONFIG_PERF_EVENTS_AMD_BRS
to make the support for AMD Zen3 Branch Sampling (BRS) an opt-in
compile time option.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-8-eranian@google.com
Add code to adjust the sampling event period when used with the Branch
Sampling feature (BRS). Given the depth of the BRS (16), the period is
reduced by that depth such that in the best case scenario, BRS saturates at
the desired sampling period. In practice, though, the processor may execute
more branches. Given a desired period P and a depth D, the kernel programs
the actual period at P - D. After P occurrences of the sampling event, the
counter overflows. It then may take X branches (skid) before the NMI is
caught and held by the hardware and BRS activates. Then, after D branches,
BRS saturates and the NMI is delivered. With no skid, the effective period
would be (P - D) + D = P. In practice, however, it will likely be (P - D) +
X + D. There is no way to eliminate X or predict X.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-7-eranian@google.com
The AMD Branch Sampling features does not provide hardware filtering by
privilege level. The associated PMU counter does but not the branch sampling
by itself. Given how BRS operates there is a possibility that BRS captures
kernel level branches even though the event is programmed to count only at
the user level.
Implement a workaround in software by removing the branches which belong to
the wrong privilege level. The privilege level is evaluated on the target of
the branch and not the source so as to be compatible with other architectures.
As a consequence of this patch, the number of entries in the
PERF_RECORD_BRANCH_STACK buffer may be less than the maximum (16). It could
even be zero. Another consequence is that consecutive entries in the branch
stack may not reflect actual code path and may have discontinuities, in case
kernel branches were suppressed. But this is no different than what happens
on other architectures.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-6-eranian@google.com
Add a pseudo event called branch-brs to help use the FAM Fam19h
Branch Sampling feature (BRS). BRS samples taken branches, so it is best used
when sampling on a retired taken branch event (0xc4) which is what BRS
captures. Instead of trying to remember the event code or actual event name,
users can simply do:
$ perf record -b -e cpu/branch-brs/ -c 1000037 .....
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-5-eranian@google.com
Add support for the AMD Fam19h 16-deep branch sampling feature as
described in the AMD PPR Fam19h Model 01h Revision B1. This is a model
specific extension. It is not an architected AMD feature.
The Branch Sampling (BRS) operates with a 16-deep saturating buffer in MSR
registers. There is no branch type filtering. All control flow changes are
captured. BRS relies on specific programming of the core PMU of Fam19h. In
particular, the following requirements must be met:
- the sampling period be greater than 16 (BRS depth)
- the sampling period must use a fixed and not frequency mode
BRS interacts with the NMI interrupt as well. Because enabling BRS is
expensive, it is only activated after P event occurrences, where P is the
desired sampling period. At P occurrences of the event, the counter
overflows, the CPU catches the interrupt, activates BRS for 16 branches until
it saturates, and then delivers the NMI to the kernel. Between the overflow
and the time BRS activates more branches may be executed skewing the period.
All along, the sampling event keeps counting. The skid may be attenuated by
reducing the sampling period by 16 (subsequent patch).
BRS is integrated into perf_events seamlessly via the same
PERF_RECORD_BRANCH_STACK sample format. BRS generates perf_branch_entry
records in the sampling buffer. No prediction information is supported. The
branches are stored in reverse order of execution. The most recent branch is
the first entry in each record.
No modification to the perf tool is necessary.
BRS can be used with any sampling event. However, it is recommended to use
the RETIRED_BRANCH_INSTRUCTIONS event because it matches what the BRS
captures.
$ perf record -b -c 1000037 -e cpu/event=0xc2,name=ret_br_instructions/ test
$ perf report -D
56531696056126 0x193c000 [0x1a8]: PERF_RECORD_SAMPLE(IP, 0x2): 18122/18230: 0x401d24 period: 1000037 addr: 0
... branch stack: nr:16
..... 0: 0000000000401d24 -> 0000000000401d5a 0 cycles 0
..... 1: 0000000000401d5c -> 0000000000401d24 0 cycles 0
..... 2: 0000000000401d22 -> 0000000000401d5c 0 cycles 0
..... 3: 0000000000401d5e -> 0000000000401d22 0 cycles 0
..... 4: 0000000000401d20 -> 0000000000401d5e 0 cycles 0
..... 5: 0000000000401d3e -> 0000000000401d20 0 cycles 0
..... 6: 0000000000401d42 -> 0000000000401d3e 0 cycles 0
..... 7: 0000000000401d3c -> 0000000000401d42 0 cycles 0
..... 8: 0000000000401d44 -> 0000000000401d3c 0 cycles 0
..... 9: 0000000000401d3a -> 0000000000401d44 0 cycles 0
..... 10: 0000000000401d46 -> 0000000000401d3a 0 cycles 0
..... 11: 0000000000401d38 -> 0000000000401d46 0 cycles 0
..... 12: 0000000000401d48 -> 0000000000401d38 0 cycles 0
..... 13: 0000000000401d36 -> 0000000000401d48 0 cycles 0
..... 14: 0000000000401d4a -> 0000000000401d36 0 cycles 0
..... 15: 0000000000401d34 -> 0000000000401d4a 0 cycles 0
... thread: test:18230
...... dso: test
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-4-eranian@google.com
Make it simpler to reset all the info fields on the
perf_branch_entry by adding a helper inline function.
The goal is to centralize the initialization to avoid missing
a field in case more are added.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220322221517.2510440-2-eranian@google.com
On Sapphire Rapids, the FRONTEND_RETIRED.MS_FLOWS event requires the
FRONTEND MSR value 0x8. However, the current FRONTEND MSR mask doesn't
support it.
Update intel_spr_extra_regs[] to support it.
Fixes: 61b985e3e7 ("perf/x86/intel: Add perf core PMU support for Sapphire Rapids")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/1648482543-14923-2-git-send-email-kan.liang@linux.intel.com
The INST_RETIRED.PREC_DIST event (0x0100) doesn't count on SPR.
perf stat -e cpu/event=0xc0,umask=0x0/,cpu/event=0x0,umask=0x1/ -C0
Performance counter stats for 'CPU(s) 0':
607,246 cpu/event=0xc0,umask=0x0/
0 cpu/event=0x0,umask=0x1/
The encoding for INST_RETIRED.PREC_DIST is pseudo-encoding, which
doesn't work on the generic counters. However, current perf extends its
mask to the generic counters.
The pseudo event-code for a fixed counter must be 0x00. Check and avoid
extending the mask for the fixed counter event which using the
pseudo-encoding, e.g., ref-cycles and PREC_DIST event.
With the patch,
perf stat -e cpu/event=0xc0,umask=0x0/,cpu/event=0x0,umask=0x1/ -C0
Performance counter stats for 'CPU(s) 0':
583,184 cpu/event=0xc0,umask=0x0/
583,048 cpu/event=0x0,umask=0x1/
Fixes: 2de71ee153 ("perf/x86/intel: Fix ICL/SPR INST_RETIRED.PREC_DIST encodings")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1648482543-14923-1-git-send-email-kan.liang@linux.intel.com
Raptor Lake is Intel's successor to Alder lake. From the perspective of
Intel cstate residency counters, there is nothing changed compared with
Alder lake.
Share adl_cstates with Alder lake.
Update the comments for Raptor Lake.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/1647366360-82824-2-git-send-email-kan.liang@linux.intel.com
From PMU's perspective, Raptor Lake is the same as the Alder Lake. The
only difference is the event list, which will be supported in the perf
tool later.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/1647366360-82824-1-git-send-email-kan.liang@linux.intel.com
There are three sets of updates for 5.18 in the asm-generic tree:
- The set_fs()/get_fs() infrastructure gets removed for good. This
was already gone from all major architectures, but now we can
finally remove it everywhere, which loses some particularly
tricky and error-prone code.
There is a small merge conflict against a parisc cleanup, the
solution is to use their new version.
- The nds32 architecture ends its tenure in the Linux kernel. The
hardware is still used and the code is in reasonable shape, but
the mainline port is not actively maintained any more, as all
remaining users are thought to run vendor kernels that would never
be updated to a future release.
There are some obvious conflicts against changes to the removed
files.
- A series from Masahiro Yamada cleans up some of the uapi header
files to pass the compile-time checks.
-----BEGIN PGP SIGNATURE-----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=vtCN
-----END PGP SIGNATURE-----
Merge tag 'asm-generic-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic
Pull asm-generic updates from Arnd Bergmann:
"There are three sets of updates for 5.18 in the asm-generic tree:
- The set_fs()/get_fs() infrastructure gets removed for good.
This was already gone from all major architectures, but now we can
finally remove it everywhere, which loses some particularly tricky
and error-prone code. There is a small merge conflict against a
parisc cleanup, the solution is to use their new version.
- The nds32 architecture ends its tenure in the Linux kernel.
The hardware is still used and the code is in reasonable shape, but
the mainline port is not actively maintained any more, as all
remaining users are thought to run vendor kernels that would never
be updated to a future release.
- A series from Masahiro Yamada cleans up some of the uapi header
files to pass the compile-time checks"
* tag 'asm-generic-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic: (27 commits)
nds32: Remove the architecture
uaccess: remove CONFIG_SET_FS
ia64: remove CONFIG_SET_FS support
sh: remove CONFIG_SET_FS support
sparc64: remove CONFIG_SET_FS support
lib/test_lockup: fix kernel pointer check for separate address spaces
uaccess: generalize access_ok()
uaccess: fix type mismatch warnings from access_ok()
arm64: simplify access_ok()
m68k: fix access_ok for coldfire
MIPS: use simpler access_ok()
MIPS: Handle address errors for accesses above CPU max virtual user address
uaccess: add generic __{get,put}_kernel_nofault
nios2: drop access_ok() check from __put_user()
x86: use more conventional access_ok() definition
x86: remove __range_not_ok()
sparc64: add __{get,put}_kernel_nofault()
nds32: fix access_ok() checks in get/put_user
uaccess: fix nios2 and microblaze get_user_8()
sparc64: fix building assembly files
...
- Fix address filtering for Intel/PT,ARM/CoreSight
- Enable Intel/PEBS format 5
- Allow more fixed-function counters for x86
- Intel/PT: Enable not recording Taken-Not-Taken packets
- Add a few branch-types
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=XPuo
-----END PGP SIGNATURE-----
Merge tag 'perf-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 perf event updates from Ingo Molnar:
- Fix address filtering for Intel/PT,ARM/CoreSight
- Enable Intel/PEBS format 5
- Allow more fixed-function counters for x86
- Intel/PT: Enable not recording Taken-Not-Taken packets
- Add a few branch-types
* tag 'perf-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel/uncore: Fix the build on !CONFIG_PHYS_ADDR_T_64BIT
perf: Add irq and exception return branch types
perf/x86/intel/uncore: Make uncore_discovery clean for 64 bit addresses
perf/x86/intel/pt: Add a capability and config bit for disabling TNTs
perf/x86/intel/pt: Add a capability and config bit for event tracing
perf/x86/intel: Increase max number of the fixed counters
KVM: x86: use the KVM side max supported fixed counter
perf/x86/intel: Enable PEBS format 5
perf/core: Allow kernel address filter when not filtering the kernel
perf/x86/intel/pt: Fix address filter config for 32-bit kernel
perf/core: Fix address filter parser for multiple filters
x86: Share definition of __is_canonical_address()
perf/x86/intel/pt: Relax address filter validation
This expands generic branch type classification by adding two more entries
there in i.e irq and exception return. Also updates the x86 implementation
to process X86_BR_IRET and X86_BR_IRQ records as appropriate. This changes
branch types reported to user space on x86 platform but it should not be a
problem. The possible scenarios and impacts are enumerated here.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1645681014-3346-1-git-send-email-anshuman.khandual@arm.com
Support 64-bit BAR size for discovery, and do not truncate return from
generic_uncore_mmio_box_ctl() to 32 bits.
Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20220218175418.421268-1-steve.wahl@hpe.com
The __range_not_ok() helper is an x86 (and sparc64) specific interface
that does roughly the same thing as __access_ok(), but with different
calling conventions.
Change this to use the normal interface in order for consistency as we
clean up all access_ok() implementations.
This changes the limit from TASK_SIZE to TASK_SIZE_MAX, which Al points
out is the right thing do do here anyway.
The callers have to use __access_ok() instead of the normal access_ok()
though, because on x86 that contains a WARN_ON_IN_IRQ() check that cannot
be used inside of NMI context while tracing.
The check in copy_code() is not needed any more, because this one is
already done by copy_from_user_nmi().
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Link: https://lore.kernel.org/lkml/YgsUKcXGR7r4nINj@zeniv-ca.linux.org.uk/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
As of Intel SDM (https://www.intel.com/sdm) version 076, there is a new
Intel PT feature called TNT-Disable which is enabled config bit 55.
TNT-Disable disables Taken-Not-Taken packets to reduce the tracing
overhead, but with the result that exact control flow information is
lost.
Add a capability and config bit for TNT-Disable.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20220126104815.2807416-3-adrian.hunter@intel.com
As of Intel SDM (https://www.intel.com/sdm) version 076, there is a new
Intel PT feature called Event Trace which is enabled config bit 31.
Event Trace exposes details about asynchronous events such as interrupts
and VM-Entry/Exit.
Add a capability and config bit for Event Trace.
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20220126104815.2807416-2-adrian.hunter@intel.com
The new PEBS format 5 implies that the number of the fixed counters can
be up to 16. The current INTEL_PMC_MAX_FIXED is still 4. If the current
kernel runs on a future platform which has more than 4 fixed counters,
a warning will be triggered. The number of the fixed counters will be
clipped to 4. Users have to upgrade the kernel to access the new fixed
counters.
Add a new default constraint for PerfMon v5 and up, which can support
up to 16 fixed counters. The pseudo-encoding is applied for the fixed
counters 4 and later. The user can have generic support for the new
fixed counters on the future platfroms without updating the kernel.
Increase the INTEL_PMC_MAX_FIXED to 16.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/1643750603-100733-3-git-send-email-kan.liang@linux.intel.com
The new PEBS Record Format 5 is similar to the PEBS Record Format 4. The
only difference is the layout of the Counter Reset fields of the PEBS
Config Buffer in the DS area. For the PEBS format 4, the Counter Reset
fields allocation is for 8 general-purpose counters followed by 4
fixed-function counters. For the PEBS format 5, the Counter Reset fields
allocation is for 32 general-purpose counters followed by 16
fixed-function counters.
Extend the MAX_PEBS_EVENTS to 32. Add MAX_PEBS_EVENTS_FMT4 for the
previous platform. Except for the DS auto-reload code, other places
already assume 32 counters. Only check the PEBS_FMT in the DS
auto-reload code.
Extend the MAX_FIXED_PEBS_EVENTS to 16, which only impacts the size of
struct debug_store and some local temporary variables. The size of
struct debug_store increases 288B, which is small and should be
acceptable.
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/1643750603-100733-1-git-send-email-kan.liang@linux.intel.com
Change from shifting 'unsigned long' to 'u64' to prevent the config bits
being lost on a 32-bit kernel.
Fixes: eadf48cab4 ("perf/x86/intel/pt: Add support for address range filtering in PT")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220131072453.2839535-5-adrian.hunter@intel.com
The requirement for 64-bit address filters is that they are canonical
addresses. In other respects any address range is allowed which would
include user space addresses.
That can be useful for tracing virtual machine guests because address
filtering can be used to advantage in place of current privilege level
(CPL) filtering.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220131072453.2839535-2-adrian.hunter@intel.com
Add a check for !buf->single before calling pt_buffer_region_size in a
place where a missing check can cause a kernel crash.
Fixes a bug introduced by commit 670638477a ("perf/x86/intel/pt:
Opportunistically use single range output mode"), which added a
support for PT single-range output mode. Since that commit if a PT
stop filter range is hit while tracing, the kernel will crash because
of a null pointer dereference in pt_handle_status due to calling
pt_buffer_region_size without a ToPA configured.
The commit which introduced single-range mode guarded almost all uses of
the ToPA buffer variables with checks of the buf->single variable, but
missed the case where tracing was stopped by the PT hardware, which
happens when execution hits a configured stop filter.
Tested that hitting a stop filter while PT recording successfully
records a trace with this patch but crashes without this patch.
Fixes: 670638477a ("perf/x86/intel/pt: Opportunistically use single range output mode")
Signed-off-by: Tristan Hume <tristan@thume.ca>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: stable@kernel.org
Link: https://lkml.kernel.org/r/20220127220806.73664-1-tristan@thume.ca
Kyle reported that rr[0] has started to malfunction on Comet Lake and
later CPUs due to EFI starting to make use of CPL3 [1] and the PMU
event filtering not distinguishing between regular CPL3 and SMM CPL3.
Since this is a privilege violation, default disable SMM visibility
where possible.
Administrators wanting to observe SMM cycles can easily change this
using the sysfs attribute while regular users don't have access to
this file.
[0] https://rr-project.org/
[1] See the Intel white paper "Trustworthy SMM on the Intel vPro Platform"
at https://bugzilla.kernel.org/attachment.cgi?id=300300, particularly the
end of page 5.
Reported-by: Kyle Huey <me@kylehuey.com>
Suggested-by: Andrew Cooper <Andrew.Cooper3@citrix.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@kernel.org
Link: https://lkml.kernel.org/r/YfKChjX61OW4CkYm@hirez.programming.kicks-ass.net
Some hypervisors support Arch LBR, but without the LBR XSAVE support.
The current Arch LBR init code prints a warning when the xsave size (0) is
unexpected. Avoid printing the warning for the "no LBR XSAVE" case.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20211215204029.150686-1-ak@linux.intel.com
Current ADL uncore code only supports the legacy IMC (memory controller)
free-running counters. Besides the free-running counters, ADL also
supports several general purpose-counters.
The general-purpose counters can also be accessed via MMIO but in a
different location. Factor out __uncore_imc_init_box() with offset as a
parameter. The function can be shared between ADL and TGL.
The event format and the layout of the control registers are a little
bit different from other uncore counters.
The intel_generic_uncore_mmio_enable_event() can be shared with client
IMC uncore. Expose the function.
Add more PCI IDs for ADL machines.
Fixes: 772ed05f3c ("perf/x86/intel/uncore: Add Alder Lake support")
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/1642111554-118524-1-git-send-email-kan.liang@linux.intel.com
Using static_branch to replace the LBR INFO flags to optimize the LBR
INFO parsing.
Signed-off-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>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lkml.kernel.org/r/1641315077-96661-2-git-send-email-peterz@infradead.org
The Goldmont plus and Tremont have LBR format V7. The V7 has LBR_INFO,
which is the same as LBR format V5. But V7 doesn't support TSX.
Without the patch, the associated misprediction and cycles information
in the LBR_INFO may be lost on a Goldmont plus platform.
For Tremont, the patch only impacts the non-PEBS events. Because of the
adaptive PEBS, the LBR_INFO is always processed for a PEBS event.
Currently, two different ways are used to check the LBR capabilities,
which make the codes complex and confusing.
For the LBR format V4 and earlier, the global static lbr_desc array is
used to store the flags for the LBR capabilities in each LBR format.
For LBR format V5 and V6, the current code checks the version number
for the LBR capabilities.
There are common LBR capabilities among LBR format versions. Several
flags for the LBR capabilities are introduced into the struct x86_pmu.
The flags, which can be shared among LBR formats, are used to check
the LBR capabilities. Add intel_pmu_lbr_init() to set the flags
accordingly at boot time.
Signed-off-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>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lkml.kernel.org/r/1641315077-96661-1-git-send-email-peterz@infradead.org
The RAPL events exposed under /sys/devices/power/events should only reflect
what the underlying hardware actually support. This is how it works on Intel
RAPL and Intel core/uncore PMUs in general.
But on AMD, this was not the case. All possible RAPL events were advertised.
This is what it showed on an AMD Fam17h:
$ ls /sys/devices/power/events/
energy-cores energy-gpu energy-pkg energy-psys
energy-ram energy-cores.scale energy-gpu.scale energy-pkg.scale
energy-psys.scale energy-ram.scale energy-cores.unit energy-gpu.unit
energy-pkg.unit energy-psys.unit energy-ram.unit
Yet, on AMD Fam17h, only energy-pkg is supported.
This patch fixes the problem. Given the way perf_msr_probe() works, the
amd_rapl_msrs[] table has to have all entries filled out and in particular
the group field, otherwise perf_msr_probe() defaults to making the event
visible.
With the patch applied, the kernel now only shows was is actually supported:
$ ls /sys/devices/power/events/
energy-pkg energy-pkg.scale energy-pkg.unit
The patch also uses the RAPL_MSR_MASK because only the 32-bits LSB of the
RAPL counters are relevant when reading power consumption.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220105185659.643355-1-eranian@google.com
The user recently report a perf issue in the ICX platform, when test by
perf event “uncore_imc_x/cas_count_write”,the write bandwidth is always
very small (only 0.38MB/s), it is caused by the wrong "umask" for the
"cas_count_write" event. When double-checking, find "cas_count_read"
also is wrong.
The public document for ICX uncore:
3rd Gen Intel® Xeon® Processor Scalable Family, Codename Ice Lake,Uncore
Performance Monitoring Reference Manual, Revision 1.00, May 2021
On 2.4.7, it defines Unit Masks for CAS_COUNT:
RD b00001111
WR b00110000
So corrected both "cas_count_read" and "cas_count_write" for ICX.
Old settings:
hswep_uncore_imc_events
INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03")
INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c")
New settings:
snr_uncore_imc_events
INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x0f")
INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x30")
Fixes: 2b3b76b5ec ("perf/x86/intel/uncore: Add Ice Lake server uncore support")
Signed-off-by: Zhengjun Xing <zhengjun.xing@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20211223144826.841267-1-zhengjun.xing@linux.intel.com
For some Alder Lake machine with all E-cores disabled in a BIOS, the
below warning may be triggered.
[ 2.010766] hw perf events fixed 5 > max(4), clipping!
Current perf code relies on the CPUID leaf 0xA and leaf 7.EDX[15] to
calculate the number of the counters and follow the below assumption.
For a hybrid configuration, the leaf 7.EDX[15] (X86_FEATURE_HYBRID_CPU)
is set. The leaf 0xA only enumerate the common counters. Linux perf has
to manually add the extra GP counters and fixed counters for P-cores.
For a non-hybrid configuration, the X86_FEATURE_HYBRID_CPU should not
be set. The leaf 0xA enumerates all counters.
However, that's not the case when all E-cores are disabled in a BIOS.
Although there are only P-cores in the system, the leaf 7.EDX[15]
(X86_FEATURE_HYBRID_CPU) is still set. But the leaf 0xA is updated
to enumerate all counters of P-cores. The inconsistency triggers the
warning.
Several software ways were considered to handle the inconsistency.
- Drop the leaf 0xA and leaf 7.EDX[15] CPUID enumeration support.
Hardcode the number of counters. This solution may be a problem for
virtualization. A hypervisor cannot control the number of counters
in a Linux guest via changing the guest CPUID enumeration anymore.
- Find another CPUID bit that is also updated with E-cores disabled.
There may be a problem in the virtualization environment too. Because
a hypervisor may disable the feature/CPUID bit.
- The P-cores have a maximum of 8 GP counters and 4 fixed counters on
ADL. The maximum number can be used to detect the case.
This solution is implemented in this patch.
Fixes: ee72a94ea4 ("perf/x86/intel: Fix fixed counter check warning for some Alder Lake")
Reported-by: Damjan Marion (damarion) <damarion@cisco.com>
Reported-by: Chan Edison <edison_chan_gz@hotmail.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Damjan Marion (damarion) <damarion@cisco.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1641925238-149288-1-git-send-email-kan.liang@linux.intel.com
"Cleanup of the perf/kvm interaction."
-----BEGIN PGP SIGNATURE-----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=tU5G
-----END PGP SIGNATURE-----
Merge tag 'perf_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Borislav Petkov:
"Cleanup of the perf/kvm interaction."
* tag 'perf_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf: Drop guest callback (un)register stubs
KVM: arm64: Drop perf.c and fold its tiny bits of code into arm.c
KVM: arm64: Hide kvm_arm_pmu_available behind CONFIG_HW_PERF_EVENTS=y
KVM: arm64: Convert to the generic perf callbacks
KVM: x86: Move Intel Processor Trace interrupt handler to vmx.c
KVM: Move x86's perf guest info callbacks to generic KVM
KVM: x86: More precisely identify NMI from guest when handling PMI
KVM: x86: Drop current_vcpu for kvm_running_vcpu + kvm_arch_vcpu variable
perf/core: Use static_call to optimize perf_guest_info_callbacks
perf: Force architectures to opt-in to guest callbacks
perf: Add wrappers for invoking guest callbacks
perf/core: Rework guest callbacks to prepare for static_call support
perf: Drop dead and useless guest "support" from arm, csky, nds32 and riscv
perf: Stop pretending that perf can handle multiple guest callbacks
KVM: x86: Register Processor Trace interrupt hook iff PT enabled in guest
KVM: x86: Register perf callbacks after calling vendor's hardware_setup()
perf: Protect perf_guest_cbs with RCU
-----BEGIN PGP SIGNATURE-----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=u68B
-----END PGP SIGNATURE-----
Merge tag 'x86_cleanups_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 cleanups from Borislav Petkov:
"The mandatory set of random minor cleanups all over tip"
* tag 'x86_cleanups_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/events/amd/iommu: Remove redundant assignment to variable shift
x86/boot/string: Add missing function prototypes
x86/fpu: Remove duplicate copy_fpstate_to_sigframe() prototype
x86/uaccess: Move variable into switch case statement
Variable shift is being initialized with a value that is never read, it
is being re-assigned later inside a loop. The assignment is redundant
and can be removed.
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211207185001.1412413-1-colin.i.king@gmail.com
In preparation to enable user counter access on arm64 and to move some
of the user access handling to perf core, create a common event flag for
user counter access and convert x86 to use it.
Since the architecture specific flags start at the LSB, starting at the
MSB for common flags.
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: linux-perf-users@vger.kernel.org
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20211208201124.310740-2-robh@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
Add helpers for the guest callbacks to prepare for burying the callbacks
behind a Kconfig (it's a lot easier to provide a few stubs than to #ifdef
piles of code), and also to prepare for converting the callbacks to
static_call(). perf_instruction_pointer() in particular will have subtle
semantics with static_call(), as the "no callbacks" case will return 0 if
the callbacks are unregistered between querying guest state and getting
the IP. Implement the change now to avoid a functional change when adding
static_call() support, and because the new helper needs to return
_something_ in this case.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20211111020738.2512932-8-seanjc@google.com
To prepare for using static_calls to optimize perf's guest callbacks,
replace ->is_in_guest and ->is_user_mode with a new multiplexed hook
->state, tweak ->handle_intel_pt_intr to play nice with being called when
there is no active guest, and drop "guest" from ->get_guest_ip.
Return '0' from ->state and ->handle_intel_pt_intr to indicate "not in
guest" so that DEFINE_STATIC_CALL_RET0 can be used to define the static
calls, i.e. no callback == !guest.
[sean: extracted from static_call patch, fixed get_ip() bug, wrote changelog]
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Originally-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20211111020738.2512932-7-seanjc@google.com
Protect perf_guest_cbs with RCU to fix multiple possible errors. Luckily,
all paths that read perf_guest_cbs already require RCU protection, e.g. to
protect the callback chains, so only the direct perf_guest_cbs touchpoints
need to be modified.
Bug #1 is a simple lack of WRITE_ONCE/READ_ONCE behavior to ensure
perf_guest_cbs isn't reloaded between a !NULL check and a dereference.
Fixed via the READ_ONCE() in rcu_dereference().
Bug #2 is that on weakly-ordered architectures, updates to the callbacks
themselves are not guaranteed to be visible before the pointer is made
visible to readers. Fixed by the smp_store_release() in
rcu_assign_pointer() when the new pointer is non-NULL.
Bug #3 is that, because the callbacks are global, it's possible for
readers to run in parallel with an unregisters, and thus a module
implementing the callbacks can be unloaded while readers are in flight,
resulting in a use-after-free. Fixed by a synchronize_rcu() call when
unregistering callbacks.
Bug #1 escaped notice because it's extremely unlikely a compiler will
reload perf_guest_cbs in this sequence. perf_guest_cbs does get reloaded
for future derefs, e.g. for ->is_user_mode(), but the ->is_in_guest()
guard all but guarantees the consumer will win the race, e.g. to nullify
perf_guest_cbs, KVM has to completely exit the guest and teardown down
all VMs before KVM start its module unload / unregister sequence. This
also makes it all but impossible to encounter bug #3.
Bug #2 has not been a problem because all architectures that register
callbacks are strongly ordered and/or have a static set of callbacks.
But with help, unloading kvm_intel can trigger bug #1 e.g. wrapping
perf_guest_cbs with READ_ONCE in perf_misc_flags() while spamming
kvm_intel module load/unload leads to:
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP
CPU: 6 PID: 1825 Comm: stress Not tainted 5.14.0-rc2+ #459
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
RIP: 0010:perf_misc_flags+0x1c/0x70
Call Trace:
perf_prepare_sample+0x53/0x6b0
perf_event_output_forward+0x67/0x160
__perf_event_overflow+0x52/0xf0
handle_pmi_common+0x207/0x300
intel_pmu_handle_irq+0xcf/0x410
perf_event_nmi_handler+0x28/0x50
nmi_handle+0xc7/0x260
default_do_nmi+0x6b/0x170
exc_nmi+0x103/0x130
asm_exc_nmi+0x76/0xbf
Fixes: 39447b386c ("perf: Enhance perf to allow for guest statistic collection from host")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20211111020738.2512932-2-seanjc@google.com
When running in VM intel_pmu_snapshot_branch_stack triggers WRMSR warning
like:
[ ] unchecked MSR access error: WRMSR to 0x3f1 (tried to write 0x0000000000000000) at rIP: 0xffffffff81011a5b (intel_pmu_snapshot_branch_stack+0x3b/0xd0)
This can be triggered with BPF selftests:
tools/testing/selftests/bpf/test_progs -t get_branch_snapshot
This warning is caused by __intel_pmu_pebs_disable_all() in the VM.
Since it is not necessary to disable PEBS for LBR, remove it from
intel_pmu_snapshot_branch_stack and intel_pmu_snapshot_arch_branch_stack.
Fixes: c22ac2a3d4 ("perf: Enable branch record for software events")
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Like Xu <likexu@tencent.com>
Link: https://lore.kernel.org/r/20211112054510.2667030-1-songliubraving@fb.com
According to the latest uncore document, DATA_REQ_OF_CPU (0x83),
DATA_REQ_BY_CPU (0xc0) and COMP_BUF_OCCUPANCY (0xd5) events have
constraints. Add uncore IIO constraints for Snowridge.
Fixes: 210cc5f9db ("perf/x86/intel/uncore: Add uncore support for Snow Ridge server")
Signed-off-by: Alexander Antonov <alexander.antonov@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20211115090334.3789-4-alexander.antonov@linux.intel.com
According to the latest uncore document, COMP_BUF_OCCUPANCY (0xd5) event
can be collected on 2-3 counters. Update uncore IIO event constraints for
Skylake Server.
Fixes: cd34cd97b7 ("perf/x86/intel/uncore: Add Skylake server uncore support")
Signed-off-by: Alexander Antonov <alexander.antonov@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20211115090334.3789-3-alexander.antonov@linux.intel.com
According Uncore Reference Manual: any of the CHA events may be filtered
by Thread/Core-ID by using tid modifier in CHA Filter 0 Register.
Update skx_cha_hw_config() to follow Uncore Guide.
Fixes: cd34cd97b7 ("perf/x86/intel/uncore: Add Skylake server uncore support")
Signed-off-by: Alexander Antonov <alexander.antonov@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20211115090334.3789-2-alexander.antonov@linux.intel.com
Just like what we do in the x86_get_event_constraints(), the
PERF_X86_EVENT_LBR_SELECT flag should also be propagated
to event->hw.flags so that the host lbr driver can save/restore
MSR_LBR_SELECT for the special vlbr event created by KVM or BPF.
Fixes: 097e4311cd ("perf/x86: Add constraint to create guest LBR event without hw counter")
Reported-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Wanpeng Li <wanpengli@tencent.com>
Link: https://lore.kernel.org/r/20211103091716.59906-1-likexu@tencent.com
lbr_select in kvm guest has residual data even if kvm guest is poweroff.
We can get residual data in the next boot. Because lbr_select is not
reset during kvm vlbr release. Let's reset LBR_SELECT during vlbr reset.
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1636096851-36623-1-git-send-email-wanpengli@tencent.com
-----BEGIN PGP SIGNATURE-----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=nsMh
-----END PGP SIGNATURE-----
Merge tag 'pci-v5.16-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci
Pull pci updates from Bjorn Helgaas:
"Enumeration:
- Conserve IRQs by setting up portdrv IRQs only when there are users
(Jan Kiszka)
- Rework and simplify _OSC negotiation for control of PCIe features
(Joerg Roedel)
- Remove struct pci_dev.driver pointer since it's redundant with the
struct device.driver pointer (Uwe Kleine-König)
Resource management:
- Coalesce contiguous host bridge apertures from _CRS to accommodate
BARs that cover more than one aperture (Kai-Heng Feng)
Sysfs:
- Check CAP_SYS_ADMIN before parsing user input (Krzysztof
Wilczyński)
- Return -EINVAL consistently from "store" functions (Krzysztof
Wilczyński)
- Use sysfs_emit() in endpoint "show" functions to avoid buffer
overruns (Kunihiko Hayashi)
PCIe native device hotplug:
- Ignore Link Down/Up caused by resets during error recovery so
endpoint drivers can remain bound to the device (Lukas Wunner)
Virtualization:
- Avoid bus resets on Atheros QCA6174, where they hang the device
(Ingmar Klein)
- Work around Pericom PI7C9X2G switch packet drop erratum by using
store and forward mode instead of cut-through (Nathan Rossi)
- Avoid trying to enable AtomicOps on VFs; the PF setting applies to
all VFs (Selvin Xavier)
MSI:
- Document that /sys/bus/pci/devices/.../irq contains the legacy INTx
interrupt or the IRQ of the first MSI (not MSI-X) vector (Barry
Song)
VPD:
- Add pci_read_vpd_any() and pci_write_vpd_any() to access anywhere
in the possible VPD space; use these to simplify the cxgb3 driver
(Heiner Kallweit)
Peer-to-peer DMA:
- Add (not subtract) the bus offset when calculating DMA address
(Wang Lu)
ASPM:
- Re-enable LTR at Downstream Ports so they don't report Unsupported
Requests when reset or hot-added devices send LTR messages
(Mingchuang Qiao)
Apple PCIe controller driver:
- Add driver for Apple M1 PCIe controller (Alyssa Rosenzweig, Marc
Zyngier)
Cadence PCIe controller driver:
- Return success when probe succeeds instead of falling into error
path (Li Chen)
HiSilicon Kirin PCIe controller driver:
- Reorganize PHY logic and add support for external PHY drivers
(Mauro Carvalho Chehab)
- Support PERST# GPIOs for HiKey970 external PEX 8606 bridge (Mauro
Carvalho Chehab)
- Add Kirin 970 support (Mauro Carvalho Chehab)
- Make driver removable (Mauro Carvalho Chehab)
Intel VMD host bridge driver:
- If IOMMU supports interrupt remapping, leave VMD MSI-X remapping
enabled (Adrian Huang)
- Number each controller so we can tell them apart in
/proc/interrupts (Chunguang Xu)
- Avoid building on UML because VMD depends on x86 bare metal APIs
(Johannes Berg)
Marvell Aardvark PCIe controller driver:
- Define macros for PCI_EXP_DEVCTL_PAYLOAD_* (Pali Rohár)
- Set Max Payload Size to 512 bytes per Marvell spec (Pali Rohár)
- Downgrade PIO Response Status messages to debug level (Marek Behún)
- Preserve CRS SV (Config Request Retry Software Visibility) bit in
emulated Root Control register (Pali Rohár)
- Fix issue in configuring reference clock (Pali Rohár)
- Don't clear status bits for masked interrupts (Pali Rohár)
- Don't mask unused interrupts (Pali Rohár)
- Avoid code repetition in advk_pcie_rd_conf() (Marek Behún)
- Retry config accesses on CRS response (Pali Rohár)
- Simplify emulated Root Capabilities initialization (Pali Rohár)
- Fix several link training issues (Pali Rohár)
- Fix link-up checking via LTSSM (Pali Rohár)
- Fix reporting of Data Link Layer Link Active (Pali Rohár)
- Fix emulation of W1C bits (Marek Behún)
- Fix MSI domain .alloc() method to return zero on success (Marek
Behún)
- Read entire 16-bit MSI vector in MSI handler, not just low 8 bits
(Marek Behún)
- Clear Root Port I/O Space, Memory Space, and Bus Master Enable bits
at startup; PCI core will set those as necessary (Pali Rohár)
- When operating as a Root Port, set class code to "PCI Bridge"
instead of the default "Mass Storage Controller" (Pali Rohár)
- Add emulation for PCI_BRIDGE_CTL_BUS_RESET since aardvark doesn't
implement this per spec (Pali Rohár)
- Add emulation of option ROM BAR since aardvark doesn't implement
this per spec (Pali Rohár)
MediaTek MT7621 PCIe controller driver:
- Add MediaTek MT7621 PCIe host controller driver and DT binding
(Sergio Paracuellos)
Qualcomm PCIe controller driver:
- Add SC8180x compatible string (Bjorn Andersson)
- Add endpoint controller driver and DT binding (Manivannan
Sadhasivam)
- Restructure to use of_device_get_match_data() (Prasad Malisetty)
- Add SC7280-specific pcie_1_pipe_clk_src handling (Prasad Malisetty)
Renesas R-Car PCIe controller driver:
- Remove unnecessary includes (Geert Uytterhoeven)
Rockchip DesignWare PCIe controller driver:
- Add DT binding (Simon Xue)
Socionext UniPhier Pro5 controller driver:
- Serialize INTx masking/unmasking (Kunihiko Hayashi)
Synopsys DesignWare PCIe controller driver:
- Run dwc .host_init() method before registering MSI interrupt
handler so we can deal with pending interrupts left by bootloader
(Bjorn Andersson)
- Clean up Kconfig dependencies (Andy Shevchenko)
- Export symbols to allow more modular drivers (Luca Ceresoli)
TI DRA7xx PCIe controller driver:
- Allow host and endpoint drivers to be modules (Luca Ceresoli)
- Enable external clock if present (Luca Ceresoli)
TI J721E PCIe driver:
- Disable PHY when probe fails after initializing it (Christophe
JAILLET)
MicroSemi Switchtec management driver:
- Return error to application when command execution fails because an
out-of-band reset has cleared the device BARs, Memory Space Enable,
etc (Kelvin Cao)
- Fix MRPC error status handling issue (Kelvin Cao)
- Mask out other bits when reading of management VEP instance ID
(Kelvin Cao)
- Return EOPNOTSUPP instead of ENOTSUPP from sysfs show functions
(Kelvin Cao)
- Add check of event support (Logan Gunthorpe)
Miscellaneous:
- Remove unused pci_pool wrappers, which have been replaced by
dma_pool (Cai Huoqing)
- Use 'unsigned int' instead of bare 'unsigned' (Krzysztof
Wilczyński)
- Use kstrtobool() directly, sans strtobool() wrapper (Krzysztof
Wilczyński)
- Fix some sscanf(), sprintf() format mismatches (Krzysztof
Wilczyński)
- Update PCI subsystem information in MAINTAINERS (Krzysztof
Wilczyński)
- Correct some misspellings (Krzysztof Wilczyński)"
* tag 'pci-v5.16-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (137 commits)
PCI: Add ACS quirk for Pericom PI7C9X2G switches
PCI: apple: Configure RID to SID mapper on device addition
iommu/dart: Exclude MSI doorbell from PCIe device IOVA range
PCI: apple: Implement MSI support
PCI: apple: Add INTx and per-port interrupt support
PCI: kirin: Allow removing the driver
PCI: kirin: De-init the dwc driver
PCI: kirin: Disable clkreq during poweroff sequence
PCI: kirin: Move the power-off code to a common routine
PCI: kirin: Add power_off support for Kirin 960 PHY
PCI: kirin: Allow building it as a module
PCI: kirin: Add MODULE_* macros
PCI: kirin: Add Kirin 970 compatible
PCI: kirin: Support PERST# GPIOs for HiKey970 external PEX 8606 bridge
PCI: apple: Set up reference clocks when probing
PCI: apple: Add initial hardware bring-up
PCI: of: Allow matching of an interrupt-map local to a PCI device
of/irq: Allow matching of an interrupt-map local to an interrupt controller
irqdomain: Make of_phandle_args_to_fwspec() generally available
PCI: Do not enable AtomicOps on VFs
...
- Remove socket skb caches
- Add a SO_RESERVE_MEM socket op to forward allocate buffer space
and avoid memory accounting overhead on each message sent
- Introduce managed neighbor entries - added by control plane and
resolved by the kernel for use in acceleration paths (BPF / XDP
right now, HW offload users will benefit as well)
- Make neighbor eviction on link down controllable by userspace
to work around WiFi networks with bad roaming implementations
- vrf: Rework interaction with netfilter/conntrack
- fq_codel: implement L4S style ce_threshold_ect1 marking
- sch: Eliminate unnecessary RCU waits in mini_qdisc_pair_swap()
BPF:
- Add support for new btf kind BTF_KIND_TAG, arbitrary type tagging
as implemented in LLVM14
- Introduce bpf_get_branch_snapshot() to capture Last Branch Records
- Implement variadic trace_printk helper
- Add a new Bloomfilter map type
- Track <8-byte scalar spill and refill
- Access hw timestamp through BPF's __sk_buff
- Disallow unprivileged BPF by default
- Document BPF licensing
Netfilter:
- Introduce egress hook for looking at raw outgoing packets
- Allow matching on and modifying inner headers / payload data
- Add NFT_META_IFTYPE to match on the interface type either from
ingress or egress
Protocols:
- Multi-Path TCP:
- increase default max additional subflows to 2
- rework forward memory allocation
- add getsockopts: MPTCP_INFO, MPTCP_TCPINFO, MPTCP_SUBFLOW_ADDRS
- MCTP flow support allowing lower layer drivers to configure msg
muxing as needed
- Automatic Multicast Tunneling (AMT) driver based on RFC7450
- HSR support the redbox supervision frames (IEC-62439-3:2018)
- Support for the ip6ip6 encapsulation of IOAM
- Netlink interface for CAN-FD's Transmitter Delay Compensation
- Support SMC-Rv2 eliminating the current same-subnet restriction,
by exploiting the UDP encapsulation feature of RoCE adapters
- TLS: add SM4 GCM/CCM crypto support
- Bluetooth: initial support for link quality and audio/codec
offload
Driver APIs:
- Add a batched interface for RX buffer allocation in AF_XDP
buffer pool
- ethtool: Add ability to control transceiver modules' power mode
- phy: Introduce supported interfaces bitmap to express MAC
capabilities and simplify PHY code
- Drop rtnl_lock from DSA .port_fdb_{add,del} callbacks
New drivers:
- WiFi driver for Realtek 8852AE 802.11ax devices (rtw89)
- Ethernet driver for ASIX AX88796C SPI device (x88796c)
Drivers:
- Broadcom PHYs
- support 72165, 7712 16nm PHYs
- support IDDQ-SR for additional power savings
- PHY support for QCA8081, QCA9561 PHYs
- NXP DPAA2: support for IRQ coalescing
- NXP Ethernet (enetc): support for software TCP segmentation
- Renesas Ethernet (ravb) - support DMAC and EMAC blocks of
Gigabit-capable IP found on RZ/G2L SoC
- Intel 100G Ethernet
- support for eswitch offload of TC/OvS flow API, including
offload of GRE, VxLAN, Geneve tunneling
- support application device queues - ability to assign Rx and Tx
queues to application threads
- PTP and PPS (pulse-per-second) extensions
- Broadcom Ethernet (bnxt)
- devlink health reporting and device reload extensions
- Mellanox Ethernet (mlx5)
- offload macvlan interfaces
- support HW offload of TC rules involving OVS internal ports
- support HW-GRO and header/data split
- support application device queues
- Marvell OcteonTx2:
- add XDP support for PF
- add PTP support for VF
- Qualcomm Ethernet switch (qca8k): support for QCA8328
- Realtek Ethernet DSA switch (rtl8366rb)
- support bridge offload
- support STP, fast aging, disabling address learning
- support for Realtek RTL8365MB-VC, a 4+1 port 10M/100M/1GE switch
- Mellanox Ethernet/IB switch (mlxsw)
- multi-level qdisc hierarchy offload (e.g. RED, prio and shaping)
- offload root TBF qdisc as port shaper
- support multiple routing interface MAC address prefixes
- support for IP-in-IP with IPv6 underlay
- MediaTek WiFi (mt76)
- mt7921 - ASPM, 6GHz, SDIO and testmode support
- mt7915 - LED and TWT support
- Qualcomm WiFi (ath11k)
- include channel rx and tx time in survey dump statistics
- support for 80P80 and 160 MHz bandwidths
- support channel 2 in 6 GHz band
- spectral scan support for QCN9074
- support for rx decapsulation offload (data frames in 802.3
format)
- Qualcomm phone SoC WiFi (wcn36xx)
- enable Idle Mode Power Save (IMPS) to reduce power consumption
during idle
- Bluetooth driver support for MediaTek MT7922 and MT7921
- Enable support for AOSP Bluetooth extension in Qualcomm WCN399x
and Realtek 8822C/8852A
- Microsoft vNIC driver (mana)
- support hibernation and kexec
- Google vNIC driver (gve)
- support for jumbo frames
- implement Rx page reuse
Refactor:
- Make all writes to netdev->dev_addr go thru helpers, so that we
can add this address to the address rbtree and handle the updates
- Various TCP cleanups and optimizations including improvements
to CPU cache use
- Simplify the gnet_stats, Qdisc stats' handling and remove
qdisc->running sequence counter
- Driver changes and API updates to address devlink locking
deficiencies
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----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=srde
-----END PGP SIGNATURE-----
Merge tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- Remove socket skb caches
- Add a SO_RESERVE_MEM socket op to forward allocate buffer space and
avoid memory accounting overhead on each message sent
- Introduce managed neighbor entries - added by control plane and
resolved by the kernel for use in acceleration paths (BPF / XDP
right now, HW offload users will benefit as well)
- Make neighbor eviction on link down controllable by userspace to
work around WiFi networks with bad roaming implementations
- vrf: Rework interaction with netfilter/conntrack
- fq_codel: implement L4S style ce_threshold_ect1 marking
- sch: Eliminate unnecessary RCU waits in mini_qdisc_pair_swap()
BPF:
- Add support for new btf kind BTF_KIND_TAG, arbitrary type tagging
as implemented in LLVM14
- Introduce bpf_get_branch_snapshot() to capture Last Branch Records
- Implement variadic trace_printk helper
- Add a new Bloomfilter map type
- Track <8-byte scalar spill and refill
- Access hw timestamp through BPF's __sk_buff
- Disallow unprivileged BPF by default
- Document BPF licensing
Netfilter:
- Introduce egress hook for looking at raw outgoing packets
- Allow matching on and modifying inner headers / payload data
- Add NFT_META_IFTYPE to match on the interface type either from
ingress or egress
Protocols:
- Multi-Path TCP:
- increase default max additional subflows to 2
- rework forward memory allocation
- add getsockopts: MPTCP_INFO, MPTCP_TCPINFO, MPTCP_SUBFLOW_ADDRS
- MCTP flow support allowing lower layer drivers to configure msg
muxing as needed
- Automatic Multicast Tunneling (AMT) driver based on RFC7450
- HSR support the redbox supervision frames (IEC-62439-3:2018)
- Support for the ip6ip6 encapsulation of IOAM
- Netlink interface for CAN-FD's Transmitter Delay Compensation
- Support SMC-Rv2 eliminating the current same-subnet restriction, by
exploiting the UDP encapsulation feature of RoCE adapters
- TLS: add SM4 GCM/CCM crypto support
- Bluetooth: initial support for link quality and audio/codec offload
Driver APIs:
- Add a batched interface for RX buffer allocation in AF_XDP buffer
pool
- ethtool: Add ability to control transceiver modules' power mode
- phy: Introduce supported interfaces bitmap to express MAC
capabilities and simplify PHY code
- Drop rtnl_lock from DSA .port_fdb_{add,del} callbacks
New drivers:
- WiFi driver for Realtek 8852AE 802.11ax devices (rtw89)
- Ethernet driver for ASIX AX88796C SPI device (x88796c)
Drivers:
- Broadcom PHYs
- support 72165, 7712 16nm PHYs
- support IDDQ-SR for additional power savings
- PHY support for QCA8081, QCA9561 PHYs
- NXP DPAA2: support for IRQ coalescing
- NXP Ethernet (enetc): support for software TCP segmentation
- Renesas Ethernet (ravb) - support DMAC and EMAC blocks of
Gigabit-capable IP found on RZ/G2L SoC
- Intel 100G Ethernet
- support for eswitch offload of TC/OvS flow API, including
offload of GRE, VxLAN, Geneve tunneling
- support application device queues - ability to assign Rx and Tx
queues to application threads
- PTP and PPS (pulse-per-second) extensions
- Broadcom Ethernet (bnxt)
- devlink health reporting and device reload extensions
- Mellanox Ethernet (mlx5)
- offload macvlan interfaces
- support HW offload of TC rules involving OVS internal ports
- support HW-GRO and header/data split
- support application device queues
- Marvell OcteonTx2:
- add XDP support for PF
- add PTP support for VF
- Qualcomm Ethernet switch (qca8k): support for QCA8328
- Realtek Ethernet DSA switch (rtl8366rb)
- support bridge offload
- support STP, fast aging, disabling address learning
- support for Realtek RTL8365MB-VC, a 4+1 port 10M/100M/1GE switch
- Mellanox Ethernet/IB switch (mlxsw)
- multi-level qdisc hierarchy offload (e.g. RED, prio and shaping)
- offload root TBF qdisc as port shaper
- support multiple routing interface MAC address prefixes
- support for IP-in-IP with IPv6 underlay
- MediaTek WiFi (mt76)
- mt7921 - ASPM, 6GHz, SDIO and testmode support
- mt7915 - LED and TWT support
- Qualcomm WiFi (ath11k)
- include channel rx and tx time in survey dump statistics
- support for 80P80 and 160 MHz bandwidths
- support channel 2 in 6 GHz band
- spectral scan support for QCN9074
- support for rx decapsulation offload (data frames in 802.3
format)
- Qualcomm phone SoC WiFi (wcn36xx)
- enable Idle Mode Power Save (IMPS) to reduce power consumption
during idle
- Bluetooth driver support for MediaTek MT7922 and MT7921
- Enable support for AOSP Bluetooth extension in Qualcomm WCN399x and
Realtek 8822C/8852A
- Microsoft vNIC driver (mana)
- support hibernation and kexec
- Google vNIC driver (gve)
- support for jumbo frames
- implement Rx page reuse
Refactor:
- Make all writes to netdev->dev_addr go thru helpers, so that we can
add this address to the address rbtree and handle the updates
- Various TCP cleanups and optimizations including improvements to
CPU cache use
- Simplify the gnet_stats, Qdisc stats' handling and remove
qdisc->running sequence counter
- Driver changes and API updates to address devlink locking
deficiencies"
* tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2122 commits)
Revert "net: avoid double accounting for pure zerocopy skbs"
selftests: net: add arp_ndisc_evict_nocarrier
net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter
net: arp: introduce arp_evict_nocarrier sysctl parameter
libbpf: Deprecate AF_XDP support
kbuild: Unify options for BTF generation for vmlinux and modules
selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
net: vmxnet3: remove multiple false checks in vmxnet3_ethtool.c
net: avoid double accounting for pure zerocopy skbs
tcp: rename sk_wmem_free_skb
netdevsim: fix uninit value in nsim_drv_configure_vfs()
selftests/bpf: Fix also no-alu32 strobemeta selftest
bpf: Add missing map_delete_elem method to bloom filter map
selftests/bpf: Add bloom map success test for userspace calls
bpf: Add alignment padding for "map_extra" + consolidate holes
bpf: Bloom filter map naming fixups
selftests/bpf: Add test cases for struct_ops prog
bpf: Add dummy BPF STRUCT_OPS for test purpose
...
- Cleanup of extable fixup handling to be more robust, which in turn
allows to make the FPU exception fixups more robust as well.
- Change the return code for signal frame related failures from explicit
error codes to a boolean fail/success as that's all what the calling
code evaluates.
- A large refactoring of the FPU code to prepare for adding AMX support:
- Distangle the public header maze and remove especially the misnomed
kitchen sink internal.h which is despite it's name included all over
the place.
- Add a proper abstraction for the register buffer storage (struct
fpstate) which allows to dynamically size the buffer at runtime by
flipping the pointer to the buffer container from the default
container which is embedded in task_struct::tread::fpu to a
dynamically allocated container with a larger register buffer.
- Convert the code over to the new fpstate mechanism.
- Consolidate the KVM FPU handling by moving the FPU related code into
the FPU core which removes the number of exports and avoids adding
even more export when AMX has to be supported in KVM. This also
removes duplicated code which was of course unnecessary different and
incomplete in the KVM copy.
- Simplify the KVM FPU buffer handling by utilizing the new fpstate
container and just switching the buffer pointer from the user space
buffer to the KVM guest buffer when entering vcpu_run() and flipping
it back when leaving the function. This cuts the memory requirements
of a vCPU for FPU buffers in half and avoids pointless memory copy
operations.
This also solves the so far unresolved problem of adding AMX support
because the current FPU buffer handling of KVM inflicted a circular
dependency between adding AMX support to the core and to KVM. With
the new scheme of switching fpstate AMX support can be added to the
core code without affecting KVM.
- Replace various variables with proper data structures so the extra
information required for adding dynamically enabled FPU features (AMX)
can be added in one place
- Add AMX (Advanved Matrix eXtensions) support (finally):
AMX is a large XSTATE component which is going to be available with
Saphire Rapids XEON CPUs. The feature comes with an extra MSR (MSR_XFD)
which allows to trap the (first) use of an AMX related instruction,
which has two benefits:
1) It allows the kernel to control access to the feature
2) It allows the kernel to dynamically allocate the large register
state buffer instead of burdening every task with the the extra 8K
or larger state storage.
It would have been great to gain this kind of control already with
AVX512.
The support comes with the following infrastructure components:
1) arch_prctl() to
- read the supported features (equivalent to XGETBV(0))
- read the permitted features for a task
- request permission for a dynamically enabled feature
Permission is granted per process, inherited on fork() and cleared
on exec(). The permission policy of the kernel is restricted to
sigaltstack size validation, but the syscall obviously allows
further restrictions via seccomp etc.
2) A stronger sigaltstack size validation for sys_sigaltstack(2) which
takes granted permissions and the potentially resulting larger
signal frame into account. This mechanism can also be used to
enforce factual sigaltstack validation independent of dynamic
features to help with finding potential victims of the 2K
sigaltstack size constant which is broken since AVX512 support was
added.
3) Exception handling for #NM traps to catch first use of a extended
feature via a new cause MSR. If the exception was caused by the use
of such a feature, the handler checks permission for that
feature. If permission has not been granted, the handler sends a
SIGILL like the #UD handler would do if the feature would have been
disabled in XCR0. If permission has been granted, then a new fpstate
which fits the larger buffer requirement is allocated.
In the unlikely case that this allocation fails, the handler sends
SIGSEGV to the task. That's not elegant, but unavoidable as the
other discussed options of preallocation or full per task
permissions come with their own set of horrors for kernel and/or
userspace. So this is the lesser of the evils and SIGSEGV caused by
unexpected memory allocation failures is not a fundamentally new
concept either.
When allocation succeeds, the fpstate properties are filled in to
reflect the extended feature set and the resulting sizes, the
fpu::fpstate pointer is updated accordingly and the trap is disarmed
for this task permanently.
4) Enumeration and size calculations
5) Trap switching via MSR_XFD
The XFD (eXtended Feature Disable) MSR is context switched with the
same life time rules as the FPU register state itself. The mechanism
is keyed off with a static key which is default disabled so !AMX
equipped CPUs have zero overhead. On AMX enabled CPUs the overhead
is limited by comparing the tasks XFD value with a per CPU shadow
variable to avoid redundant MSR writes. In case of switching from a
AMX using task to a non AMX using task or vice versa, the extra MSR
write is obviously inevitable.
All other places which need to be aware of the variable feature sets
and resulting variable sizes are not affected at all because they
retrieve the information (feature set, sizes) unconditonally from
the fpstate properties.
6) Enable the new AMX states
Note, this is relatively new code despite the fact that AMX support is in
the works for more than a year now.
The big refactoring of the FPU code, which allowed to do a proper
integration has been started exactly 3 weeks ago. Refactoring of the
existing FPU code and of the original AMX patches took a week and has
been subject to extensive review and testing. The only fallout which has
not been caught in review and testing right away was restricted to AMX
enabled systems, which is completely irrelevant for anyone outside Intel
and their early access program. There might be dragons lurking as usual,
but so far the fine grained refactoring has held up and eventual yet
undetected fallout is bisectable and should be easily addressable before
the 5.16 release. Famous last words...
Many thanks to Chang Bae and Dave Hansen for working hard on this and
also to the various test teams at Intel who reserved extra capacity to
follow the rapid development of this closely which provides the
confidence level required to offer this rather large update for inclusion
into 5.16-rc1.
-----BEGIN PGP SIGNATURE-----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=x3WL
-----END PGP SIGNATURE-----
Merge tag 'x86-fpu-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fpu updates from Thomas Gleixner:
- Cleanup of extable fixup handling to be more robust, which in turn
allows to make the FPU exception fixups more robust as well.
- Change the return code for signal frame related failures from
explicit error codes to a boolean fail/success as that's all what the
calling code evaluates.
- A large refactoring of the FPU code to prepare for adding AMX
support:
- Distangle the public header maze and remove especially the
misnomed kitchen sink internal.h which is despite it's name
included all over the place.
- Add a proper abstraction for the register buffer storage (struct
fpstate) which allows to dynamically size the buffer at runtime
by flipping the pointer to the buffer container from the default
container which is embedded in task_struct::tread::fpu to a
dynamically allocated container with a larger register buffer.
- Convert the code over to the new fpstate mechanism.
- Consolidate the KVM FPU handling by moving the FPU related code
into the FPU core which removes the number of exports and avoids
adding even more export when AMX has to be supported in KVM.
This also removes duplicated code which was of course
unnecessary different and incomplete in the KVM copy.
- Simplify the KVM FPU buffer handling by utilizing the new
fpstate container and just switching the buffer pointer from the
user space buffer to the KVM guest buffer when entering
vcpu_run() and flipping it back when leaving the function. This
cuts the memory requirements of a vCPU for FPU buffers in half
and avoids pointless memory copy operations.
This also solves the so far unresolved problem of adding AMX
support because the current FPU buffer handling of KVM inflicted
a circular dependency between adding AMX support to the core and
to KVM. With the new scheme of switching fpstate AMX support can
be added to the core code without affecting KVM.
- Replace various variables with proper data structures so the
extra information required for adding dynamically enabled FPU
features (AMX) can be added in one place
- Add AMX (Advanced Matrix eXtensions) support (finally):
AMX is a large XSTATE component which is going to be available with
Saphire Rapids XEON CPUs. The feature comes with an extra MSR
(MSR_XFD) which allows to trap the (first) use of an AMX related
instruction, which has two benefits:
1) It allows the kernel to control access to the feature
2) It allows the kernel to dynamically allocate the large register
state buffer instead of burdening every task with the the extra
8K or larger state storage.
It would have been great to gain this kind of control already with
AVX512.
The support comes with the following infrastructure components:
1) arch_prctl() to
- read the supported features (equivalent to XGETBV(0))
- read the permitted features for a task
- request permission for a dynamically enabled feature
Permission is granted per process, inherited on fork() and
cleared on exec(). The permission policy of the kernel is
restricted to sigaltstack size validation, but the syscall
obviously allows further restrictions via seccomp etc.
2) A stronger sigaltstack size validation for sys_sigaltstack(2)
which takes granted permissions and the potentially resulting
larger signal frame into account. This mechanism can also be used
to enforce factual sigaltstack validation independent of dynamic
features to help with finding potential victims of the 2K
sigaltstack size constant which is broken since AVX512 support
was added.
3) Exception handling for #NM traps to catch first use of a extended
feature via a new cause MSR. If the exception was caused by the
use of such a feature, the handler checks permission for that
feature. If permission has not been granted, the handler sends a
SIGILL like the #UD handler would do if the feature would have
been disabled in XCR0. If permission has been granted, then a new
fpstate which fits the larger buffer requirement is allocated.
In the unlikely case that this allocation fails, the handler
sends SIGSEGV to the task. That's not elegant, but unavoidable as
the other discussed options of preallocation or full per task
permissions come with their own set of horrors for kernel and/or
userspace. So this is the lesser of the evils and SIGSEGV caused
by unexpected memory allocation failures is not a fundamentally
new concept either.
When allocation succeeds, the fpstate properties are filled in to
reflect the extended feature set and the resulting sizes, the
fpu::fpstate pointer is updated accordingly and the trap is
disarmed for this task permanently.
4) Enumeration and size calculations
5) Trap switching via MSR_XFD
The XFD (eXtended Feature Disable) MSR is context switched with
the same life time rules as the FPU register state itself. The
mechanism is keyed off with a static key which is default
disabled so !AMX equipped CPUs have zero overhead. On AMX enabled
CPUs the overhead is limited by comparing the tasks XFD value
with a per CPU shadow variable to avoid redundant MSR writes. In
case of switching from a AMX using task to a non AMX using task
or vice versa, the extra MSR write is obviously inevitable.
All other places which need to be aware of the variable feature
sets and resulting variable sizes are not affected at all because
they retrieve the information (feature set, sizes) unconditonally
from the fpstate properties.
6) Enable the new AMX states
Note, this is relatively new code despite the fact that AMX support
is in the works for more than a year now.
The big refactoring of the FPU code, which allowed to do a proper
integration has been started exactly 3 weeks ago. Refactoring of the
existing FPU code and of the original AMX patches took a week and has
been subject to extensive review and testing. The only fallout which
has not been caught in review and testing right away was restricted
to AMX enabled systems, which is completely irrelevant for anyone
outside Intel and their early access program. There might be dragons
lurking as usual, but so far the fine grained refactoring has held up
and eventual yet undetected fallout is bisectable and should be
easily addressable before the 5.16 release. Famous last words...
Many thanks to Chang Bae and Dave Hansen for working hard on this and
also to the various test teams at Intel who reserved extra capacity
to follow the rapid development of this closely which provides the
confidence level required to offer this rather large update for
inclusion into 5.16-rc1
* tag 'x86-fpu-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (110 commits)
Documentation/x86: Add documentation for using dynamic XSTATE features
x86/fpu: Include vmalloc.h for vzalloc()
selftests/x86/amx: Add context switch test
selftests/x86/amx: Add test cases for AMX state management
x86/fpu/amx: Enable the AMX feature in 64-bit mode
x86/fpu: Add XFD handling for dynamic states
x86/fpu: Calculate the default sizes independently
x86/fpu/amx: Define AMX state components and have it used for boot-time checks
x86/fpu/xstate: Prepare XSAVE feature table for gaps in state component numbers
x86/fpu/xstate: Add fpstate_realloc()/free()
x86/fpu/xstate: Add XFD #NM handler
x86/fpu: Update XFD state where required
x86/fpu: Add sanity checks for XFD
x86/fpu: Add XFD state to fpstate
x86/msr-index: Add MSRs for XFD
x86/cpufeatures: Add eXtended Feature Disabling (XFD) feature bit
x86/fpu: Reset permission and fpstate on exec()
x86/fpu: Prepare fpu_clone() for dynamically enabled features
x86/fpu/signal: Prepare for variable sigframe length
x86/signal: Use fpu::__state_user_size for sigalt stack validation
...
core:
- Allow ftrace to instrument parts of the perf core code
- Add a new mem_hops field to perf_mem_data_src which allows to represent
intra-node/package or inter-node/off-package details to prepare for
next generation systems which have more hieararchy within the
node/pacakge level.
tools:
- Update for the new mem_hops field in perf_mem_data_src
arch:
- A set of constraints fixes for the Intel uncore PMU
- The usual set of small fixes and improvements for x86 and PPC
-----BEGIN PGP SIGNATURE-----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=Oj0G
-----END PGP SIGNATURE-----
Merge tag 'perf-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Thomas Gleixner:
"Core:
- Allow ftrace to instrument parts of the perf core code
- Add a new mem_hops field to perf_mem_data_src which allows to
represent intra-node/package or inter-node/off-package details to
prepare for next generation systems which have more hieararchy
within the node/pacakge level.
Tools:
- Update for the new mem_hops field in perf_mem_data_src
Arch:
- A set of constraints fixes for the Intel uncore PMU
- The usual set of small fixes and improvements for x86 and PPC"
* tag 'perf-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel: Fix ICL/SPR INST_RETIRED.PREC_DIST encodings
powerpc/perf: Fix data source encodings for L2.1 and L3.1 accesses
tools/perf: Add mem_hops field in perf_mem_data_src structure
perf: Add mem_hops field in perf_mem_data_src structure
perf: Add comment about current state of PERF_MEM_LVL_* namespace and remove an extra line
perf/core: Allow ftrace for functions in kernel/event/core.c
perf/x86: Add new event for AUX output counter index
perf/x86: Add compiler barrier after updating BTS
perf/x86/intel/uncore: Fix Intel SPR M3UPI event constraints
perf/x86/intel/uncore: Fix Intel SPR M2PCIE event constraints
perf/x86/intel/uncore: Fix Intel SPR IIO event constraints
perf/x86/intel/uncore: Fix Intel SPR CHA event constraints
perf/x86/intel/uncore: Fix Intel ICX IIO event constraints
perf/x86/intel/uncore: Fix invalid unit check
perf/x86/intel/uncore: Support extra IMC channel on Ice Lake server
This patch fixes the encoding for INST_RETIRED.PREC_DIST as published by Intel
(download.01.org/perfmon/) for Icelake. The official encoding
is event code 0x00 umask 0x1, a change from Skylake where it was code 0xc0
umask 0x1.
With this patch applied it is possible to run:
$ perf record -a -e cpu/event=0x00,umask=0x1/pp .....
Whereas before this would fail.
To avoid problems with tools which may use the old code, we maintain the old
encoding for Icelake.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20211014001214.2680534-1-eranian@google.com
PKRU code does not need anything from FPU headers. Include cpufeature.h
instead and fixup the resulting fallout in perf.
This is a preparation for FPU changes in order to prevent recursive include
hell.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20211015011538.551522694@linutronix.de
Struct pci_driver contains a struct device_driver, so for PCI devices, it's
easy to convert a device_driver * to a pci_driver * with to_pci_driver().
The device_driver * is in struct device, so we don't need to also keep
track of the pci_driver * in struct pci_dev.
Replace pdev->driver with to_pci_driver(). This is a step toward removing
pci_dev->driver.
[bhelgaas: split to separate patch]
Link: https://lore.kernel.org/r/20211004125935.2300113-11-u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
PEBS-via-PT records contain a mask of applicable counters. To identify
which event belongs to which counter, a side-band event is needed. Until
now, there has been no side-band event, and consequently users were limited
to using a single event.
Add such a side-band event. Note the event is optimised to output only
when the counter index changes for an event. That works only so long as
all PEBS-via-PT events are scheduled together, which they are for a
recording session because they are in a single group.
Also no attribute bit is used to select the new event, so a new
kernel is not compatible with older perf tools. The assumption
being that PEBS-via-PT is sufficiently esoteric that users will not
be troubled by this.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210907163903.11820-2-adrian.hunter@intel.com
According to the latest event list, the event encoding 0xEF is only
available on the first 4 counters. Add it into the event constraints
table.
Fixes: 6017608936 ("perf/x86/intel: Add Icelake support")
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/1632842343-25862-1-git-send-email-kan.liang@linux.intel.com
perf_init_event tries multiple init callbacks and does not reset the
event state between tries. When x86_pmu_event_init runs, it
unconditionally sets the destroy callback to hw_perf_event_destroy. On
the next init attempt after x86_pmu_event_init, in perf_try_init_event,
if the pmu's capabilities includes PERF_PMU_CAP_NO_EXCLUDE, the destroy
callback will be run. However, if the next init didn't set the destroy
callback, hw_perf_event_destroy will be run (since the callback wasn't
reset).
Looking at other pmu init functions, the common pattern is to only set
the destroy callback on a successful init. Resetting the callback on
failure tries to replicate that pattern.
This was discovered after commit f11dd0d805 ("perf/x86/amd/ibs: Extend
PERF_PMU_CAP_NO_EXCLUDE to IBS Op") when the second (and only second)
run of the perf tool after a reboot results in 0 samples being
generated. The extra run of hw_perf_event_destroy results in
active_events having an extra decrement on each perf run. The second run
has active_events == 0 and every subsequent run has active_events < 0.
When active_events == 0, the NMI handler will early-out and not record
any samples.
Signed-off-by: Anand K Mistry <amistry@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210929170405.1.I078b98ee7727f9ae9d6df8262bad7e325e40faf0@changeid
Since BTS is coherent, simply add a compiler barrier to separate the BTS
update and aux_head store.
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210809111407.596077-5-leo.yan@linaro.org
The typical way to access branch record (e.g. Intel LBR) is via hardware
perf_event. For CPUs with FREEZE_LBRS_ON_PMI support, PMI could capture
reliable LBR. On the other hand, LBR could also be useful in non-PMI
scenario. For example, in kretprobe or bpf fexit program, LBR could
provide a lot of information on what happened with the function. Add API
to use branch record for software use.
Note that, when the software event triggers, it is necessary to stop the
branch record hardware asap. Therefore, static_call is used to remove some
branch instructions in this process.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/bpf/20210910183352.3151445-2-songliubraving@fb.com
Similar to the ICX M2PCIE events, some of the SPR M2PCIE events also
have constraints. Add the constraints for SPR M2PCIE.
Fixes: f85ef898f8 ("perf/x86/intel/uncore: Add Sapphire Rapids server M2PCIe support")
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/1629991963-102621-7-git-send-email-kan.liang@linux.intel.com
SPR CHA events have the exact same event constraints as SKX, so add the
constraints.
Fixes: 949b11381f ("perf/x86/intel/uncore: Add Sapphire Rapids server CHA support")
Reported-by: Stephane Eranian <eranian@google.com>
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/1629991963-102621-5-git-send-email-kan.liang@linux.intel.com
According to the latest uncore document, both NUM_OUTSTANDING_REQ_OF_CPU
(0x88) event and COMP_BUF_OCCUPANCY(0xd5) event also have constraints. Add
them into the event constraints table.
Fixes: 2b3b76b5ec ("perf/x86/intel/uncore: Add Ice Lake server uncore support")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1629991963-102621-4-git-send-email-kan.liang@linux.intel.com
The uncore unit with the type ID 0 and the unit ID 0 is missed.
The table3 of the uncore unit maybe 0. The
uncore_discovery_invalid_unit() mistakenly treated it as an invalid
value.
Remove the !unit.table3 check.
Fixes: edae1f06c2 ("perf/x86/intel/uncore: Parse uncore discovery tables")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1629991963-102621-3-git-send-email-kan.liang@linux.intel.com
There are three channels on a Ice Lake server, but only two channels
will ever be active. Current perf only enables two channels.
Support the extra IMC channel, which may be activated on some Ice Lake
machines. For a non-activated channel, the SW can still access it. The
write will be ignored by the HW. 0 is always returned for the reading.
Fixes: 2b3b76b5ec ("perf/x86/intel/uncore: Add Ice Lake server uncore support")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1629991963-102621-2-git-send-email-kan.liang@linux.intel.com
Add <asm/amd-ibs.h> with bitfield definitions for IBS MSRs,
and demonstrate usage within the driver.
Also move 'struct perf_ibs_data' where it can be shared with
the perf tool that will soon be using it.
No functional changes.
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210817221048.88063-9-kim.phillips@amd.com
Add support to build the AMD uncore driver as a module.
This is in order to facilitate development without having
to reboot the kernel in most cases.
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210817221048.88063-8-kim.phillips@amd.com
Factor out a helper function rather than export cpu_llc_id, which is
needed in order to be able to build the AMD uncore driver as a module.
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210817221048.88063-7-kim.phillips@amd.com
free_percpu() has its own check for NULL, no need to open-code it.
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210817221048.88063-5-kim.phillips@amd.com
The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().
Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210803141621.780504-11-bigeasy@linutronix.de
The pointer 'e' is being assigned a value that is never read, the assignment
is redundant and can be removed.
Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210804115710.109608-1-colin.king@canonical.com
Assign pmu.module so the driver can't be unloaded whilst in use.
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20210817221048.88063-4-kim.phillips@amd.com
Kan Liang