perf jevents: Add ports metric group giving utilization on Intel

The ports metric group contains a metric for each port giving its
utilization as a ratio of cycles.

The metrics are created by looking for UOPS_DISPATCHED.PORT events.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add software prefetch (swpf) metric group for Intel

Add metrics that breakdown software prefetch instruction use.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add br metric group for branch statistics on Intel

The br metric group for branches itself comprises metric groups for
total, taken, conditional, fused and far metric groups using JSON
events.

Conditional taken and not taken metrics are specific to Icelake and
later generations, so the presence of the event is used to determine
whether the metric should exist.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add tsx metric group for Intel models

Allow duplicated metric to be dropped from JSON files. Detect when TSX
is supported by a model by using the JSON events, use sysfs events at
runtime as hypervisors, etc. may disable TSX.

Add CheckPmu to metric to determine if which PMUs have been associated
with the loaded events.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Mark metrics with experimental events as experimental

When metrics are made with experimental events it is desirable the
metric description also carries this information in case of metric
inaccuracies.

Suggested-by: Perry Taylor <perry.taylor@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add smi metric group for Intel models

Allow duplicated metric to be dropped from JSON files.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add CheckPmu to see if a PMU is in loaded JSON events

CheckPmu can be used to determine if hybrid events are present,
allowing for hybrid conditional metrics/events/pmus to be premised on
the JSON files rather than hard coded tables.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add idle metric for Intel models

Compute using the msr PMU the percentage of wallclock cycles where the
CPUs are in a low power state.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add RAPL metrics for all Intel models

Add a 'cpu_power' metric group that computes the power consumption
from RAPL events if they are present.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add context switch metrics for AMD

Metrics break down context switches for different kinds of
instruction.

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add load store breakdown metrics ldst for AMD

Give breakdown of number of instructions. Use the counter mask (cmask)
to show the number of cycles taken to retire the instructions.

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add uncore l3 metric group for AMD

Metrics use the amd_l3 PMU for access/miss/hit information.

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add dtlb metric group for AMD

Add metrics that give an overview and details of the dtlb (zen1, zen2,
zen3).

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add itlb metric group for AMD

Add metrics that give an overview and details of the l1 itlb (zen1,
zen2, zen3) and l2 itlb (all zens).

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add br metric group for branch statistics on AMD

The br metric group for branches itself comprises metric groups for
total, taken, conditional, fused and far metric groups using JSON
events.

The lack of conditional events on anything but zen2 means this category
is lacking on zen1, zen3 and zen4.

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add upc metric for uops per cycle for AMD

The metric adjusts for whether or not SMT is on.

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add idle metric for AMD zen models

Compute using the MSR PMU the percentage of wallclock cycles where the
CPUs are in a low power state.

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add RAPL event metric for AMD zen models

Add power per second metrics based on RAPL.

Reviewed-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Add load event JSON to verify and allow fallbacks

Add a LoadEvents function that loads all event JSON files in a
directory.

In the Event constructor ensure all events are defined in the event JSON
except for legacy events like "cycles".

If the initial event isn't found then legacy_event1 is used, and if that
isn't found legacy_event2 is used.

This allows a single Event to have multiple event names as models will
often rename the same event over time. If the event doesn't exist an
exception is raised.

So that references to metrics can be added, add the MetricRef
class. This doesn't validate as an event name and so provides an
escape hatch for metrics to refer to each other.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Build support for generating metrics from python

Generate extra-metrics.json and extra-metricgroups.json from python
architecture specific scripts. The metrics themselves will be added in
later patches.

If a build takes place in tools/perf/ then extra-metrics.json and
extra-metricgroups.json are generated in that directory and so added
to .gitignore.

If there is an OUTPUT directory then the tools/perf/pmu-events/arch
files are copied to it so the generated extra-metrics.json and
extra-metricgroups.json can be added/generated there.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Benjamin Gray <bgray@linux.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xu Yang <xu.yang_2@nxp.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf: Remove redundant kernel.h include

Now that the bitfield dependency is resolved, the explicit inclusion of
kernel.h is no longer needed.

Remove the redundant include.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools: Fix bitfield dependency failure

A perf build failure was reported by Thomas Voegtle on stable kernel
v6.6.120:

    CC      tests/sample-parsing.o
    CC      util/intel-pt-decoder/intel-pt-pkt-decoder.o
    CC      util/perf-regs-arch/perf_regs_csky.o
    CC      util/arm-spe-decoder/arm-spe-pkt-decoder.o
    CC      util/perf-regs-arch/perf_regs_loongarch.o
  In file included from util/arm-spe-decoder/arm-spe-pkt-decoder.h:10,
                   from util/arm-spe-decoder/arm-spe-pkt-decoder.c:14:
  /local/git/linux-stable-rc/tools/include/linux/bitfield.h: In function ‘le16_encode_bits’:
  /local/git/linux-stable-rc/tools/include/linux/bitfield.h:166:31: error: implicit declaration of
  function ‘cpu_to_le16’; did you mean ‘htole16’? [-Werror=implicit-function-declaration]
    ____MAKE_OP(le##size,u##size,cpu_to_le##size,le##size##_to_cpu) \
                                 ^~~~~~~~~
  /local/git/linux-stable-rc/tools/include/linux/bitfield.h:149:9: note: in definition of macro
  ‘____MAKE_OP’
    return to((v & field_mask(field)) * field_multiplier(field)); \
           ^~
  /local/git/linux-stable-rc/tools/include/linux/bitfield.h:170:1: note: in expansion of macro
  ‘__MAKE_OP’
   __MAKE_OP(16)

Fix this by including linux/kernel.h, which provides the required
definitions.

The issue was not found on the mainline due to the relevant C files have
included kernel.h.  It'd be good to merge this change on mainline
as well for robustness.

Closes: https://lore.kernel.org/stable/3a44500b-d7c8-179f-61f6-e51cb50d3512@lio96.de/
Fixes: 64d86c03e1441742 ("perf arm-spe: Extend branch operations")
Reported-by: Hamza Mahfooz <hamzamahfooz@linux.microsoft.com>
Reported-by: Thomas Voegtle <tv@lio96.de>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
To: Sasha Levin <sashal@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf sched stats: Fixes in man page

Fix the incorrect description of the schedstats report. Also fix the
spelling errors in man page.

Fixes: 800af362d68945e5 ("perf sched stats: Add details in man page")
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Reported-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anubhav Shelat <ashelat@redhat.com>
Cc: Chen Yu <yu.c.chen@intel.com>
Cc: Gautham Shenoy <gautham.shenoy@amd.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf sched stats: Define macro for SEP_LEN

Define a macro for separator length of the line in perf sched stats
report.

Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anubhav Shelat <ashelat@redhat.com>
Cc: Chen Yu <yu.c.chen@intel.com>
Cc: Gautham Shenoy <gautham.shenoy@amd.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf sched stats: correct spelling of function name

Replace store_schedtstat_cpu_diff() with store_schedstat_cpu_diff()

Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anubhav Shelat <ashelat@redhat.com>
Cc: Chen Yu <yu.c.chen@intel.com>
Cc: Gautham Shenoy <gautham.shenoy@amd.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf sched stats: Add NULL check for cd_map

In perf_sched__schedstat_live(), build_cpu_domain_map() returns the
pointer to cpu_domain_map which can also be NULL.

Add NULL check for the same to avoid NULL pointer dereference.

Fixes: 00093b3133984ffe ("perf sched stats: Add support for live mode")
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anubhav Shelat <ashelat@redhat.com>
Cc: Chen Yu <yu.c.chen@intel.com>
Cc: Gautham Shenoy <gautham.shenoy@amd.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf util: Fix NULL check in cpumask_to_cpulist()

The function cpumask_to_cpulist() allocates memory with calloc() and
stores the result in 'bm', but then incorrectly checks 'cpumask' for
NULL instead of 'bm'.

This means that if the allocation fails, the function will dereference a
NULL pointer when trying to access 'bm'.

Fix the check to test the correct variable 'bm'.

Fixes: d40c68a49f69c9bd ("perf header: Support CPU DOMAIN relation info")
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anubhav Shelat <ashelat@redhat.com>
Cc: Chen Yu <yu.c.chen@intel.com>
Cc: Gautham Shenoy <gautham.shenoy@amd.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf header: Replace hardcoded max cpus by MAX_NR_CPUS

cpumask and cpulist from cpu-domain header have hardcoded max_cpus value
of 1024.

Current systems have more cpus than this value. Replace it with
MAX_NR_CPUS.

Also define a macro to represent domain name length.

Fixes: d40c68a49f69c9bd ("perf header: Support CPU DOMAIN relation info")
Reported-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anubhav Shelat <ashelat@redhat.com>
Cc: Chen Yu <yu.c.chen@intel.com>
Cc: Gautham Shenoy <gautham.shenoy@amd.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jevents: Handle deleted JSONS in out of source builds

Make the source folders a dependency for the generated folder root so
that whenever a file is deleted from the source it will force a new
fresh copy of all the JSON files and avoid stale deleted files.

JSON_DIRS_OUTPUT_ROOT needs to be a dependency of LEGACY_CACHE_JSON so
that the root folder doesn't get cleaned after the legacy JSON is
generated. But this is a no-op with in-source builds as
JSON_DIRS_OUTPUT_ROOT is unset.

JSON_DIRS is added as a dependency of PMU_EVENTS_C which also forces a
re-build for in source builds when JSON files are deleted. This could
have also resulted in stale builds, but never a broken one.

Closes: https://lore.kernel.org/linux-next/aW5XSAo88_LBPSYI@sirena.org.uk/
Fixes: 4bb55de4ff03db3e ("perf jevents: Support copying the source json files to OUTPUT")
Reported-by: Mark Brown <broonie@kernel.org>
Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf strlist: Remove dont_dupstr logic, used only once

Ian Rogers noticed that 678ed6b707e4b2db ("perf strlist: Don't write to
const memory") breaks the 'Remove thread map' 'perf test' entry, because
it keeps pointers to the temporary string introduced to avoid touching
the const memory.

This is because the thread_map__new_by_[pt]id_str() were the only
methods using the slist->dont_dupstr knob to keep pointers to the
original const string list, as it uses strtol to parse numbers and it
stops at the comma.

As this is the only case of dont_dupstr use, dupstr being the default,
and it gets in the way of getting rid of the last const-correctness,
remove this knob, with it:

  $ perf test 37
  37: Remove thread map   : Ok
  $

Fixes: 678ed6b707e4b2db ("perf strlist: Don't write to const memory")
Reported-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf jitdump: Constify variables storing the result of strchr() on const tables

As newer glibcs will propagate the const attribute of the searched table
to its return.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf bpf-event: Constify variables storing the result of strchr() on const tables

As newer glibcs will propagate the const attribute of the searched table
to its return.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf demangle-java: Constify variables storing the result of strchr() on const tables

As newer glibcs will propagate the const attribute of the searched table
to its return.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf time-utils: Constify variables storing the result of strchr() on const tables

As newer glibcs will propagate the const attribute of the searched table
to its return.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf units: Constify variables storing the result of strchr() on const tables

As newer glibcs will propagate the const attribute of the searched table
to its return.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf trace-event: Constify variables storing the result of strchr() on const tables

As newer glibcs will propagate the const attribute of the searched table
to its return.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf tp_pmu: Address const-correctness errors in recent glibcs

To avoid having more variables, just cast the const variable searched to
non-const since the result will not be modified, its only later that
that variable will be used to modify something, but then its non-const
memory being modified, so using a cast is the cheapest thing here.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf hwmon_pmu: Constify the variables returning bsearch() on const tables

To address const-correctness errors on newer glibcs (-Werror=discarded-qualifiers).

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf session: Don't write to memory pointed to a const pointer

Since it is freshly allocated just attribute it to a non-const pointer
and then change it via that pointer.

That way we avoid const-correctness warnings in recent glibc versions.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf strlist: Don't write to const memory

Do a strdup to the list string and parse from it, free at the end.

This is to deal with newer glibcs const-correctness.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf metricgroup: Constify variables storing the result of strchr() on const tables

As newer glibcs will propagate the const attribute of the searched table
to its return.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf disasm: Constify variables storing the result of bsearch() on const tables

As newer glibcs will propagate the const attribute of the searched table
to its return.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf thread-stack: Switch thread_stack__init() to use e_machine

The architecture type is used to set the retpoline state.

Rather than use the arch string switch to using the ELF machine that's
readily available within the thread.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Yujie Liu <yujie.liu@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf callchain: Switch callchain_param_setup from an arch to an e_machine

Increase use of e_machine by replacing callchain_param_setup's arch
argument to be an e_machine typically read from the session.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Yujie Liu <yujie.liu@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf script: Fix script_fetch_insn for more than just x86

The script_fetch_insn code was only supported on natively running x86.

Implement a crude elf_machine_max_instruction_length function and use to
give an instruction length on more than just x86.

Use the ELF machine to determine the length to use to support
cross-architecture development.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Yujie Liu <yujie.liu@intel.com>
[ Conditionally define EM_CSKY and EM_LOONGARCH for older distros ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf session: Print all machines in session dump

perf_session__fprintf() prints only the host.

This has been changed to print details of host and all guests, by
traversing through the RB-Tree.

These are visible when using high verbosity (-vvvv) in KVM environments,
during perf report dumps.

Testing:

- Test 1: Record the local machine and guest VM using 'perf kvm record' and
generate the report using 'perf kvm report -vvvv -D'. The dump should show
the threads and other details related to local and guest machine.
    - 1 Ubuntu VM running on Fedora host
    - VM is running a noisy program =>
$ dd if=/dev/urandom of=/dev/null
    - On host run =>
$ sudo ./perf kvm --guestvmlinux=/tmp/shared/guest_vmlinux \
                        --guestkallsyms=/tmp/shared/guest_kallsyms \
                        --guestmodules=/tmp/shared/guest_modules \
                        record -a -g -o perf.data.guest
      and exit after a few seconds.
      [ perf record: Woken up 9 times to write data ]
      [ perf record: Captured and wrote 3.150 MB perf.data.guest \
(29311 samples) ]
    - Generate dump =>
$ sudo ./perf kvm --guestkallsyms /tmp/shared/guest_kallsyms \
                        report -vvvv -D -i perf.data.guest > output.txt
    - Check for threads associated with guest machine.
      $ grep "Thread 0" output.txt
      Thread 0 swapper
      Thread 0 [guest/0]
    PASS

- Test 2: Record the local machine and guest VM using 'perf kvm record' and
generate the report using 'perf kvm report'. The functions running on
guest VM should be seen in the report.
    - Same setup as Test 1 but the test looks at the performance profile,
      to check if the function names are visible.
    - Peek into profile using =>
$ sudo ./perf kvm  --guestkallsyms /tmp/shared/guest_kallsyms \
                                    report -i perf.data.guest
    - Samples: 29K of event 'cycles', Event count (approx.): 28711693142
Children   Self  Command  Shared Object            Symbol
35.69%   35.69%  :5820    [guest.kernel.kallsyms]  [g] chacha_permute
11.56%   11.56%  :5820    [guest.kernel.kallsyms]  [g] entry_SYSRETQ_unsXXX
11.12%   11.12%  :5820    [guest.kernel.kallsyms]  [g] syscall_return_viXXX
 7.36%    7.36%  :5820    [guest.kernel.kallsyms]  [g] entry_SYSCALL_64_XXX
 6.07%    6.07%  :5820    [guest.kernel.kallsyms]  [g] chacha_block_generic
 5.40%    5.40%  :5820    [guest.kernel.kallsyms]  [g] _copy_to_iter
 ....
    PASS

- Test 3: Record the local and 2 guest VMs using 'perf kvm record' and
generate the report using 'perf kvm report -vvvv -D'. The dump should show
the threads and other details related to local and guest machines.
    - 1 Ubuntu and 1 Alpine VMs running on Fedora host.
    - Find PIDs of qemu instances and use them during record and report
$ pgrep qemu
        5816
        25098
    - Record the activity =>
$ sudo ./perf kvm record -p 5816,25098 -a -g -o perf.data.guests
        Warning:
        PID/TID switch overriding SYSTEM
        [ perf record: Woken up 325927 times to write data ]
        [ perf record: Captured and wrote 3.692 MB perf.data.guests \
  (57389 samples) ]
    - Generate dump =>
$ sudo ./perf kvm report -vvvv -D -i perf.data.guests > output.txt
    - Check if the threads related to the local machine and guest VMs
      are present =>
$ grep "Thread 0" output.txt
        Thread 0 swapper
        Thread 0 [guest/0]
      NOTE: Threads from Ubuntu and Alpine VMs are bundled together and
      appear as one guest machine.
      Looking into output.txt =>
Threads: 6
Thread 0 [guest/0]
Thread 5816 :5816
Thread 25098 :25098
Thread 5819 :5819
Thread 5820 :5820
Thread 25103 :25103
      To conclude, information is collected for both VMs and not listed
      as two different guest machines.
    PASS

- Test 4: Check if any guest-related information is printed in
perf annotate. This test is included because the command calls
perf_session__fprintf() in its code path when using -vvvv option.
This could be explained by inability / lack of options for 'perf annotate'
to look into guest VM from host machine, due to no option to specify the
guest's kallsyms or modules. A similar explanation for 'perf mem' could
be used, as perf_session__fprintf() is also present in its code path.
    - Run annotate =>
$ sudo ./perf annotate -i perf.data.guest -vvvv  > output.txt
    - Check for threads from local machine or guest VM =>
$ grep "Thread 0" output.txt
        Thread 0 swapper

        Threads from local machine are found while threads from guest VM
are not found. It is possibly because of a lack of a guest kallsyms
option for DSO matching in perf annotate.
    PASS

- Test 5: Run kvm test available on perf path
    - $ sudo ./perf test kvm
        89: perf kvm tests                                            : Ok
    PASS

Signed-off-by: Hrishikesh Suresh <hrishikesh123s@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Blake Jones <blakejones@google.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
[ Declare 'nd' in the 'for' line and and 'pos' inside the loop body, to make it more compact ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf unwind-libdw: Wire up e_flags for CSKY

Wire up the e_flags now it can be read for a thread. The e_flags
encode the CSKY ABI level and this can impact which perf registers
need setting up for unwinding.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Tianyou Li <tianyou.li@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf perf_regs: Accurately compute register names for CSKY

CSKY needs the e_flags to determine the ABI level and know whether
additional registers are encoded or not. Wire this up now that the
e_flags for a thread can be determined.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Tianyou Li <tianyou.li@intel.com>
[ Conditionally define EF_CSKY_ABIMASK and EF_CSKY_ABIV2 for older distros ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf thread: Add optional e_flags output argument to thread__e_machine

The e_flags are needed to accurately compute complete perf register
information for CSKY.

Add the ability to read and have this value associated with a thread.

This change doesn't wire up the use of the e_flags except in disasm
where use already exists but just wasn't set up yet.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Tianyou Li <tianyou.li@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf dso: Factor out e_machine reading for use in thread

Factor out the resilient e_machine reading code in dso so that it may
be used in thread.

As there is no dso in that case, make the dso optional.

This makes some minor other changes as the swap type from the dso cannot
be ascertained.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Tianyou Li <tianyou.li@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf vendor events amd: Fix Zen 5 MAB allocation events

The unit masks for PMCx041 vary across different generations of Zen
processors.

Fix the Zen 5 events based on PMCx041 as they incorrectly use the same
unit masks as that of Zen 4.

Fixes: 45c072f2537ab07b ("perf vendor events amd: Add Zen 5 core events")
Reported-by: Suyash Mahar <smahar@meta.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ananth Narayan <ananth.narayan@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf test: Fix test perf evlist for z/VM s390x

Perf test case 'perf evlist tests' fails on z/VM machines on s390.

The failure is causes by event cycles. This event is not available
on virtualized machines like z/VM on s390.

Change to software event cpu-clock to fix this.

    Output before:
      # ./perf test 78
      79: perf evlist tests              : FAILED!
      #

    Output after:
      # ./perf test 78
      79: perf evlist tests              : Ok
      #

Fixes: b04d2b9199129f4f ("perf test: Fix test case perf evlist tests for s390x")
Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: Jan Polensky <japo@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Tested-by: Jan Polensky <japo@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf annotate: Fix BUILD_NONDISTRO=1 missing args->ms conversions to pointer

Fix a few missing conversions to pointer in the usage of 'struct
annotate_args' 'ms' member in symbol__disassemble_bpf_libbfd().

Fixes: 00419892bac28bf1 ("perf annotate: Fix args leak of map_symbol")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools headers: Don't check arm64's unistd.h

The arm64 unistd.h in tools now diverges from the kernel header.
Comparing the two headers is pointless, remove the check.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Revert "perf tools: Fix arm64 build by generating unistd_64.h"

This reverts:

commit 8988c4b91945173a ("perf tools: Fix in-source libperf build")
commit bfb713ea53c746b0 ("perf tools: Fix arm64 build by generating unistd_64.h")

Since we now have a static unistd_64.h for the arm64 build, there is no
need to generate unistd_64.h in libperf.  Revert all patches related to
generating unistd_64.h.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools headers: Go back to include asm-generic/unistd.h for arm64

The header unistd.h is included under Arm64's uAPI folder (see
tools/arch/arm64/include/uapi/asm/), but it does not include its
dependent header unistd_64.h.

The intention is for unistd_64.h to be generated dynamically using
scripts/Makefile.asm-headers.

However, this dynamic approach causes problems because the header is not
available early enough, even though it is widely included throughout
tools.

Using the perf build as an example:

 1) Feature detection: Perf first runs feature tests.

    The BPF feature program test-bpf.c includes unistd.h.  Since
    unistd_64.h has not been generated yet, the program fails to build,
    and the BPF feature ends up being disabled.

 2) libperf build:

    The libperf Makefile later generates unistd_64.h on the fly, so
    libperf itself builds successfully.

 3) Final perf build:

    Although the perf binary can build successfully using the generated
    header, we never get a chance to build BPF skeleton programs,
    because BPF support was already disabled earlier.

Restore to include asm-generic/unistd.h for fixing the issue.  This
aligns with most architectures (x86 is a special case that keeps
unistd_32.h/unistd_64.h for its particular syscall numbers) and ensures
the header is available from the start.

Fixes: 22f72088ffe69a37 ("tools headers: Update the syscall table with the kernel sources")
Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Merge remote-tracking branch 'torvalds/master' into perf-tools-next

Merge with upstream to pick up fixes from perf-tools and from other
tools/ parts that interact with tools/perf.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Merge tag 'vfs-6.19-rc8.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:

 - Fix the the buggy conversion of fuse_reverse_inval_entry() introduced
   during the creation rework

 - Disallow nfs delegation requests for directories by setting
   simple_nosetlease()

 - Require an opt-in for getting readdir flag bits outside of S_DT_MASK
   set in d_type

 - Fix scheduling delayed writeback work by only scheduling when the
   dirty time expiry interval is non-zero and cancel the delayed work if
   the interval is set to zero

 - Use rounded_jiffies_interval for dirty time work

 - Check the return value of sb_set_blocksize() for romfs

 - Wait for batched folios to be stable in __iomap_get_folio()

 - Use private naming for fuse hash size

 - Fix the stale dentry cleanup to prevent a race that causes a UAF

* tag 'vfs-6.19-rc8.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  vfs: document d_dispose_if_unused()
  fuse: shrink once after all buckets have been scanned
  fuse: clean up fuse_dentry_tree_work()
  fuse: add need_resched() before unlocking bucket
  fuse: make sure dentry is evicted if stale
  fuse: fix race when disposing stale dentries
  fuse: use private naming for fuse hash size
  writeback: use round_jiffies_relative for dirtytime_work
  iomap: wait for batched folios to be stable in __iomap_get_folio
  romfs: check sb_set_blocksize() return value
  docs: clarify that dirtytime_expire_seconds=0 disables writeback
  writeback: fix 100% CPU usage when dirtytime_expire_interval is 0
  readdir: require opt-in for d_type flags
  vboxsf: don't allow delegations to be set on directories
  ceph: don't allow delegations to be set on directories
  gfs2: don't allow delegations to be set on directories
  9p: don't allow delegations to be set on directories
  smb/client: properly disallow delegations on directories
  nfs: properly disallow delegation requests on directories
  fuse: fix conversion of fuse_reverse_inval_entry() to start_removing()

Linux 6.19-rc7

Merge tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull SCSI fixes from James Bottomley:
 "Only one core change, the rest are drivers.

  The core change reorders some state operations in the error handler to
  try to prevent missed wake ups of the error handler (which can halt
  error processing and effectively freeze the entire system)"

* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
  scsi: qla2xxx: Sanitize payload size to prevent member overflow
  scsi: target: iscsi: Fix use-after-free in iscsit_dec_session_usage_count()
  scsi: target: iscsi: Fix use-after-free in iscsit_dec_conn_usage_count()
  scsi: core: Wake up the error handler when final completions race against each other
  scsi: storvsc: Process unsupported MODE_SENSE_10
  scsi: xen: scsiback: Fix potential memory leak in scsiback_remove()

Merge tag 'keys-trusted-next-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd

Pull keys fix from Jarkko Sakkinen.

* tag 'keys-trusted-next-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd:
  keys/trusted_keys: fix handle passed to tpm_buf_append_name during unseal

Merge tag 'char-misc-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc/iio driver fixes from Greg KH:
 "Here are some small char/misc/iio and some other minor driver
  subsystem fixes for 6.19-rc7. Nothing huge here, just some fixes for
  reported issues including:

   - lots of little iio driver fixes

   - comedi driver fixes

   - mux driver fix

   - w1 driver fixes

   - uio driver fix

   - slimbus driver fixes

   - hwtracing bugfix

   - other tiny bugfixes

  All of these have been in linux-next for a while with no reported
  issues"

* tag 'char-misc-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (36 commits)
  comedi: dmm32at: serialize use of paged registers
  mei: trace: treat reg parameter as string
  uio: pci_sva: correct '-ENODEV' check logic
  uacce: ensure safe queue release with state management
  uacce: implement mremap in uacce_vm_ops to return -EPERM
  uacce: fix isolate sysfs check condition
  uacce: fix cdev handling in the cleanup path
  slimbus: core: clean up of_slim_get_device()
  slimbus: core: fix of_slim_get_device() kernel doc
  slimbus: core: amend slim_get_device() kernel doc
  slimbus: core: fix device reference leak on report present
  slimbus: core: fix runtime PM imbalance on report present
  slimbus: core: fix OF node leak on registration failure
  intel_th: rename error label
  intel_th: fix device leak on output open()
  comedi: Fix getting range information for subdevices 16 to 255
  mux: mmio: Fix IS_ERR() vs NULL check in probe()
  interconnect: debugfs: initialize src_node and dst_node to empty strings
  iio: dac: ad3552r-hs: fix out-of-bound write in ad3552r_hs_write_data_source
  iio: accel: iis328dq: fix gain values
  ...

Merge tag 'tty-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty

Pull serial driver fixes from Greg KH:
 "Here are three small serial driver fixes for 6.19-rc7 that resolve
  some reported issues. They include:

   - tty->port race condition fix for a reported problem

   - qcom_geni serial driver fix

   - 8250_pci serial driver fix

  All of these have been in linux-next with no reported issues"

* tag 'tty-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
  serial: Fix not set tty->port race condition
  serial: 8250_pci: Fix broken RS485 for F81504/508/512
  serial: qcom_geni: Fix BT failure regression on RB2 platform

Merge tag 'i2c-for-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux

Pull i2c fix from Wolfram Sang:

 - k1: drop wrong IRQF_ONESHOT from IRQ request to fix genirq warning

* tag 'i2c-for-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
  i2c: spacemit: drop IRQF_ONESHOT flag from IRQ request

Merge tag 'input-for-v6.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input

Pull input fixes from Dmitry Torokhov:

 - a couple of quirks to i8042 to enable keyboard on a Asus and MECHREVO
   laptops

* tag 'input-for-v6.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
  Input: i8042 - add quirks for MECHREVO Wujie 15X Pro
  Input: i8042 - add quirk for ASUS Zenbook UX425QA_UM425QA

keys/trusted_keys: fix handle passed to tpm_buf_append_name during unseal

TPM2_Unseal[1] expects the handle of a loaded data object, and not the
handle of the parent key. But the tpm2_unseal_cmd provides the parent
keyhandle instead of blob_handle for the session HMAC calculation. This
causes unseal to fail.

Fix this by passing blob_handle to tpm_buf_append_name().

References:

[1] trustedcomputinggroup.org/wp-content/uploads/
    Trusted-Platform-Module-2.0-Library-Part-3-Version-184_pub.pdf

Fixes: 6e9722e9a7bf ("tpm2-sessions: Fix out of range indexing in name_size")
Signed-off-by: Srish Srinivasan <ssrish@linux.ibm.com>
Reviewed-by: Stefan Berger <stefanb@linux.ibm.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>

Input: i8042 - add quirks for MECHREVO Wujie 15X Pro

The MECHREVO Wujie 15X Pro requires several i8042 quirks to function
correctly. Specifically, NOMUX, RESET_ALWAYS, NOLOOP, and NOPNP are
needed to ensure the keyboard and touchpad work reliably.

Signed-off-by: gongqi <550230171hxy@gmail.com>
Link: https://patch.msgid.link/20260122155501.376199-3-550230171hxy@gmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>

Input: i8042 - add quirk for ASUS Zenbook UX425QA_UM425QA

The ASUS Zenbook UX425QA_UM425QA fails to initialize the keyboard after
a cold boot.

A quirk already exists for "ZenBook UX425", but some Zenbooks report
"Zenbook" with a lowercase 'b'. Since DMI matching is case-sensitive,
the existing quirk is not applied to these "extra special" Zenbooks.

Testing confirms that this model needs the same quirks as the ZenBook
UX425 variants.

Signed-off-by: feng <alec.jiang@gmail.com>
Link: https://patch.msgid.link/20260122013957.11184-1-alec.jiang@gmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>

Merge tag 'riscv-for-linus-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V fixes from Paul Walmsley:
 "The notable changes here are the three RISC-V timer compare register
  update sequence patches. These only apply to RV32 systems and are
  related to the 64-bit timer compare value being split across two
  separate 32-bit registers.

  We weren't using the appropriate three-write sequence, documented in
  the RISC-V ISA specifications, to avoid spurious timer interrupts
  during the update sequence; so, these patches now use the recommended
  sequence.

  This doesn't affect 64-bit RISC-V systems, since the timer compare
  value fits inside a single register and can be updated with a single
  write.

   - Fix the RISC-V timer compare register update sequence on RV32
     systems to use the recommended sequence in the RISC-V ISA manual

     This avoids spurious interrupts during updates

   - Add a dependence on the new CONFIG_CACHEMAINT_FOR_DMA Kconfig
     symbol for Renesas and StarFive RISC-V SoCs

   - Add a temporary workaround for a Clang compiler bug caused by using
     asm_goto_output for get_user()

   - Clarify our documentation to specifically state a particular ISA
     specification version for a chapter number reference"

* tag 'riscv-for-linus-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: Add intermediate cast to 'unsigned long' in __get_user_asm
  riscv: Use 64-bit variable for output in __get_user_asm
  soc: renesas: Fix missing dependency on new CONFIG_CACHEMAINT_FOR_DMA
  riscv: ERRATA_STARFIVE_JH7100: Fix missing dependency on new CONFIG_CACHEMAINT_FOR_DMA
  riscv: suspend: Fix stimecmp update hazard on RV32
  riscv: kvm: Fix vstimecmp update hazard on RV32
  riscv: clocksource: Fix stimecmp update hazard on RV32
  Documentation: riscv: uabi: Clarify ISA spec version for canonical order

Merge tag 'ntb-6.19-bugfixes' of https://github.com/jonmason/ntb

Pull NTB fix from Jon Mason:
 "Bug fix for uninitialized mutex in ntb transport"

* tag 'ntb-6.19-bugfixes' of https://github.com/jonmason/ntb:
  ntb: transport: Fix uninitialized mutex

Merge tag 'trace-v6.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Fix a crash with passing a stacktrace between synthetic events

   A synthetic event is an event that combines two events into a single
   event that can display fields from both events as well as the time
   delta that took place between the events. It can also pass a
   stacktrace from the first event so that it can be displayed by the
   synthetic event (this is useful to get a stacktrace of a task
   scheduling out when blocked and recording the time it was blocked
   for).

   A synthetic event can also connect an existing synthetic event to
   another event. An issue was found that if the first synthetic event
   had a stacktrace as one of its fields, and that stacktrace field was
   passed to the new synthetic event to be displayed, it would crash the
   kernel. This was due to the stacktrace not being saved as a
   stacktrace but was still marked as one. When the stacktrace was read,
   it would try to read an array but instead read the integer metadata
   of the stacktrace and dereferenced a bad value.

   Fix this by saving the stacktrace field as a stacktrace.

 - Fix possible overflow in cmp_mod_entry() compare function

   A binary search is used to find a module address and if the addresses
   are greater than 2GB apart it could lead to truncation and cause a
   bad search result. Use normal compares instead of a subtraction
   between addresses to calculate the compare value.

 - Fix output of entry arguments in function graph tracer

   Depending on the configurations enabled, the entry can be two
   different types that hold the argument array. The macro
   FGRAPH_ENTRY_ARGS() is used to find the correct arguments from the
   given type. One location was missed and still referenced the
   arguments directly via entry->args and could produce the wrong value
   depending on how the kernel was configured.

 - Fix memory leak in scripts/tracepoint-update build tool

   If the array fails to allocate, the memory for the values needs to be
   freed and was not. Free the allocated values if the array failed to
   allocate.

* tag 'trace-v6.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  scripts/tracepoint-update: Fix memory leak in add_string() on failure
  function_graph: Fix args pointer mismatch in print_graph_retval()
  tracing: Avoid possible signed 64-bit truncation
  tracing: Fix crash on synthetic stacktrace field usage

Documentation: Project continuity

Document project continuity procedures.  This is a plan for a plan for
navigating events that affect the forward progress of the canonical
Linux repository, torvalds/linux.git.

It is a follow-up from Maintainer Summit [1].

Co-developed-by: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Miguel Ojeda <ojeda@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Jiri Kosina <jkosina@suse.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Link: https://lwn.net/Articles/1050179/
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Merge tag 'driver-core-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core

Pull driver core fixes from Danilo Krummrich:

 - Always inline I/O and IRQ methods using build_assert!() to avoid
   false positive build errors

 - Do not free the driver's device private data in I2C shutdown()
   avoiding race conditions that can lead to UAF bugs

 - Drop the driver's device private data after the driver has been
   fully unbound from its device to avoid UAF bugs from &Device<Bound>
   scopes, such as IRQ callbacks

* tag 'driver-core-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core:
  rust: driver: drop device private data post unbind
  rust: driver: add DriverData type to the DriverLayout trait
  rust: driver: add DEVICE_DRIVER_OFFSET to the DriverLayout trait
  rust: driver: introduce a DriverLayout trait
  rust: auxiliary: add Driver::unbind() callback
  rust: i2c: do not drop device private data on shutdown()
  rust: irq: always inline functions using build_assert with arguments
  rust: io: always inline functions using build_assert with arguments

Merge tag 'timers-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer fixes from Ingo Molnar:

 - Fix auxiliary timekeeper update & locking bug

 - Reduce the sensitivity of the clocksource watchdog,
   to fix false positive measurements that marked the
   TSC clocksource unstable

* tag 'timers-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  clocksource: Reduce watchdog readout delay limit to prevent false positives
  timekeeping: Adjust the leap state for the correct auxiliary timekeeper

Merge tag 'sched-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:

 - Fix PELT clock synchronization bug when entering idle

 - Disable the NEXT_BUDDY feature, as during extensive testing
   Mel found that the negatives outweigh the positives

 - Make wakeup preemption less aggressive, which resulted in
   an unreasonable increase in preemption frequency

* tag 'sched-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Revert force wakeup preemption
  sched/fair: Disable scheduler feature NEXT_BUDDY
  sched/fair: Fix pelt clock sync when entering idle

Merge tag 'perf-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events fixes from Ingo Molnar:

 - Fix mmap_count warning & bug when creating a group member event
   with the PERF_FLAG_FD_OUTPUT flag

 - Disable the sample period == 1 branch events BTS optimization
   on guests, because BTS is not virtualized

* tag 'perf-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Do not enable BTS for guests
  perf: Fix refcount warning on event->mmap_count increment

Merge tag 'objtool-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool fix from Ingo Molnar:
 "Fix objtool build error in non-standard static library build
  environments"

* tag 'objtool-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  objtool: Fix libopcodes linking with static libraries

Merge tag 'irq-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq fixes from Ingo Molnar:

 - Fix spurious interrupts during resume in the renesas-rzv2h driver

 - Fix a 32+ bit physical memory truncation bug in the gic-v3-its driver

* tag 'irq-urgent-2026-01-24' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  irqchip/gic-v3-its: Avoid truncating memory addresses
  irqchip/renesas-rzv2h: Prevent TINT spurious interrupt during resume

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull arm64 kvm fixes from Paolo Bonzini:

 - Ensure early return semantics are preserved for pKVM fault handlers

 - Fix case where the kernel runs with the guest's PAN value when
   CONFIG_ARM64_PAN is not set

 - Make stage-1 walks to set the access flag respect the access
   permission of the underlying stage-2, when enabled

 - Propagate computed FGT values to the pKVM view of the vCPU at
   vcpu_load()

 - Correctly program PXN and UXN privilege bits for hVHE's stage-1 page
   tables

 - Check that the VM is actually using VGICv3 before accessing the GICv3
   CPU interface

 - Delete some unused code

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: arm64: Invert KVM_PGTABLE_WALK_HANDLE_FAULT to fix pKVM walkers
  KVM: arm64: Don't blindly set set PSTATE.PAN on guest exit
  KVM: arm64: nv: Respect stage-2 write permssion when setting stage-1 AF
  KVM: arm64: Remove unused vcpu_{clear,set}_wfx_traps()
  KVM: arm64: Remove unused parameter in synchronize_vcpu_pstate()
  KVM: arm64: Remove extra argument for __pvkm_host_{share,unshare}_hyp()
  KVM: arm64: Inject UNDEF for a register trap without accessor
  KVM: arm64: Copy FGT traps to unprotected pKVM VCPU on VCPU load
  KVM: arm64: Fix EL2 S1 XN handling for hVHE setups
  KVM: arm64: gic: Check for vGICv3 when clearing TWI

Merge tag 'i2c-host-fixes-6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux into i2c/for-current

i2c-host-fixes for v6.19-rc7

k1: drop IRQF_ONESHOT from IRQ request to fix genirq warning.

Merge tag 'kvmarm-fixes-6.19-1' of https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 6.19

 - Ensure early return semantics are preserved for pKVM fault handlers

 - Fix case where the kernel runs with the guest's PAN value when
   CONFIG_ARM64_PAN is not set

 - Make stage-1 walks to set the access flag respect the access
   permission of the underlying stage-2, when enabled

 - Propagate computed FGT values to the pKVM view of the vCPU at
   vcpu_load()

 - Correctly program PXN and UXN privilege bits for hVHE's stage-1 page
   tables

 - Check that the VM is actually using VGICv3 before accessing the GICv3
   CPU interface

 - Delete some unused code

Merge tag 'kbuild-fixes-6.19-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kbuild/linux

Pull kbuild fixes from Nicolas Schier:

 - Reduce possible complications when cross-compiling by increasing use
   of ${NM} in check-function-names.sh

 - Fix static linking of nconf

* tag 'kbuild-fixes-6.19-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kbuild/linux:
  kconfig: fix static linking of nconf
  kbuild: prefer ${NM} in check-function-names.sh

Merge tag 's390-6.19-4' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 fixes from Heiko Carstens:

 - Add $(DISABLE_KSTACK_ERASE) to vdso compile flags to fix compile
   errors with old gcc versions

 - Fix path to s390 chacha implementation in vdso selftests, after
   vdso64 has been renamed to vdso

 - Fix off-by-one bug in APQN limit calculation

 - Discard .modinfo section from decompressor image to fix SecureBoot

* tag 's390-6.19-4' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390/boot/vmlinux.lds.S: Ensure bzImage ends with SecureBoot trailer
  s390/ap: Fix wrong APQN fill calculation
  selftests: vDSO: getrandom: Fix path to s390 chacha implementation
  s390/vdso: Disable kstack erase

Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Catalin Marinas:

 - A set of fixes for FPSIMD/SVE/SME state management (around signal
   handling and ptrace) where a task can be placed in an invalid state

 - __nocfi added to swsusp_arch_resume() to avoid a data abort on
   resuming from hibernate

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: Set __nocfi on swsusp_arch_resume()
  arm64/fpsimd: signal: Fix restoration of SVE context
  arm64/fpsimd: signal: Allocate SSVE storage when restoring ZA
  arm64/fpsimd: ptrace: Fix SVE writes on !SME systems

Merge tag 'v6.19-rc6-server-fixes' of git://git.samba.org/ksmbd

Pull smb server fixes from Steve French:

 - Use the original nents value for ib_dma_unmap_sg(), preventing
   potential memory corruption in the RDMA transport layer

 - Fix a naming discrepancy in the kernel-doc for
   ksmbd_vfs_kern_path_start_removing() as identified by sparse static
   analysis

 - Reset smb_direct_port to its default value during initialization to
   ensure the correct port is used when switching between different RDMA
   device types without module reload

* tag 'v6.19-rc6-server-fixes' of git://git.samba.org/ksmbd:
  smb: server: reset smb_direct_port = SMB_DIRECT_PORT_INFINIBAND on init
  smb: server: fix comment for ksmbd_vfs_kern_path_start_removing()
  ksmbd: smbd: fix dma_unmap_sg() nents

Merge tag 'pci-v6.19-fixes-4' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci

Pull PCI fixes from Bjorn Helgaas:

 - Fix the pci_do_resource_release_and_resize() failure path, which
   clobbered the intended failure return value (Ilpo Järvinen)

 - Restore resizable BAR size before value because the size determines
   which bits are writable; this fixes i915 and xe regressions (Ilpo
   Järvinen)

* tag 'pci-v6.19-fixes-4' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci:
  PCI: Fix Resizable BAR restore order
  PCI: Fix BAR resize rollback path overwriting ret

Merge tag 'platform-drivers-x86-v6.19-3' of git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86

Pull x86 platform driver fixes from Ilpo Järvinen:

 - acer-wmi:
     - Extend support for Acer Nitro AN515-58
     - Fix missing capability check

 - amd/wbrf: Fix memory leak in wbrf_record()

 - asus-armoury:
     - Fix GA403U* matching
     - Fix FA608UM TDP data
     - Add many models

 - asus-wmi: Move OOBE presence check outside deprecation ifdef

 - hp-bioscfg:
     - Fix kernel panic in GET_INSTANCE_ID macro
     - Fix kobject warnings for empty attribute names
     - Correct GUID to uppercase (lowercase letter prevented autoloading
       the module)

 - mellanox: Fix SN5640/SN5610 LED platform data

 - docs:
     - alienware-wmi: Typo fix
     - amd_hsmp: Fix document link

* tag 'platform-drivers-x86-v6.19-3' of git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86: (21 commits)
  platform/x86: acer-wmi: Fix missing capability check
  platform/x86: acer-wmi: Extend support for Acer Nitro AN515-58
  platform/x86: asus-armoury: add support for GA403WW
  platform/x86: asus-armoury: keep the list ordered alphabetically
  platform/x86: asus-armoury: add support for G835L
  platform/x86: asus-armoury: fix ppt data for FA608UM
  platform/x86: hp-bioscfg: Fix automatic module loading
  platform/x86: hp-bioscfg: Fix kernel panic in GET_INSTANCE_ID macro
  platform/x86: hp-bioscfg: Fix kobject warnings for empty attribute names
  platform/x86: asus-wmi: fix sending OOBE at probe
  platform/x86: asus-armoury: add support for FA617XT
  platform/x86: asus-armoury: add support for FA401UV
  platform/x86: asus-armoury: add support for GV302XV
  platform/x86: asus-armoury: Add power limits for Asus G513QY
  platform/x86/amd: Fix memory leak in wbrf_record()
  platform/mellanox: Fix SN5640/SN5610 LED platform data
  docs: fix PPR for AMD EPYC broken link
  docs: alienware-wmi: fix typo
  platform/x86: asus-armoury: add support for GA403UV
  asus-armoury: fix ppt data for GA403U* renaming to GA403UI
  ...

Merge tag 'pmdomain-v6.19-rc3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/linux-pm

Pull pmdomain fixes from Ulf Hansson:

 - imx: Remove incorrect reset/clock mask for 8mq vpu

 - rockchip: Fix initial state of PM domain

* tag 'pmdomain-v6.19-rc3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/linux-pm:
  pmdomain:rockchip: Fix init genpd as GENPD_STATE_ON before regulator ready
  pmdomain: imx8m-blk-ctrl: Remove separate rst and clk mask for 8mq vpu

Merge tag 'mmc-v6.19-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc

Pull MMC fixes from Ulf Hansson:

 - rtsx_pci_sdmmc: Fix signal voltage switch

 - sdhci-of-dwcmshc:
     - A couple of fixes for Eswin EIC7700
     - Fix support for HS200/HS400 mode

* tag 'mmc-v6.19-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc:
  mmc: sdhci-of-dwcmshc: Fix DMA 128MB boundary for Eswin EIC7700
  mmc: sdhci-of-dwcmshc: Fix init for AXI clock for Eswin EIC7700
  mmc: rtsx_pci_sdmmc: implement sdmmc_card_busy function
  mmc: sdhci-of-dwcmshc: Prevent illegal clock reduction in HS200/HS400 mode

Merge tag 'block-6.19-20260122' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block fixes from Jens Axboe:

 - A set of selftest fixes for ublk

 - Fix for a pid mismatch in ublk, comparing PIDs in different
   namespaces if run inside a namespace

 - Fix for a regression added in this release with polling, where the
   nvme tcp connect code would spin forever

 - Zoned device error path fix

 - Tweak the blkzoned uapi additions from this kernel release, making
   them more easily discoverable

 - Fix for a regression in bcache with bio endio handling added in this
   release

* tag 'block-6.19-20260122' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  bcache: use bio cloning for detached device requests
  blk-mq: use BLK_POLL_ONESHOT for synchronous poll completion
  selftests/ublk: fix garbage output in foreground mode
  selftests/ublk: fix error handling for starting device
  selftests/ublk: fix IO thread idle check
  block: make the new blkzoned UAPI constants discoverable
  ublk: fix ublksrv pid handling for pid namespaces
  block: Fix an error path in disk_update_zone_resources()

Merge tag 'io_uring-6.19-20260122' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring fixes from Jens Axboe:

 - Fix for a potential leak of an iovec, if a specific cleanup path is
   used and the rw_cache is full at the time of the call

 - Fix for a regression added in this cycle, where waitid should be
   using prober release/acquire semantics for updating the wait queue
   head

 - Check for the cancelation bit being set for every work item processed
   by io-wq, not just at the start of the loop. Has no real practical
   implications other than to shut up syzbot doing crazy things that
   grossly overload a system, hence slowing down ring exit

 - A few selftest additions, updating the mini_liburing that selftests
   use

* tag 'io_uring-6.19-20260122' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  selftests/io_uring: support NO_SQARRAY in miniliburing
  selftests/io_uring: add io_uring_queue_init_params
  io_uring/io-wq: check IO_WQ_BIT_EXIT inside work run loop
  io_uring/waitid: fix KCSAN warning on io_waitid->head
  io_uring/rw: free potentially allocated iovec on cache put failure

Merge tag 'iommu-fixes-v6.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux

Pull iommu fixes from Joerg Roedel:

 - AMD IOMMU: Fix potential NULL-ptr dereference in error path
   of amd_iommu_probe_device()

 - Generic IOMMUPT: Fix another compiler issue seen with older
   compiler versions

 - Fix signedness issue in ARM IO-PageTable code

* tag 'iommu-fixes-v6.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux:
  iommu/io-pgtable-arm: fix size_t signedness bug in unmap path
  iommupt: Make it clearer to the compiler that pts.level == 0 for single page
  iommu/amd: Fix error path in amd_iommu_probe_device()

perf regs: Refactor use of arch__sample_reg_masks() to perf_reg_name()

arch__sample_reg_masks isn't supported on ARM(32), csky, loongarch,
MIPS, RISC-V and s390.

The table returned by the function just has the name of a register
paired with the corresponding sample_regs_user mask value.

For a given perf register we can compute the name with perf_reg_name and
the mask is just 1 left-shifted by the perf register number.

Change __parse_regs to use this method for finding registers rather than
arch__sample_reg_masks, thereby adding __parse_regs support for ARM(32),
csky, loongarch, MIPS, RISC-V and s390.

As arch__sample_reg_masks is then unused, remove the now unneeded
declarations.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Haibo Xu <haibo1.xu@intel.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Krzysztof Łopatowski <krzysztof.m.lopatowski@gmail.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf annotate: Fix memcpy size in arch__grow_instructions()

The memcpy() in arch__grow_instructions() is copying the wrong number of
bytes when growing from a non-allocated table.

It should copy arch->nr_instructions * sizeof(struct ins) bytes, not
just arch->nr_instructions bytes.

This bug causes data corruption as only a partial copy of the
instruction table is made, leading to garbage data in most entries and
potential crashes

Fixes: 2a1ff812c40be982 ("perf annotate: Introduce alternative method of keeping instructions table")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Suchit Karunakaran <suchitkarunakaran@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf tests sched: Avoid error in cleanup on loaded machines

The stop_noploops function will kill the noploop processes that are
running for 10 seconds.

On a loaded machine they may have already terminated meaning the kill
will return an error of no such process.

This doesn't matter and so ignore the error to avoid the test
terminating in the cleanup.

Fixes: 0e22c5ca44e68798 ("perf test: Add sched latency and script shell tests")
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf inject: With --convert-callchain ignore the dummy event for dwarf stacks

On hybrid systems there is generally >1 event and a dummy event.

The perf inject --convert-callchain option is failing to convert
perf.data files on such systems reporting "--convert-callchain requires
DWARF call graph."

The failing event is the dummy event that doesn't need to be set up for
samples.

As such ignore this event when checking the evsels.

Fixes: 92ea788d2af4e65a ("perf inject: Add --convert-callchain option")
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf disasm: Minor layout tweaks for 'struct arch'

Pack some holes to bring down the overall struct size from 96 to 88
bytes.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Julia Lawall <Julia.Lawall@inria.fr>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Krzysztof Łopatowski <krzysztof.m.lopatowski@gmail.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Suchit Karunakaran <suchitkarunakaran@gmail.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tianyou Li <tianyou.li@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zecheng Li <zecheng@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf disasm: Refactor arch__find and initialization of arch structs

Switch arch__find to using an ELF machine number rather than a
string.

Rather than an array of fixed size arch structs turn the init functions
into new functions indexed by the ELF machine they correspond to.

This allows data to be stored with a struct arch with the container_of
trick, so the priv variable can be removed.

Switch to using the thread to find the arch rather than the evsel as the
evsel only has limited notions of the running thread upon which
disassembly is performed.

Factor out the e_machine and e_flags into their own struct to make them
easier to pass around.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Julia Lawall <Julia.Lawall@inria.fr>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Krzysztof Łopatowski <krzysztof.m.lopatowski@gmail.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Suchit Karunakaran <suchitkarunakaran@gmail.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tianyou Li <tianyou.li@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zecheng Li <zecheng@google.com>
[ Include elf.h for EM_CSKY and friends and also conditionally define EM_CSKY_ABIMASK for old distros ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf map_symbol: Switch from holding maps to holding thread

maps may belong to >1 thread. In contexts like symbolization
information from the thread may be useful, such as the ELF machine.

As the maps can be gained from the thread switch from holding maps in
struct map_symbol to holding the thread.

Holding the maps in addr_location is also redundant, switch this to
using thread__maps.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Julia Lawall <Julia.Lawall@inria.fr>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Krzysztof Łopatowski <krzysztof.m.lopatowski@gmail.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Suchit Karunakaran <suchitkarunakaran@gmail.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tianyou Li <tianyou.li@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zecheng Li <zecheng@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

perf disasm: Refactor ins__is_call/jump to avoid exposing arch ins_ops

Add booleans indicating whether and ins_ops are call or jump and
return it. This avoids exposing loongarch and s390 ins_ops for the
sake of matching.

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Julia Lawall <Julia.Lawall@inria.fr>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Krzysztof Łopatowski <krzysztof.m.lopatowski@gmail.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Suchit Karunakaran <suchitkarunakaran@gmail.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Tianyou Li <tianyou.li@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zecheng Li <zecheng@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>