Skip to contentSkip to conversation

perf/docs: Add info on AMD raw event encoding

PATCH Superseded Sandipan Das 2 participants 3 messages Nov 23, 2021 perf events

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/2 perf/docs: Add info on AMD raw event encoding

AMD processors have events with event select codes and unit masks larger than a byte. The core PMU, for example, uses 12-bit event select codes split between bits 0-7 and 32-35 of the PERF_CTL MSRs as can be seen from /sys/bus/event_sources/devices/cpu/format/*.

The Processor Programming Reference (PPR) lists the event codes as unified 12-bit hexadecimal values instead and the split between the bits is not apparent to someone who is not aware of the layout of the PERF_CTL MSRs.

8-bit event select codes continue to work as the layout matches that of the PERF_CTL MSRs i.e. bits 0-7 for event select and 8-15 for unit mask.

This adds more details in the perf man pages about using /sys/bus/event_sources/devices/*/format/* for determining the correct raw event encoding scheme.

E.g. the "op_cache_hit_miss.op_cache_hit" event with code 0x28f and umask 0x03 can be programmed using its symbolic name as:

  $ sudo perf --debug perf-event-open stat -e op_cache_hit_miss.op_cache_hit sleep 1
  ------------------------------------------------------------
  perf_event_attr:
    type                             4
    size                             128
    config                           0x20000038f
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  [...]

In raw format, it may be programmed incorrectly as:

  $ sudo perf --debug perf-event-open stat -e r0328f sleep 1
  ------------------------------------------------------------
  perf_event_attr:
    type                             4
    size                             128
    config                           0x328f
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  [...]

When it should have been based on the format from sysfs:

  $ cat /sys/bus/event_source/devices/cpu/format/event
  config:0-7,32-35
  $ sudo perf --debug perf-event-open stat -e r20000038f sleep 1
  ------------------------------------------------------------
  perf_event_attr:
    type                             4
    size                             128
    config                           0x20000038f
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  [...]

---
v1: https://lore.kernel.org/linux-perf-users/[email protected]/

v2:
- Use the "op_cache_hit_miss.op_cache_hit" event as an example since the event select and unit mask nibbles are all different.

- Refer to sysfs files for cpu pmu when describing the "rN" notation.

---
 tools/perf/Documentation/perf-list.txt   | 34 +++++++++++++++++++++++-
 tools/perf/Documentation/perf-record.txt |  6 +++--
 tools/perf/Documentation/perf-stat.txt   |  6 +++--
 tools/perf/Documentation/perf-top.txt    |  7 ++---
 4 files changed, 45 insertions(+), 8 deletions(-)
tools/perf/Documentation/perf-list.txt +33 -1
index 4dc8d0af19df..a922a95289a9 100644
@@ -94,7 +94,7 @@ RAW HARDWARE EVENT DESCRIPTOR
 Even when an event is not available in a symbolic form within perf right now,
 it can be encoded in a per processor specific way.
 
-For instance For x86 CPUs NNN represents the raw register encoding with the
+For instance on x86 CPUs, N is a hexadecimal value that represents the raw register encoding with the
 layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
 of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
 Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
@@ -126,6 +126,38 @@ It's also possible to use pmu syntax:
  perf record -e cpu/r1a8/ ...
  perf record -e cpu/r0x1a8/ ...
 
+Some processors, like those from AMD, support event codes and unit masks
+larger than a byte. In such cases, the bits corresponding to the event
+configuration parameters can be seen with:
+
+  cat /sys/bus/event_source/devices/<pmu>/format/<config>
+
+Example:
+
+If the AMD docs for an EPYC 7713 processor describe an event as:
+
+  Event  Umask  Event Mask
+  Num.   Value  Mnemonic                        Description
+
+  28FH     03H  op_cache_hit_miss.op_cache_hit  Counts Op Cache micro-tag
+                                                hit events.
+
+raw encoding of 0x0328F cannot be used since the upper nibble of the
+EventSelect bits have to be specified via bits 32-35 as can be seen with:
+
+  cat /sys/bus/event_source/devices/cpu/format/event
+
+raw encoding of 0x20000038F should be used instead:
+
+ perf stat -e r20000038f -a sleep 1
+ perf record -e r20000038f ...
+
+It's also possible to use pmu syntax:
+
+ perf record -e r20000038f -a sleep 1
+ perf record -e cpu/r20000038f/ ...
+ perf record -e cpu/r0x20000038f/ ...
+
 You should refer to the processor specific documentation for getting these
 details. Some of them are referenced in the SEE ALSO section below.
 
tools/perf/Documentation/perf-record.txt +4 -2
index 3cf7bac67239..55df7b073a55 100644
@@ -30,8 +30,10 @@ OPTIONS
 
         - a symbolic event name	(use 'perf list' to list all events)
 
-        - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
-	  hexadecimal event descriptor.
+        - a raw PMU event in the form of rN where N is a hexadecimal value
+          that represents the raw register encoding with the layout of the
+          event control registers as described by entries in
+          /sys/bus/event_sources/devices/cpu/format/*.
 
         - a symbolic or raw PMU event followed by an optional colon
 	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
tools/perf/Documentation/perf-stat.txt +4 -2
index 7e6fb7cbc0f4..604e6f2301ea 100644
@@ -36,8 +36,10 @@ report::
 
 	- a symbolic event name (use 'perf list' to list all events)
 
-	- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
-	  hexadecimal event descriptor.
+	- a raw PMU event in the form of rN where N is a hexadecimal value
+	  that represents the raw register encoding with the layout of the
+	  event control registers as described by entries in
+	  /sys/bus/event_sources/devices/cpu/format/*.
 
         - a symbolic or raw PMU event followed by an optional colon
 	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
tools/perf/Documentation/perf-top.txt +4 -3
index 9898a32b8d9c..cac3dfbee7d8 100644
@@ -38,9 +38,10 @@ Default is to monitor all CPUS.
 -e <event>::
 --event=<event>::
 	Select the PMU event. Selection can be a symbolic event name
-	(use 'perf list' to list all events) or a raw PMU
-	event (eventsel+umask) in the form of rNNN where NNN is a
-	hexadecimal event descriptor.
+	(use 'perf list' to list all events) or a raw PMU event in the form
+	of rN where N is a hexadecimal value that represents the raw register
+	encoding with the layout of the event control registers as described
+	by entries in /sys/bus/event_sources/devices/cpu/format/*.
 
 -E <entries>::
 --entries=<entries>::
Signature · 1 line
2.30.2
#1 lore raw

PATCH v2 2/2 perf/docs: Update link to AMD documentation

This updates the link to documentation on AMD processors. The new link points to a page where users can find the Processor Programming Reference (PPR) documents for the family and model codes corresponding to processors they are using.

---
v1: https://lore.kernel.org/linux-perf-users/[email protected]/

v2:
- Use family, model and stepping when referring to processors.
- Use the kernel bugzilla link for access to PPRs.

---
 tools/perf/Documentation/perf-list.txt | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)
tools/perf/Documentation/perf-list.txt +10 -4
index a922a95289a9..57384a97c04f 100644
@@ -81,7 +81,11 @@ On AMD systems it is implemented using IBS (up to precise-level 2).
 The precise modifier works with event types 0x76 (cpu-cycles, CPU
 clocks not halted) and 0xC1 (micro-ops retired). Both events map to
 IBS execution sampling (IBS op) with the IBS Op Counter Control bit
-(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
+(IbsOpCntCtl) set respectively (see the
+Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS)
+section of the [AMD Processor Programming Reference (PPR)] relevant to the
+family, model and stepping of the processor being used).
+
 Manual Volume 2: System Programming, 13.3 Instruction-Based
 Sampling). Examples to use IBS:
 
@@ -96,8 +100,10 @@ it can be encoded in a per processor specific way.
 
 For instance on x86 CPUs, N is a hexadecimal value that represents the raw register encoding with the
 layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
-of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
-Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
+of IA32_PERFEVTSELx MSRs) or AMD's PERF_CTL MSRs (see the
+Core Complex (CCX) -> Processor x86 Core -> MSR Registers section of the
+[AMD Processor Programming Reference (PPR)] relevant to the family, model
+and stepping of the processor being used).
 
 Note: Only the following bit fields can be set in x86 counter
 registers: event, umask, edge, inv, cmask. Esp. guest/host only and
@@ -348,4 +354,4 @@ SEE ALSO
 linkperf:perf-stat[1], linkperf:perf-top[1],
 linkperf:perf-record[1],
 http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
-http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
+https://bugzilla.kernel.org/show_bug.cgi?id=206537[AMD Processor Programming Reference (PPR)]
Signature · 1 line
2.30.2
#2 lore raw
In reply to Sandipan Das
Quoted 38 lines · Sandipan Das

AMD processors have events with event select codes and unit masks larger than a byte. The core PMU, for example, uses 12-bit event select codes split between bits 0-7 and 32-35 of the PERF_CTL MSRs as can be seen from /sys/bus/event_sources/devices/cpu/format/*.

The Processor Programming Reference (PPR) lists the event codes as unified 12-bit hexadecimal values instead and the split between the bits is not apparent to someone who is not aware of the layout of the PERF_CTL MSRs.

8-bit event select codes continue to work as the layout matches that of the PERF_CTL MSRs i.e. bits 0-7 for event select and 8-15 for unit mask.

This adds more details in the perf man pages about using /sys/bus/event_sources/devices/*/format/* for determining the correct raw event encoding scheme.

E.g. the "op_cache_hit_miss.op_cache_hit" event with code 0x28f and umask 0x03 can be programmed using its symbolic name as:

  $ sudo perf --debug perf-event-open stat -e op_cache_hit_miss.op_cache_hit sleep 1
  ------------------------------------------------------------
  perf_event_attr:
    type                             4
    size                             128
    config                           0x20000038f
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  [...]
Quoted 1 line

In raw format, it may be programmed incorrectly as:

Hi Sandipan,
Can you specify more clearly on why it can be programmed incorrectly?
From my understanding, you mentioned it based on the current documentation we had for raw event encoding:

- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor

Incase you want to specify this negative case, can you also point why it might happen so that it will be clear and it also explains need of change in raw event description.

Thanks,
Kajol Jain

Quoted 160 lines
  $ sudo perf --debug perf-event-open stat -e r0328f sleep 1
  ------------------------------------------------------------
  perf_event_attr:
    type                             4
    size                             128
    config                           0x328f
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  [...]

When it should have been based on the format from sysfs:

  $ cat /sys/bus/event_source/devices/cpu/format/event
  config:0-7,32-35
  $ sudo perf --debug perf-event-open stat -e r20000038f sleep 1
  ------------------------------------------------------------
  perf_event_attr:
    type                             4
    size                             128
    config                           0x20000038f
    sample_type                      IDENTIFIER
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ------------------------------------------------------------
  [...]

---
v1: https://lore.kernel.org/linux-perf-users/[email protected]/

v2:
- Use the "op_cache_hit_miss.op_cache_hit" event as an example since the event select and unit mask nibbles are all different.

- Refer to sysfs files for cpu pmu when describing the "rN" notation.

---
 tools/perf/Documentation/perf-list.txt   | 34 +++++++++++++++++++++++-
 tools/perf/Documentation/perf-record.txt |  6 +++--
 tools/perf/Documentation/perf-stat.txt   |  6 +++--
 tools/perf/Documentation/perf-top.txt    |  7 ++---
 4 files changed, 45 insertions(+), 8 deletions(-)
tools/perf/Documentation/perf-list.txt +33 -1
index 4dc8d0af19df..a922a95289a9 100644
@@ -94,7 +94,7 @@ RAW HARDWARE EVENT DESCRIPTOR
 Even when an event is not available in a symbolic form within perf right now,
 it can be encoded in a per processor specific way.
 
-For instance For x86 CPUs NNN represents the raw register encoding with the
+For instance on x86 CPUs, N is a hexadecimal value that represents the raw register encoding with the
 layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
 of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
 Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
@@ -126,6 +126,38 @@ It's also possible to use pmu syntax:
  perf record -e cpu/r1a8/ ...
  perf record -e cpu/r0x1a8/ ...
 
+Some processors, like those from AMD, support event codes and unit masks
+larger than a byte. In such cases, the bits corresponding to the event
+configuration parameters can be seen with:
+
+  cat /sys/bus/event_source/devices/<pmu>/format/<config>
+
+Example:
+
+If the AMD docs for an EPYC 7713 processor describe an event as:
+
+  Event  Umask  Event Mask
+  Num.   Value  Mnemonic                        Description
+
+  28FH     03H  op_cache_hit_miss.op_cache_hit  Counts Op Cache micro-tag
+                                                hit events.
+
+raw encoding of 0x0328F cannot be used since the upper nibble of the
+EventSelect bits have to be specified via bits 32-35 as can be seen with:
+
+  cat /sys/bus/event_source/devices/cpu/format/event
+
+raw encoding of 0x20000038F should be used instead:
+
+ perf stat -e r20000038f -a sleep 1
+ perf record -e r20000038f ...
+
+It's also possible to use pmu syntax:
+
+ perf record -e r20000038f -a sleep 1
+ perf record -e cpu/r20000038f/ ...
+ perf record -e cpu/r0x20000038f/ ...
+
 You should refer to the processor specific documentation for getting these
 details. Some of them are referenced in the SEE ALSO section below.
 
tools/perf/Documentation/perf-record.txt +4 -2
index 3cf7bac67239..55df7b073a55 100644
@@ -30,8 +30,10 @@ OPTIONS
 
         - a symbolic event name	(use 'perf list' to list all events)
 
-        - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
-	  hexadecimal event descriptor.
+        - a raw PMU event in the form of rN where N is a hexadecimal value
+          that represents the raw register encoding with the layout of the
+          event control registers as described by entries in
+          /sys/bus/event_sources/devices/cpu/format/*.
 
         - a symbolic or raw PMU event followed by an optional colon
 	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
tools/perf/Documentation/perf-stat.txt +4 -2
index 7e6fb7cbc0f4..604e6f2301ea 100644
@@ -36,8 +36,10 @@ report::
 
 	- a symbolic event name (use 'perf list' to list all events)
 
-	- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
-	  hexadecimal event descriptor.
+	- a raw PMU event in the form of rN where N is a hexadecimal value
+	  that represents the raw register encoding with the layout of the
+	  event control registers as described by entries in
+	  /sys/bus/event_sources/devices/cpu/format/*.
 
         - a symbolic or raw PMU event followed by an optional colon
 	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
tools/perf/Documentation/perf-top.txt +4 -3
index 9898a32b8d9c..cac3dfbee7d8 100644
@@ -38,9 +38,10 @@ Default is to monitor all CPUS.
 -e <event>::
 --event=<event>::
 	Select the PMU event. Selection can be a symbolic event name
-	(use 'perf list' to list all events) or a raw PMU
-	event (eventsel+umask) in the form of rNNN where NNN is a
-	hexadecimal event descriptor.
+	(use 'perf list' to list all events) or a raw PMU event in the form
+	of rN where N is a hexadecimal value that represents the raw register
+	encoding with the layout of the event control registers as described
+	by entries in /sys/bus/event_sources/devices/cpu/format/*.
 
 -E <entries>::
 --entries=<entries>::