6 files changed, 72 insertions, 5 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 5ad07ef417f0..e9cd39a92dc2 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -93,6 +93,9 @@ OPTIONS
 --skip-missing::
         Skip symbols that cannot be annotated.
 
+--group::
+        Show event group information together
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
new file mode 100644
index 000000000000..888d51137fbe
--- /dev/null
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -0,0 +1,48 @@
+perf-mem(1)
+===========
+
+NAME
+----
+perf-mem - Profile memory accesses
+
+SYNOPSIS
+--------
+[verse]
+'perf mem' [<options>] (record [<command>] | report)
+
+DESCRIPTION
+-----------
+"perf mem -t <TYPE> record" runs a command and gathers memory operation data
+from it, into perf.data. Perf record options are accepted and are passed through.
+
+"perf mem -t <TYPE> report" displays the result. It invokes perf report with the
+right set of options to display a memory access profile.
+
+OPTIONS
+-------
+<command>...::
+        Any command you can specify in a shell.
+
+-t::
+--type=::
+        Select the memory operation type: load or store (default: load)
+
+-D::
+--dump-raw-samples=::
+        Dump the raw decoded samples on the screen in a format that is easy to parse with
+        one sample per line.
+
+-x::
+--field-separator::
+        Specify the field separator used when dump raw samples (-D option). By default,
+        The separator is the space character.
+
+-C::
+--cpu-list::
+        Restrict dump of raw samples to those provided via this option. Note that the same
+        option can be passed in record mode. It will be interpreted the same way as perf
+        record.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 938e8904f64d..d4da111ef53d 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -182,6 +182,12 @@ is enabled for all the sampling events. The sampled branch type is the same for
 The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
 Note that this feature may not be available on all processors.
 
+-W::
+--weight::
+Enable weightened sampling. An additional weight is recorded per sample and can be
+displayed with the weight and local_weight sort keys.  This currently works for TSX
+abort events and some memory events in precise mode on modern Intel CPUs.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 02284a0067f0..7d5f4f38aa52 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -59,7 +59,7 @@ OPTIONS
 --sort=::
         Sort histogram entries by given key(s) - multiple keys can be specified
         in CSV format.  Following sort keys are available:
-        pid, comm, dso, symbol, parent, cpu, srcline.
+        pid, comm, dso, symbol, parent, cpu, srcline, weight, local_weight.
 
         Each key has following meaning:
 
@@ -206,6 +206,10 @@ OPTIONS
 --group::
         Show event group information together.
 
+--demangle::
+        Demangle symbol names to human readable form. It's enabled by default,
+        disable with --no-demangle.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index faf4f4feebcc..2fe87fb558f0 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -52,7 +52,7 @@ OPTIONS
 
 -r::
 --repeat=<n>::
-        repeat command and print average + stddev (max: 100)
+        repeat command and print average + stddev (max: 100). 0 means forever.
 
 -B::
 --big-num::
@@ -119,13 +119,19 @@ perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- m
         Print count deltas every N milliseconds (minimum: 100ms)
         example: perf stat -I 1000 -e cycles -a sleep 5
 
---aggr-socket::
+--per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
 is a useful mode to detect imbalance between sockets.  To enable this mode,
-use --aggr-socket in addition to -a. (system-wide).  The output includes the
+use --per-socket in addition to -a. (system-wide).  The output includes the
 socket number and the number of online processors on that socket. This is
 useful to gauge the amount of aggregation.
 
+--per-core::
+Aggregate counts per physical processor for system-wide mode measurements.  This
+is a useful mode to detect imbalance between physical cores.  To enable this mode,
+use --per-core in addition to -a. (system-wide).  The output includes the
+core number and the number of online logical processors on that physical processor.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index a414bc95fd52..9f1a2fe54757 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -112,7 +112,7 @@ Default is to monitor all CPUS.
 
 -s::
 --sort::
-        Sort by key(s): pid, comm, dso, symbol, parent, srcline.
+        Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, local_weight.
 
 -n::
 --show-nr-samples::