* [PATCH v5 05/58] perf script: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-24 16:46 UTC (permalink / raw)
To: acme, adrian.hunter, james.clark, leo.yan, namhyung, tmricht
Cc: alice.mei.rogers, dapeng1.mi, linux-arm-kernel, linux-kernel,
linux-perf-users, mingo, peterz, Ian Rogers
In-Reply-To: <20260424164721.2229025-1-irogers@google.com>
Fix missing #include of pmu.h found while cleaning the evsel/evlist
header files. Sort the remaining header files for consistency with the
rest of the code. Doing this exposed a missing forward declaration of
addr_location in print_insn.h, add this and sort the forward
declarations.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/builtin-script.c | 111 ++++++++++++++++++-----------------
tools/perf/util/print_insn.h | 5 +-
2 files changed, 60 insertions(+), 56 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c8ac9f01a36b..853b141a0d50 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1,74 +1,77 @@
// SPDX-License-Identifier: GPL-2.0
-#include "builtin.h"
+#include <errno.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <stdio.h>
+
+#include <dirent.h>
+#include <fcntl.h>
+#include <linux/bitmap.h>
+#include <linux/compiler.h>
+#include <linux/ctype.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/stringify.h>
+#include <linux/time64.h>
+#include <linux/unaligned.h>
+#include <linux/zalloc.h>
+#include <sys/param.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <unistd.h>
+#include <perf/evlist.h>
+#include <subcmd/exec-cmd.h>
+#include <subcmd/pager.h>
+#include <subcmd/parse-options.h>
+
+#include "asm/bug.h"
+#include "builtin.h"
+#include "perf.h"
+#include "print_binary.h"
+#include "print_insn.h"
+#include "ui/ui.h"
+#include "util/annotate.h"
+#include "util/auxtrace.h"
+#include "util/cgroup.h"
+#include "util/color.h"
#include "util/counts.h"
+#include "util/cpumap.h"
+#include "util/data.h"
#include "util/debug.h"
+#include "util/dlfilter.h"
#include "util/dso.h"
-#include <subcmd/exec-cmd.h>
-#include "util/header.h"
-#include <subcmd/parse-options.h>
-#include "util/perf_regs.h"
-#include "util/session.h"
-#include "util/tool.h"
-#include "util/map.h"
-#include "util/srcline.h"
-#include "util/symbol.h"
-#include "util/thread.h"
-#include "util/trace-event.h"
+#include "util/dump-insn.h"
#include "util/env.h"
+#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/evsel_fprintf.h"
#include "util/evswitch.h"
+#include "util/header.h"
+#include "util/map.h"
+#include "util/mem-events.h"
+#include "util/mem-info.h"
+#include "util/metricgroup.h"
+#include "util/path.h"
+#include "util/perf_regs.h"
+#include "util/pmu.h"
+#include "util/record.h"
+#include "util/session.h"
#include "util/sort.h"
-#include "util/data.h"
-#include "util/auxtrace.h"
-#include "util/cpumap.h"
-#include "util/thread_map.h"
+#include "util/srcline.h"
#include "util/stat.h"
-#include "util/color.h"
#include "util/string2.h"
+#include "util/symbol.h"
#include "util/thread-stack.h"
+#include "util/thread.h"
+#include "util/thread_map.h"
#include "util/time-utils.h"
-#include "util/path.h"
-#include "util/event.h"
-#include "util/mem-info.h"
-#include "util/metricgroup.h"
-#include "ui/ui.h"
-#include "print_binary.h"
-#include "print_insn.h"
-#include <linux/bitmap.h>
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/stringify.h>
-#include <linux/time64.h>
-#include <linux/zalloc.h>
-#include <linux/unaligned.h>
-#include <sys/utsname.h>
-#include "asm/bug.h"
-#include "util/mem-events.h"
-#include "util/dump-insn.h"
-#include <dirent.h>
-#include <errno.h>
-#include <inttypes.h>
-#include <signal.h>
-#include <stdio.h>
-#include <sys/param.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <subcmd/pager.h>
-#include <perf/evlist.h>
-#include <linux/err.h>
-#include "util/dlfilter.h"
-#include "util/record.h"
+#include "util/tool.h"
+#include "util/trace-event.h"
#include "util/util.h"
-#include "util/cgroup.h"
-#include "util/annotate.h"
-#include "perf.h"
-#include <linux/ctype.h>
#ifdef HAVE_LIBTRACEEVENT
#include <event-parse.h>
#endif
diff --git a/tools/perf/util/print_insn.h b/tools/perf/util/print_insn.h
index 07d11af3fc1c..a54f7e858e49 100644
--- a/tools/perf/util/print_insn.h
+++ b/tools/perf/util/print_insn.h
@@ -5,10 +5,11 @@
#include <stddef.h>
#include <stdio.h>
-struct perf_sample;
-struct thread;
+struct addr_location;
struct machine;
struct perf_insn;
+struct perf_sample;
+struct thread;
#define PRINT_INSN_IMM_HEX (1<<0)
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v5 04/58] perf tests: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-24 16:46 UTC (permalink / raw)
To: acme, adrian.hunter, james.clark, leo.yan, namhyung, tmricht
Cc: alice.mei.rogers, dapeng1.mi, linux-arm-kernel, linux-kernel,
linux-perf-users, mingo, peterz, Ian Rogers
In-Reply-To: <20260424164721.2229025-1-irogers@google.com>
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/tests/hwmon_pmu.c | 14 +++++++++-----
tools/perf/tests/mmap-basic.c | 18 +++++++++++-------
2 files changed, 20 insertions(+), 12 deletions(-)
diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index 4aa4aac94f09..ada6e445c4c4 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -1,15 +1,19 @@
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-#include "debug.h"
-#include "evlist.h"
#include "hwmon_pmu.h"
-#include "parse-events.h"
-#include "tests.h"
+
#include <errno.h>
+
#include <fcntl.h>
-#include <sys/stat.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/string.h>
+#include <sys/stat.h>
+
+#include "debug.h"
+#include "evlist.h"
+#include "parse-events.h"
+#include "pmus.h"
+#include "tests.h"
static const struct test_event {
const char *name;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 3313c236104e..8d04f6edb004 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -1,25 +1,29 @@
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
-#include <fcntl.h>
#include <inttypes.h>
#include <stdlib.h>
+
+#include <fcntl.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
#include <perf/cpumap.h>
+#include <perf/evlist.h>
+#include <perf/mmap.h>
#include "cpumap.h"
#include "debug.h"
#include "event.h"
#include "evlist.h"
#include "evsel.h"
-#include "thread_map.h"
+#include "pmu.h"
+#include "pmus.h"
#include "tests.h"
+#include "thread_map.h"
#include "util/affinity.h"
#include "util/mmap.h"
#include "util/sample.h"
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <perf/evlist.h>
-#include <perf/mmap.h>
/*
* This test will generate random numbers of calls to some getpid syscalls,
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v5 03/58] perf arch x86: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-24 16:46 UTC (permalink / raw)
To: acme, adrian.hunter, james.clark, leo.yan, namhyung, tmricht
Cc: alice.mei.rogers, dapeng1.mi, linux-arm-kernel, linux-kernel,
linux-perf-users, mingo, peterz, Ian Rogers
In-Reply-To: <20260424164721.2229025-1-irogers@google.com>
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/arch/x86/util/intel-bts.c | 20 +++++++++++--------
tools/perf/arch/x86/util/intel-pt.c | 29 +++++++++++++++-------------
2 files changed, 28 insertions(+), 21 deletions(-)
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 85c8186300c8..100a23d27998 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -4,26 +4,30 @@
* Copyright (c) 2013-2015, Intel Corporation.
*/
+#include "../../../util/intel-bts.h"
+
#include <errno.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
+
#include <linux/bitops.h>
+#include <linux/kernel.h>
#include <linux/log2.h>
+#include <linux/types.h>
#include <linux/zalloc.h>
+#include <internal/lib.h> // page_size
+
+#include "../../../util/auxtrace.h"
#include "../../../util/cpumap.h"
+#include "../../../util/debug.h"
#include "../../../util/event.h"
-#include "../../../util/evsel.h"
#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
#include "../../../util/mmap.h"
-#include "../../../util/session.h"
+#include "../../../util/pmu.h"
#include "../../../util/pmus.h"
-#include "../../../util/debug.h"
#include "../../../util/record.h"
+#include "../../../util/session.h"
#include "../../../util/tsc.h"
-#include "../../../util/auxtrace.h"
-#include "../../../util/intel-bts.h"
-#include <internal/lib.h> // page_size
#define KiB(x) ((x) * 1024)
#define MiB(x) ((x) * 1024 * 1024)
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index c131a727774f..0307ff15d9fc 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -3,36 +3,39 @@
* intel_pt.c: Intel Processor Trace support
* Copyright (c) 2013-2015, Intel Corporation.
*/
+#include "../../../util/intel-pt.h"
#include <errno.h>
#include <stdbool.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
+
#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
#include <linux/log2.h>
+#include <linux/types.h>
#include <linux/zalloc.h>
-#include <linux/err.h>
-#include "../../../util/session.h"
+#include <api/fs/fs.h>
+#include <internal/lib.h> // page_size
+#include <subcmd/parse-options.h>
+
+#include "../../../util/auxtrace.h"
+#include "../../../util/config.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/debug.h"
#include "../../../util/event.h"
#include "../../../util/evlist.h"
#include "../../../util/evsel.h"
#include "../../../util/evsel_config.h"
-#include "../../../util/config.h"
-#include "../../../util/cpumap.h"
#include "../../../util/mmap.h"
-#include <subcmd/parse-options.h>
#include "../../../util/parse-events.h"
-#include "../../../util/pmus.h"
-#include "../../../util/debug.h"
-#include "../../../util/auxtrace.h"
#include "../../../util/perf_api_probe.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
#include "../../../util/record.h"
+#include "../../../util/session.h"
#include "../../../util/target.h"
#include "../../../util/tsc.h"
-#include <internal/lib.h> // page_size
-#include "../../../util/intel-pt.h"
-#include <api/fs/fs.h>
#include "cpuid.h"
#define KiB(x) ((x) * 1024)
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v5 02/58] perf arch arm: Sort includes and add missed explicit dependencies
From: Ian Rogers @ 2026-04-24 16:46 UTC (permalink / raw)
To: acme, adrian.hunter, james.clark, leo.yan, namhyung, tmricht
Cc: alice.mei.rogers, dapeng1.mi, linux-arm-kernel, linux-kernel,
linux-perf-users, mingo, peterz, Ian Rogers
In-Reply-To: <20260424164721.2229025-1-irogers@google.com>
Fix missing #includes found while cleaning the evsel/evlist header
files. Sort the remaining header files for consistency with the rest
of the code.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/arch/arm/util/cs-etm.c | 26 ++++++++++++++------------
1 file changed, 14 insertions(+), 12 deletions(-)
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index b7a839de8707..cdf8e3e60606 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -3,10 +3,13 @@
* Copyright(C) 2015 Linaro Limited. All rights reserved.
* Author: Mathieu Poirier <mathieu.poirier@linaro.org>
*/
+#include "../../../util/cs-etm.h"
+
+#include <errno.h>
+#include <stdlib.h>
-#include <api/fs/fs.h>
-#include <linux/bits.h>
#include <linux/bitops.h>
+#include <linux/bits.h>
#include <linux/compiler.h>
#include <linux/coresight-pmu.h>
#include <linux/kernel.h>
@@ -14,25 +17,24 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/zalloc.h>
+#include <sys/stat.h>
+
+#include <api/fs/fs.h>
+#include <internal/lib.h> // page_size
-#include "cs-etm.h"
-#include "../../../util/debug.h"
-#include "../../../util/record.h"
#include "../../../util/auxtrace.h"
#include "../../../util/cpumap.h"
+#include "../../../util/debug.h"
#include "../../../util/event.h"
#include "../../../util/evlist.h"
#include "../../../util/evsel.h"
-#include "../../../util/perf_api_probe.h"
#include "../../../util/evsel_config.h"
+#include "../../../util/perf_api_probe.h"
+#include "../../../util/pmu.h"
#include "../../../util/pmus.h"
-#include "../../../util/cs-etm.h"
-#include <internal/lib.h> // page_size
+#include "../../../util/record.h"
#include "../../../util/session.h"
-
-#include <errno.h>
-#include <stdlib.h>
-#include <sys/stat.h>
+#include "cs-etm.h"
struct cs_etm_recording {
struct auxtrace_record itr;
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH v5 00/58] perf: Reorganize scripting support
From: Ian Rogers @ 2026-04-24 16:46 UTC (permalink / raw)
To: acme, adrian.hunter, james.clark, leo.yan, namhyung, tmricht
Cc: alice.mei.rogers, dapeng1.mi, linux-arm-kernel, linux-kernel,
linux-perf-users, mingo, peterz, Ian Rogers
In-Reply-To: <20260423163406.1779809-1-irogers@google.com>
The perf script command has long supported running Python and Perl scripts by
embedding libpython and libperl. This approach has several drawbacks:
- overhead by creating Python dictionaries for every event (whether used or
not),
- complex build dependencies on specific Python/Perl versions,
- complications with threading due to perf being the interpreter,
- no clear way to run standalone scripts like ilist.py.
This series takes a different approach with some initial implementation posted
as an RFC last October:
https://lore.kernel.org/linux-perf-users/20251029053413.355154-1-irogers@google.com/
with the motivation coming up on the mailing list earlier:
https://lore.kernel.org/lkml/CAP-5=fWDqE8SYfOLZkg_0=4Ayx6E7O+h7uUp4NDeCFkiN4b7-w@mail.gmail.com/
The changes remove the embedded libpython and libperl support from perf
entirely. Instead, they expand the existing perf Python module to provide full
access to perf data files and events, allowing scripts to be run as standalone
Python applications.
To demonstrate the benefits, we ported all existing Python and Perl scripts to
use the new Python session API. The performance improvement is dramatic. For
example, porting mem-phys-addr.py:
Before (using embedded libpython in perf script):
```
$ perf mem record a sleep 1
$ time perf script tools/perf/scripts/python/mem-phys-addr.py
Event: cpu_core/mem-loads-aux/
Memory type count percentage
--------------------------------------- ---------- ----------
0-fff : Reserved 3217 100.0
real 0m3.754s
user 0m0.023s
sys 0m0.018s
```
After (using standalone Python script with perf module):
```
$ PYTHONPATH=/tmp/perf/python time python3 tools/perf/python/mem-phys-addr.py
Event: evsel(cpu_core/mem-loads-aux/)
Memory type count percentage
--------------------------------------- ---------- ----------
0-fff : Reserved 3217 100.0
real 0m0.106s
user 0m0.021s
sys 0m0.020s
```
This is a roughly 35x speedup!
The change is large (11291 insertions, 15964 deletions, net 4673
deletions) due to porting all existing perl and python code to the new
API. Gemini was used to achieve this and to improve the code
quality. Removing support may be controversial, however, the first 52
patches are additive and merging those would allow us to focus on the
remaining 6 patches that finalize the new perf script behavior.
---
v5 Changes
----------
Resending due to partial send of v4 due to a quota limit.
---
v4 Changes
----------
1. Git Fixup Cleanups
- Squashed the lingering `fixup!` commit remaining from the previous session back
into `perf check-perf-trace: Port check-perf-trace to use python module`.
---
v3 Changes
----------
1. Memory Safety & Reference Counting Fixes
- Stored transient mmap event data inside the Python object's permanent
`pevent->event` and invoked `evsel__parse_sample()` to safely point
attributes into it, resolving Use-After-Free vulnerabilities.
- Nullified `sample->evsel` after calling `evsel__put()` in
`perf_sample__exit()` to protect against potential refcount double-put
crashes in error paths.
- Reordered operations inside `evlist__remove()` to invoke
`perf_evlist__remove()` before reference release.
- Patched an `evsel` reference leak inside `evlist__deliver_deferred_callchain()`.
2. Sashiko AI Review Cleanups
- Corrected the broken event name equality check in `gecko.py` to search
for a substring match within the parsed event string.
- Fixed a latent `AttributeError` crash in `task-analyzer.py` by properly
assigning the session instance.
- Safeguarded thread reporting in `check-perf-trace.py` by utilizing
`sample_tid` instead of `sample_pid`, and wrapping the session thread
resolution in a try-except block.
3. Omitted Minor Issues
- The minor review comments (such as permanent iterator exhaustion on
`brstack`, or dead-code in `failed-syscalls-by-pid.py`) have been omitted
because they do not affect correctness, lead to crashes, or require
significant architectural rework.
---
v2 Changes
----------
1. String Match and Event Name Accuracy
- Replaced loose substring event matching across the script suite with exact
matches or specific prefix constraints (syscalls:sys_exit_,
evsel(skb:kfree_skb), etc.).
- Added getattr() safety checks to prevent script failures caused by
unresolved attributes from older kernel traces.
2. OOM and Memory Protections
- Refactored netdev-times.py to compute and process network statistics
chronologically on-the-fly, eliminating an unbounded in-memory list
that caused Out-Of-Memory crashes on large files.
- Implemented threshold limits on intel-pt-events.py to cap memory allocation
during event interleaving.
- Optimized export-to-sqlite.py to periodically commit database transactions
(every 10,000 samples) to reduce temporary SQLite journal sizes.
3. Portability & Environment Independence
- Re-keyed internal tracking dictionaries in scripts like powerpc-hcalls.py to
use thread PIDs instead of CPUs, ensuring correctness when threads migrate.
- Switched net_dropmonitor.py from host-specific /proc/kallsyms parsing to
perf's built-in symbol resolution API.
- Added the --iomem parameter to mem-phys-addr.py to support offline analysis
of data collected on different architectures.
4. Standalone Scripting Improvements
- Patched builtin-script.c to ensure --input parameters are successfully passed
down to standalone execution pipelines via execvp().
- Guarded against string buffer overflows during .py extension path resolving.
5. Code Cleanups
- Removed stale perl subdirectories from being detected by the TUI script
browser.
- Ran the entire script suite through mypy and pylint to achieve strict static
type checking and resolve unreferenced variables.
Ian Rogers (58):
perf inject: Fix itrace branch stack synthesis
perf arch arm: Sort includes and add missed explicit dependencies
perf arch x86: Sort includes and add missed explicit dependencies
perf tests: Sort includes and add missed explicit dependencies
perf script: Sort includes and add missed explicit dependencies
perf util: Sort includes and add missed explicit dependencies
perf python: Add missed explicit dependencies
perf evsel/evlist: Avoid unnecessary #includes
perf data: Add open flag
perf evlist: Add reference count
perf evsel: Add reference count
perf evlist: Add reference count checking
perf python: Use evsel in sample in pyrf_event
perf python: Add wrapper for perf_data file abstraction
perf python: Add python session abstraction wrapping perf's session
perf python: Add syscall name/id to convert syscall number and name
perf python: Refactor and add accessors to sample event
perf python: Add callchain support
perf python: Add config file access
perf python: Extend API for stat events in python.c
perf python: Expose brstack in sample event
perf python: Add perf.pyi stubs file
perf python: Add LiveSession helper
perf python: Move exported-sql-viewer.py and parallel-perf.py to
tools/perf/python/
perf stat-cpi: Port stat-cpi to use python module
perf mem-phys-addr: Port mem-phys-addr to use python module
perf syscall-counts: Port syscall-counts to use python module
perf syscall-counts-by-pid: Port syscall-counts-by-pid to use python
module
perf futex-contention: Port futex-contention to use python module
perf flamegraph: Port flamegraph to use python module
perf gecko: Port gecko to use python module
perf arm-cs-trace-disasm: Port arm-cs-trace-disasm to use python
module
perf check-perf-trace: Port check-perf-trace to use python module
perf compaction-times: Port compaction-times to use python module
perf event_analyzing_sample: Port event_analyzing_sample to use python
module
perf export-to-sqlite: Port export-to-sqlite to use python module
perf export-to-postgresql: Port export-to-postgresql to use python
module
perf failed-syscalls-by-pid: Port failed-syscalls-by-pid to use python
module
perf intel-pt-events: Port intel-pt-events/libxed to use python module
perf net_dropmonitor: Port net_dropmonitor to use python module
perf netdev-times: Port netdev-times to use python module
perf powerpc-hcalls: Port powerpc-hcalls to use python module
perf sched-migration: Port sched-migration/SchedGui to use python
module
perf sctop: Port sctop to use python module
perf stackcollapse: Port stackcollapse to use python module
perf task-analyzer: Port task-analyzer to use python module
perf failed-syscalls: Port failed-syscalls to use python module
perf rw-by-file: Port rw-by-file to use python module
perf rw-by-pid: Port rw-by-pid to use python module
perf rwtop: Port rwtop to use python module
perf wakeup-latency: Port wakeup-latency to use python module
perf test: Migrate Intel PT virtual LBR test to use Python API
perf: Remove libperl support, legacy Perl scripts and tests
perf: Remove libpython support and legacy Python scripts
perf Makefile: Update Python script installation path
perf script: Refactor to support standalone scripts and remove legacy
features
perf Documentation: Update for standalone Python scripts and remove
obsolete data
perf python: Improve perf script -l descriptions
tools/build/Makefile.feature | 5 +-
tools/build/feature/Makefile | 23 +-
tools/build/feature/test-all.c | 6 +-
tools/build/feature/test-libperl.c | 10 -
tools/build/feature/test-libpython.c | 10 -
tools/build/feature/test-python-module.c | 12 +
tools/perf/Documentation/perf-check.txt | 2 -
tools/perf/Documentation/perf-script-perl.txt | 216 --
.../perf/Documentation/perf-script-python.txt | 702 +-----
tools/perf/Documentation/perf-script.txt | 70 +-
tools/perf/Makefile.config | 37 +-
tools/perf/Makefile.perf | 22 +-
tools/perf/arch/arm/util/cs-etm.c | 36 +-
tools/perf/arch/arm64/util/arm-spe.c | 8 +-
tools/perf/arch/arm64/util/hisi-ptt.c | 2 +-
tools/perf/arch/x86/tests/hybrid.c | 22 +-
tools/perf/arch/x86/tests/topdown.c | 2 +-
tools/perf/arch/x86/util/auxtrace.c | 2 +-
tools/perf/arch/x86/util/intel-bts.c | 26 +-
tools/perf/arch/x86/util/intel-pt.c | 38 +-
tools/perf/arch/x86/util/iostat.c | 8 +-
tools/perf/bench/evlist-open-close.c | 29 +-
tools/perf/bench/inject-buildid.c | 9 +-
tools/perf/builtin-annotate.c | 2 +-
tools/perf/builtin-check.c | 3 +-
tools/perf/builtin-ftrace.c | 14 +-
tools/perf/builtin-inject.c | 81 +-
tools/perf/builtin-kvm.c | 14 +-
tools/perf/builtin-kwork.c | 8 +-
tools/perf/builtin-lock.c | 2 +-
tools/perf/builtin-record.c | 95 +-
tools/perf/builtin-report.c | 6 +-
tools/perf/builtin-sched.c | 26 +-
tools/perf/builtin-script.c | 895 +++----
tools/perf/builtin-stat.c | 81 +-
tools/perf/builtin-top.c | 104 +-
tools/perf/builtin-trace.c | 60 +-
tools/perf/python/SchedGui.py | 219 ++
tools/perf/python/arm-cs-trace-disasm.py | 338 +++
tools/perf/python/check-perf-trace.py | 113 +
tools/perf/python/compaction-times.py | 326 +++
tools/perf/python/counting.py | 1 +
tools/perf/python/event_analyzing_sample.py | 296 +++
tools/perf/python/export-to-postgresql.py | 697 ++++++
tools/perf/python/export-to-sqlite.py | 380 +++
.../python/exported-sql-viewer.py | 6 +-
tools/perf/python/failed-syscalls-by-pid.py | 119 +
tools/perf/python/failed-syscalls.py | 78 +
tools/perf/python/flamegraph.py | 250 ++
tools/perf/python/futex-contention.py | 87 +
tools/perf/python/gecko.py | 380 +++
tools/perf/python/intel-pt-events.py | 435 ++++
tools/perf/python/libxed.py | 122 +
.../{scripts => }/python/mem-phys-addr.py | 66 +-
tools/perf/python/net_dropmonitor.py | 58 +
tools/perf/python/netdev-times.py | 472 ++++
.../{scripts => }/python/parallel-perf.py | 0
tools/perf/python/perf.pyi | 579 +++++
tools/perf/python/perf_live.py | 48 +
tools/perf/python/powerpc-hcalls.py | 211 ++
tools/perf/python/rw-by-file.py | 103 +
tools/perf/python/rw-by-pid.py | 158 ++
tools/perf/python/rwtop.py | 219 ++
tools/perf/python/sched-migration.py | 469 ++++
tools/perf/python/sctop.py | 174 ++
tools/perf/python/stackcollapse.py | 126 +
tools/perf/python/stat-cpi.py | 151 ++
tools/perf/python/syscall-counts-by-pid.py | 88 +
tools/perf/python/syscall-counts.py | 72 +
tools/perf/python/task-analyzer.py | 547 ++++
tools/perf/python/tracepoint.py | 1 +
tools/perf/python/twatch.py | 1 +
tools/perf/python/wakeup-latency.py | 88 +
tools/perf/scripts/Build | 4 -
tools/perf/scripts/perl/Perf-Trace-Util/Build | 9 -
.../scripts/perl/Perf-Trace-Util/Context.c | 122 -
.../scripts/perl/Perf-Trace-Util/Context.xs | 42 -
.../scripts/perl/Perf-Trace-Util/Makefile.PL | 18 -
.../perf/scripts/perl/Perf-Trace-Util/README | 59 -
.../Perf-Trace-Util/lib/Perf/Trace/Context.pm | 55 -
.../Perf-Trace-Util/lib/Perf/Trace/Core.pm | 192 --
.../Perf-Trace-Util/lib/Perf/Trace/Util.pm | 94 -
.../perf/scripts/perl/Perf-Trace-Util/typemap | 1 -
.../scripts/perl/bin/check-perf-trace-record | 2 -
.../scripts/perl/bin/failed-syscalls-record | 3 -
.../scripts/perl/bin/failed-syscalls-report | 10 -
tools/perf/scripts/perl/bin/rw-by-file-record | 3 -
tools/perf/scripts/perl/bin/rw-by-file-report | 10 -
tools/perf/scripts/perl/bin/rw-by-pid-record | 2 -
tools/perf/scripts/perl/bin/rw-by-pid-report | 3 -
tools/perf/scripts/perl/bin/rwtop-record | 2 -
tools/perf/scripts/perl/bin/rwtop-report | 20 -
.../scripts/perl/bin/wakeup-latency-record | 6 -
.../scripts/perl/bin/wakeup-latency-report | 3 -
tools/perf/scripts/perl/check-perf-trace.pl | 106 -
tools/perf/scripts/perl/failed-syscalls.pl | 47 -
tools/perf/scripts/perl/rw-by-file.pl | 106 -
tools/perf/scripts/perl/rw-by-pid.pl | 184 --
tools/perf/scripts/perl/rwtop.pl | 203 --
tools/perf/scripts/perl/wakeup-latency.pl | 107 -
.../perf/scripts/python/Perf-Trace-Util/Build | 4 -
.../scripts/python/Perf-Trace-Util/Context.c | 225 --
.../Perf-Trace-Util/lib/Perf/Trace/Core.py | 116 -
.../lib/Perf/Trace/EventClass.py | 97 -
.../lib/Perf/Trace/SchedGui.py | 184 --
.../Perf-Trace-Util/lib/Perf/Trace/Util.py | 92 -
.../scripts/python/arm-cs-trace-disasm.py | 355 ---
.../python/bin/compaction-times-record | 2 -
.../python/bin/compaction-times-report | 4 -
.../python/bin/event_analyzing_sample-record | 8 -
.../python/bin/event_analyzing_sample-report | 3 -
.../python/bin/export-to-postgresql-record | 8 -
.../python/bin/export-to-postgresql-report | 29 -
.../python/bin/export-to-sqlite-record | 8 -
.../python/bin/export-to-sqlite-report | 29 -
.../python/bin/failed-syscalls-by-pid-record | 3 -
.../python/bin/failed-syscalls-by-pid-report | 10 -
.../perf/scripts/python/bin/flamegraph-record | 2 -
.../perf/scripts/python/bin/flamegraph-report | 3 -
.../python/bin/futex-contention-record | 2 -
.../python/bin/futex-contention-report | 4 -
tools/perf/scripts/python/bin/gecko-record | 2 -
tools/perf/scripts/python/bin/gecko-report | 7 -
.../scripts/python/bin/intel-pt-events-record | 13 -
.../scripts/python/bin/intel-pt-events-report | 3 -
.../scripts/python/bin/mem-phys-addr-record | 19 -
.../scripts/python/bin/mem-phys-addr-report | 3 -
.../scripts/python/bin/net_dropmonitor-record | 2 -
.../scripts/python/bin/net_dropmonitor-report | 4 -
.../scripts/python/bin/netdev-times-record | 8 -
.../scripts/python/bin/netdev-times-report | 5 -
.../scripts/python/bin/powerpc-hcalls-record | 2 -
.../scripts/python/bin/powerpc-hcalls-report | 2 -
.../scripts/python/bin/sched-migration-record | 2 -
.../scripts/python/bin/sched-migration-report | 3 -
tools/perf/scripts/python/bin/sctop-record | 3 -
tools/perf/scripts/python/bin/sctop-report | 24 -
.../scripts/python/bin/stackcollapse-record | 8 -
.../scripts/python/bin/stackcollapse-report | 3 -
.../python/bin/syscall-counts-by-pid-record | 3 -
.../python/bin/syscall-counts-by-pid-report | 10 -
.../scripts/python/bin/syscall-counts-record | 3 -
.../scripts/python/bin/syscall-counts-report | 10 -
.../scripts/python/bin/task-analyzer-record | 2 -
.../scripts/python/bin/task-analyzer-report | 3 -
tools/perf/scripts/python/check-perf-trace.py | 84 -
tools/perf/scripts/python/compaction-times.py | 311 ---
.../scripts/python/event_analyzing_sample.py | 192 --
.../scripts/python/export-to-postgresql.py | 1114 ---------
tools/perf/scripts/python/export-to-sqlite.py | 799 ------
.../scripts/python/failed-syscalls-by-pid.py | 79 -
tools/perf/scripts/python/flamegraph.py | 267 --
tools/perf/scripts/python/futex-contention.py | 57 -
tools/perf/scripts/python/gecko.py | 395 ---
tools/perf/scripts/python/intel-pt-events.py | 494 ----
tools/perf/scripts/python/libxed.py | 107 -
tools/perf/scripts/python/net_dropmonitor.py | 78 -
tools/perf/scripts/python/netdev-times.py | 473 ----
tools/perf/scripts/python/powerpc-hcalls.py | 202 --
tools/perf/scripts/python/sched-migration.py | 462 ----
tools/perf/scripts/python/sctop.py | 89 -
tools/perf/scripts/python/stackcollapse.py | 127 -
tools/perf/scripts/python/stat-cpi.py | 79 -
.../scripts/python/syscall-counts-by-pid.py | 75 -
tools/perf/scripts/python/syscall-counts.py | 65 -
tools/perf/scripts/python/task-analyzer.py | 934 -------
tools/perf/tests/backward-ring-buffer.c | 26 +-
tools/perf/tests/code-reading.c | 14 +-
tools/perf/tests/dlfilter-test.c | 8 +-
tools/perf/tests/event-times.c | 6 +-
tools/perf/tests/event_update.c | 4 +-
tools/perf/tests/evsel-roundtrip-name.c | 8 +-
tools/perf/tests/evsel-tp-sched.c | 4 +-
tools/perf/tests/expand-cgroup.c | 12 +-
tools/perf/tests/hists_cumulate.c | 2 +-
tools/perf/tests/hists_filter.c | 2 +-
tools/perf/tests/hists_link.c | 2 +-
tools/perf/tests/hists_output.c | 2 +-
tools/perf/tests/hwmon_pmu.c | 21 +-
tools/perf/tests/keep-tracking.c | 10 +-
tools/perf/tests/make | 9 +-
tools/perf/tests/mmap-basic.c | 42 +-
tools/perf/tests/openat-syscall-all-cpus.c | 6 +-
tools/perf/tests/openat-syscall-tp-fields.c | 26 +-
tools/perf/tests/openat-syscall.c | 6 +-
tools/perf/tests/parse-events.c | 139 +-
tools/perf/tests/parse-metric.c | 8 +-
tools/perf/tests/parse-no-sample-id-all.c | 2 +-
tools/perf/tests/perf-record.c | 38 +-
tools/perf/tests/perf-time-to-tsc.c | 12 +-
tools/perf/tests/pfm.c | 12 +-
tools/perf/tests/pmu-events.c | 11 +-
tools/perf/tests/pmu.c | 4 +-
tools/perf/tests/sample-parsing.c | 39 +-
.../perf/tests/shell/lib/perf_brstack_max.py | 43 +
tools/perf/tests/shell/script.sh | 2 +-
tools/perf/tests/shell/script_perl.sh | 102 -
tools/perf/tests/shell/script_python.sh | 113 -
.../tests/shell/test_arm_coresight_disasm.sh | 12 +-
tools/perf/tests/shell/test_intel_pt.sh | 35 +-
tools/perf/tests/shell/test_task_analyzer.sh | 79 +-
tools/perf/tests/sw-clock.c | 20 +-
tools/perf/tests/switch-tracking.c | 10 +-
tools/perf/tests/task-exit.c | 20 +-
tools/perf/tests/time-utils-test.c | 14 +-
tools/perf/tests/tool_pmu.c | 7 +-
tools/perf/tests/topology.c | 4 +-
tools/perf/ui/browsers/annotate.c | 2 +-
tools/perf/ui/browsers/hists.c | 22 +-
tools/perf/ui/browsers/scripts.c | 7 +-
tools/perf/util/Build | 1 -
tools/perf/util/amd-sample-raw.c | 2 +-
tools/perf/util/annotate-data.c | 2 +-
tools/perf/util/annotate.c | 10 +-
tools/perf/util/arm-spe.c | 7 +-
tools/perf/util/auxtrace.c | 14 +-
tools/perf/util/block-info.c | 4 +-
tools/perf/util/bpf_counter.c | 2 +-
tools/perf/util/bpf_counter_cgroup.c | 10 +-
tools/perf/util/bpf_ftrace.c | 9 +-
tools/perf/util/bpf_lock_contention.c | 12 +-
tools/perf/util/bpf_off_cpu.c | 44 +-
tools/perf/util/bpf_trace_augment.c | 8 +-
tools/perf/util/cgroup.c | 26 +-
tools/perf/util/cs-etm.c | 6 +-
tools/perf/util/data-convert-bt.c | 2 +-
tools/perf/util/data.c | 26 +-
tools/perf/util/data.h | 4 +-
tools/perf/util/evlist.c | 487 ++--
tools/perf/util/evlist.h | 273 +-
tools/perf/util/evsel.c | 109 +-
tools/perf/util/evsel.h | 35 +-
tools/perf/util/expr.c | 2 +-
tools/perf/util/header.c | 51 +-
tools/perf/util/header.h | 2 +-
tools/perf/util/intel-bts.c | 3 +-
tools/perf/util/intel-pt.c | 13 +-
tools/perf/util/intel-tpebs.c | 7 +-
tools/perf/util/map.h | 9 +-
tools/perf/util/metricgroup.c | 12 +-
tools/perf/util/parse-events.c | 10 +-
tools/perf/util/parse-events.y | 2 +-
tools/perf/util/perf_api_probe.c | 20 +-
tools/perf/util/pfm.c | 4 +-
tools/perf/util/print-events.c | 2 +-
tools/perf/util/print_insn.h | 5 +-
tools/perf/util/python.c | 1854 ++++++++++++--
tools/perf/util/record.c | 11 +-
tools/perf/util/s390-sample-raw.c | 19 +-
tools/perf/util/sample-raw.c | 4 +-
tools/perf/util/sample.c | 17 +-
tools/perf/util/scripting-engines/Build | 9 -
.../util/scripting-engines/trace-event-perl.c | 773 ------
.../scripting-engines/trace-event-python.c | 2209 -----------------
tools/perf/util/session.c | 59 +-
tools/perf/util/sideband_evlist.c | 40 +-
tools/perf/util/sort.c | 2 +-
tools/perf/util/stat-display.c | 6 +-
tools/perf/util/stat-shadow.c | 24 +-
tools/perf/util/stat.c | 20 +-
tools/perf/util/stream.c | 4 +-
tools/perf/util/synthetic-events.c | 36 +-
tools/perf/util/synthetic-events.h | 6 +-
tools/perf/util/time-utils.c | 12 +-
tools/perf/util/top.c | 4 +-
tools/perf/util/trace-event-parse.c | 65 -
tools/perf/util/trace-event-scripting.c | 410 ---
tools/perf/util/trace-event.h | 75 +-
268 files changed, 11291 insertions(+), 15964 deletions(-)
delete mode 100644 tools/build/feature/test-libperl.c
delete mode 100644 tools/build/feature/test-libpython.c
create mode 100644 tools/build/feature/test-python-module.c
delete mode 100644 tools/perf/Documentation/perf-script-perl.txt
create mode 100755 tools/perf/python/SchedGui.py
create mode 100755 tools/perf/python/arm-cs-trace-disasm.py
create mode 100755 tools/perf/python/check-perf-trace.py
create mode 100755 tools/perf/python/compaction-times.py
create mode 100755 tools/perf/python/event_analyzing_sample.py
create mode 100755 tools/perf/python/export-to-postgresql.py
create mode 100755 tools/perf/python/export-to-sqlite.py
rename tools/perf/{scripts => }/python/exported-sql-viewer.py (99%)
create mode 100755 tools/perf/python/failed-syscalls-by-pid.py
create mode 100755 tools/perf/python/failed-syscalls.py
create mode 100755 tools/perf/python/flamegraph.py
create mode 100755 tools/perf/python/futex-contention.py
create mode 100755 tools/perf/python/gecko.py
create mode 100755 tools/perf/python/intel-pt-events.py
create mode 100755 tools/perf/python/libxed.py
rename tools/perf/{scripts => }/python/mem-phys-addr.py (73%)
mode change 100644 => 100755
create mode 100755 tools/perf/python/net_dropmonitor.py
create mode 100755 tools/perf/python/netdev-times.py
rename tools/perf/{scripts => }/python/parallel-perf.py (100%)
create mode 100644 tools/perf/python/perf.pyi
create mode 100755 tools/perf/python/perf_live.py
create mode 100755 tools/perf/python/powerpc-hcalls.py
create mode 100755 tools/perf/python/rw-by-file.py
create mode 100755 tools/perf/python/rw-by-pid.py
create mode 100755 tools/perf/python/rwtop.py
create mode 100755 tools/perf/python/sched-migration.py
create mode 100755 tools/perf/python/sctop.py
create mode 100755 tools/perf/python/stackcollapse.py
create mode 100755 tools/perf/python/stat-cpi.py
create mode 100755 tools/perf/python/syscall-counts-by-pid.py
create mode 100755 tools/perf/python/syscall-counts.py
create mode 100755 tools/perf/python/task-analyzer.py
create mode 100755 tools/perf/python/wakeup-latency.py
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/Build
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/Context.c
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/Makefile.PL
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/README
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
delete mode 100644 tools/perf/scripts/perl/Perf-Trace-Util/typemap
delete mode 100644 tools/perf/scripts/perl/bin/check-perf-trace-record
delete mode 100644 tools/perf/scripts/perl/bin/failed-syscalls-record
delete mode 100644 tools/perf/scripts/perl/bin/failed-syscalls-report
delete mode 100644 tools/perf/scripts/perl/bin/rw-by-file-record
delete mode 100644 tools/perf/scripts/perl/bin/rw-by-file-report
delete mode 100644 tools/perf/scripts/perl/bin/rw-by-pid-record
delete mode 100644 tools/perf/scripts/perl/bin/rw-by-pid-report
delete mode 100644 tools/perf/scripts/perl/bin/rwtop-record
delete mode 100644 tools/perf/scripts/perl/bin/rwtop-report
delete mode 100644 tools/perf/scripts/perl/bin/wakeup-latency-record
delete mode 100644 tools/perf/scripts/perl/bin/wakeup-latency-report
delete mode 100644 tools/perf/scripts/perl/check-perf-trace.pl
delete mode 100644 tools/perf/scripts/perl/failed-syscalls.pl
delete mode 100644 tools/perf/scripts/perl/rw-by-file.pl
delete mode 100644 tools/perf/scripts/perl/rw-by-pid.pl
delete mode 100644 tools/perf/scripts/perl/rwtop.pl
delete mode 100644 tools/perf/scripts/perl/wakeup-latency.pl
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/Build
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/Context.c
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
delete mode 100755 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
delete mode 100644 tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
delete mode 100755 tools/perf/scripts/python/arm-cs-trace-disasm.py
delete mode 100644 tools/perf/scripts/python/bin/compaction-times-record
delete mode 100644 tools/perf/scripts/python/bin/compaction-times-report
delete mode 100644 tools/perf/scripts/python/bin/event_analyzing_sample-record
delete mode 100644 tools/perf/scripts/python/bin/event_analyzing_sample-report
delete mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-record
delete mode 100644 tools/perf/scripts/python/bin/export-to-postgresql-report
delete mode 100644 tools/perf/scripts/python/bin/export-to-sqlite-record
delete mode 100644 tools/perf/scripts/python/bin/export-to-sqlite-report
delete mode 100644 tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
delete mode 100644 tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
delete mode 100755 tools/perf/scripts/python/bin/flamegraph-record
delete mode 100755 tools/perf/scripts/python/bin/flamegraph-report
delete mode 100644 tools/perf/scripts/python/bin/futex-contention-record
delete mode 100644 tools/perf/scripts/python/bin/futex-contention-report
delete mode 100644 tools/perf/scripts/python/bin/gecko-record
delete mode 100755 tools/perf/scripts/python/bin/gecko-report
delete mode 100644 tools/perf/scripts/python/bin/intel-pt-events-record
delete mode 100644 tools/perf/scripts/python/bin/intel-pt-events-report
delete mode 100644 tools/perf/scripts/python/bin/mem-phys-addr-record
delete mode 100644 tools/perf/scripts/python/bin/mem-phys-addr-report
delete mode 100755 tools/perf/scripts/python/bin/net_dropmonitor-record
delete mode 100755 tools/perf/scripts/python/bin/net_dropmonitor-report
delete mode 100644 tools/perf/scripts/python/bin/netdev-times-record
delete mode 100644 tools/perf/scripts/python/bin/netdev-times-report
delete mode 100644 tools/perf/scripts/python/bin/powerpc-hcalls-record
delete mode 100644 tools/perf/scripts/python/bin/powerpc-hcalls-report
delete mode 100644 tools/perf/scripts/python/bin/sched-migration-record
delete mode 100644 tools/perf/scripts/python/bin/sched-migration-report
delete mode 100644 tools/perf/scripts/python/bin/sctop-record
delete mode 100644 tools/perf/scripts/python/bin/sctop-report
delete mode 100755 tools/perf/scripts/python/bin/stackcollapse-record
delete mode 100755 tools/perf/scripts/python/bin/stackcollapse-report
delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-by-pid-record
delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-by-pid-report
delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-record
delete mode 100644 tools/perf/scripts/python/bin/syscall-counts-report
delete mode 100755 tools/perf/scripts/python/bin/task-analyzer-record
delete mode 100755 tools/perf/scripts/python/bin/task-analyzer-report
delete mode 100644 tools/perf/scripts/python/check-perf-trace.py
delete mode 100644 tools/perf/scripts/python/compaction-times.py
delete mode 100644 tools/perf/scripts/python/event_analyzing_sample.py
delete mode 100644 tools/perf/scripts/python/export-to-postgresql.py
delete mode 100644 tools/perf/scripts/python/export-to-sqlite.py
delete mode 100644 tools/perf/scripts/python/failed-syscalls-by-pid.py
delete mode 100755 tools/perf/scripts/python/flamegraph.py
delete mode 100644 tools/perf/scripts/python/futex-contention.py
delete mode 100644 tools/perf/scripts/python/gecko.py
delete mode 100644 tools/perf/scripts/python/intel-pt-events.py
delete mode 100644 tools/perf/scripts/python/libxed.py
delete mode 100755 tools/perf/scripts/python/net_dropmonitor.py
delete mode 100644 tools/perf/scripts/python/netdev-times.py
delete mode 100644 tools/perf/scripts/python/powerpc-hcalls.py
delete mode 100644 tools/perf/scripts/python/sched-migration.py
delete mode 100644 tools/perf/scripts/python/sctop.py
delete mode 100755 tools/perf/scripts/python/stackcollapse.py
delete mode 100644 tools/perf/scripts/python/stat-cpi.py
delete mode 100644 tools/perf/scripts/python/syscall-counts-by-pid.py
delete mode 100644 tools/perf/scripts/python/syscall-counts.py
delete mode 100755 tools/perf/scripts/python/task-analyzer.py
create mode 100644 tools/perf/tests/shell/lib/perf_brstack_max.py
delete mode 100755 tools/perf/tests/shell/script_perl.sh
delete mode 100755 tools/perf/tests/shell/script_python.sh
delete mode 100644 tools/perf/util/scripting-engines/Build
delete mode 100644 tools/perf/util/scripting-engines/trace-event-perl.c
delete mode 100644 tools/perf/util/scripting-engines/trace-event-python.c
delete mode 100644 tools/perf/util/trace-event-scripting.c
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply
* [PATCH v5 01/58] perf inject: Fix itrace branch stack synthesis
From: Ian Rogers @ 2026-04-24 16:46 UTC (permalink / raw)
To: acme, adrian.hunter, james.clark, leo.yan, namhyung, tmricht
Cc: alice.mei.rogers, dapeng1.mi, linux-arm-kernel, linux-kernel,
linux-perf-users, mingo, peterz, Ian Rogers
In-Reply-To: <20260424164721.2229025-1-irogers@google.com>
When using "perf inject --itrace=L" to synthesize branch stacks from
AUX data, several issues caused failures:
1. The synthesized samples were delivered without the
PERF_SAMPLE_BRANCH_STACK flag if it was not in the original event's
sample_type. Fixed by using sample_type | evsel->synth_sample_type
in intel_pt_deliver_synth_event.
2. The record layout was misaligned because of inconsistent handling
of PERF_SAMPLE_BRANCH_HW_INDEX. Fixed by explicitly writing nr and
hw_idx in perf_event__synthesize_sample.
3. Modifying evsel->core.attr.sample_type early in __cmd_inject caused
parse failures for subsequent records in the input file. Fixed by
moving this modification to just before writing the header.
4. perf_event__repipe_sample was narrowed to only synthesize samples
when branch stack injection was requested, and restored the use of
perf_inject__cut_auxtrace_sample as a fallback to preserve
functionality.
Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
Issues fixed in v2:
1. Potential Heap Overflow in perf_event__repipe_sample : Addressed by
adding a check that prints an error and returns -EFAULT if the
calculated event size exceeds PERF_SAMPLE_MAX_SIZE , as you
requested.
2. Header vs Payload Mismatch in __cmd_inject : Addressed by narrowing
the condition so that HEADER_BRANCH_STACK is only set in the file
header if add_last_branch was true.
3. NULL Pointer Dereference in intel-pt.c : Addressed by updating the
condition in intel_pt_do_synth_pebs_sample to fill sample.
branch_stack if it was synthesized, even if not in the original
sample_type .
4. Unsafe Reads for events lacking HW_INDEX in synthetic-events.c :
Addressed by using the perf_sample__branch_entries() macro and
checking sample->no_hw_idx .
5. Size mismatch in perf_event__sample_event_size : Addressed by
passing branch_sample_type to it and conditioning the hw_idx size on
PERF_SAMPLE_BRANCH_HW_INDEX .
---
tools/perf/bench/inject-buildid.c | 9 ++--
tools/perf/builtin-inject.c | 77 ++++++++++++++++++++++++++++--
tools/perf/tests/dlfilter-test.c | 8 +++-
tools/perf/tests/sample-parsing.c | 5 +-
tools/perf/util/arm-spe.c | 7 ++-
tools/perf/util/cs-etm.c | 6 ++-
tools/perf/util/intel-bts.c | 3 +-
tools/perf/util/intel-pt.c | 13 +++--
tools/perf/util/synthetic-events.c | 25 +++++++---
tools/perf/util/synthetic-events.h | 6 ++-
10 files changed, 129 insertions(+), 30 deletions(-)
diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c
index aad572a78d7f..bfd2c5ec9488 100644
--- a/tools/perf/bench/inject-buildid.c
+++ b/tools/perf/bench/inject-buildid.c
@@ -228,9 +228,12 @@ static ssize_t synthesize_sample(struct bench_data *data, struct bench_dso *dso,
event.header.type = PERF_RECORD_SAMPLE;
event.header.misc = PERF_RECORD_MISC_USER;
- event.header.size = perf_event__sample_event_size(&sample, bench_sample_type, 0);
-
- perf_event__synthesize_sample(&event, bench_sample_type, 0, &sample);
+ event.header.size = perf_event__sample_event_size(&sample, bench_sample_type,
+ /*read_format=*/0,
+ /*branch_sample_type=*/0);
+ perf_event__synthesize_sample(&event, bench_sample_type,
+ /*read_format=*/0,
+ /*branch_sample_type=*/0, &sample);
return writen(data->input_pipe[1], &event, event.header.size);
}
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index f174bc69cec4..88c0ef4f5ff1 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -375,7 +375,59 @@ static int perf_event__repipe_sample(const struct perf_tool *tool,
build_id__mark_dso_hit(tool, event, sample, evsel, machine);
- if (inject->itrace_synth_opts.set && sample->aux_sample.size) {
+ if (inject->itrace_synth_opts.set &&
+ (inject->itrace_synth_opts.last_branch ||
+ inject->itrace_synth_opts.add_last_branch)) {
+ union perf_event *event_copy = (void *)inject->event_copy;
+ struct branch_stack dummy_bs = { .nr = 0 };
+ int err;
+ size_t sz;
+ u64 orig_type = evsel->core.attr.sample_type;
+ u64 orig_branch_type = evsel->core.attr.branch_sample_type;
+
+ if (event_copy == NULL) {
+ inject->event_copy = malloc(PERF_SAMPLE_MAX_SIZE);
+ if (!inject->event_copy)
+ return -ENOMEM;
+
+ event_copy = (void *)inject->event_copy;
+ }
+
+ if (!sample->branch_stack)
+ sample->branch_stack = &dummy_bs;
+
+ if (inject->itrace_synth_opts.add_last_branch) {
+ /* Temporarily add in type bits for synthesis. */
+ evsel->core.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+ evsel->core.attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+ evsel->core.attr.sample_type &= ~PERF_SAMPLE_AUX;
+ }
+
+ sz = perf_event__sample_event_size(sample, evsel->core.attr.sample_type,
+ evsel->core.attr.read_format,
+ evsel->core.attr.branch_sample_type);
+
+ if (sz > PERF_SAMPLE_MAX_SIZE) {
+ pr_err("Sample size %zu exceeds max size %d\n", sz, PERF_SAMPLE_MAX_SIZE);
+ return -EFAULT;
+ }
+
+ event_copy->header.type = PERF_RECORD_SAMPLE;
+ event_copy->header.size = sz;
+
+ err = perf_event__synthesize_sample(event_copy, evsel->core.attr.sample_type,
+ evsel->core.attr.read_format,
+ evsel->core.attr.branch_sample_type, sample);
+
+ evsel->core.attr.sample_type = orig_type;
+ evsel->core.attr.branch_sample_type = orig_branch_type;
+
+ if (err) {
+ pr_err("Failed to synthesize sample\n");
+ return err;
+ }
+ event = event_copy;
+ } else if (inject->itrace_synth_opts.set && sample->aux_sample.size) {
event = perf_inject__cut_auxtrace_sample(inject, event, sample);
if (IS_ERR(event))
return PTR_ERR(event);
@@ -464,7 +516,8 @@ static int perf_event__convert_sample_callchain(const struct perf_tool *tool,
sample_type &= ~(PERF_SAMPLE_STACK_USER | PERF_SAMPLE_REGS_USER);
perf_event__synthesize_sample(event_copy, sample_type,
- evsel->core.attr.read_format, sample);
+ evsel->core.attr.read_format,
+ evsel->core.attr.branch_sample_type, sample);
return perf_event__repipe_synth(tool, event_copy);
}
@@ -1100,7 +1153,8 @@ static int perf_inject__sched_stat(const struct perf_tool *tool,
sample_sw.period = sample->period;
sample_sw.time = sample->time;
perf_event__synthesize_sample(event_sw, evsel->core.attr.sample_type,
- evsel->core.attr.read_format, &sample_sw);
+ evsel->core.attr.read_format,
+ evsel->core.attr.branch_sample_type, &sample_sw);
build_id__mark_dso_hit(tool, event_sw, &sample_sw, evsel, machine);
ret = perf_event__repipe(tool, event_sw, &sample_sw, machine);
perf_sample__exit(&sample_sw);
@@ -2434,12 +2488,25 @@ static int __cmd_inject(struct perf_inject *inject)
* synthesized hardware events, so clear the feature flag.
*/
if (inject->itrace_synth_opts.set) {
+ struct evsel *evsel;
+
perf_header__clear_feat(&session->header,
HEADER_AUXTRACE);
- if (inject->itrace_synth_opts.last_branch ||
- inject->itrace_synth_opts.add_last_branch)
+
+ evlist__for_each_entry(session->evlist, evsel) {
+ evsel->core.attr.sample_type &= ~PERF_SAMPLE_AUX;
+ }
+
+ if (inject->itrace_synth_opts.add_last_branch) {
perf_header__set_feat(&session->header,
HEADER_BRANCH_STACK);
+
+ evlist__for_each_entry(session->evlist, evsel) {
+ evsel->core.attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+ evsel->core.attr.branch_sample_type |=
+ PERF_SAMPLE_BRANCH_HW_INDEX;
+ }
+ }
}
/*
diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c
index e63790c61d53..204663571943 100644
--- a/tools/perf/tests/dlfilter-test.c
+++ b/tools/perf/tests/dlfilter-test.c
@@ -188,8 +188,12 @@ static int write_sample(struct test_data *td, u64 sample_type, u64 id, pid_t pid
event->header.type = PERF_RECORD_SAMPLE;
event->header.misc = PERF_RECORD_MISC_USER;
- event->header.size = perf_event__sample_event_size(&sample, sample_type, 0);
- err = perf_event__synthesize_sample(event, sample_type, 0, &sample);
+ event->header.size = perf_event__sample_event_size(&sample, sample_type,
+ /*read_format=*/0,
+ /*branch_sample_type=*/0);
+ err = perf_event__synthesize_sample(event, sample_type,
+ /*read_format=*/0,
+ /*branch_sample_type=*/0, &sample);
if (err)
return test_result("perf_event__synthesize_sample() failed", TEST_FAIL);
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index a7327c942ca2..55f0b73ca20e 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -310,7 +310,8 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
sample.read.one.lost = 1;
}
- sz = perf_event__sample_event_size(&sample, sample_type, read_format);
+ sz = perf_event__sample_event_size(&sample, sample_type, read_format,
+ evsel.core.attr.branch_sample_type);
bufsz = sz + 4096; /* Add a bit for overrun checking */
event = malloc(bufsz);
if (!event) {
@@ -324,7 +325,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
event->header.size = sz;
err = perf_event__synthesize_sample(event, sample_type, read_format,
- &sample);
+ evsel.core.attr.branch_sample_type, &sample);
if (err) {
pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
"perf_event__synthesize_sample", sample_type, err);
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index e5835042acdf..c4ed9f10e731 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -484,8 +484,11 @@ static void arm_spe__prep_branch_stack(struct arm_spe_queue *speq)
static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type)
{
- event->header.size = perf_event__sample_event_size(sample, type, 0);
- return perf_event__synthesize_sample(event, type, 0, sample);
+ event->header.type = PERF_RECORD_SAMPLE;
+ event->header.size = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+ /*branch_sample_type=*/0);
+ return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+ /*branch_sample_type=*/0, sample);
}
static inline int
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 8a639d2e51a4..1ebc1a6a5e75 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1425,8 +1425,10 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq,
static int cs_etm__inject_event(union perf_event *event,
struct perf_sample *sample, u64 type)
{
- event->header.size = perf_event__sample_event_size(sample, type, 0);
- return perf_event__synthesize_sample(event, type, 0, sample);
+ event->header.size = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+ /*branch_sample_type=*/0);
+ return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+ /*branch_sample_type=*/0, sample);
}
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 382255393fb3..0b18ebd13f7c 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -303,7 +303,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
event.sample.header.size = bts->branches_event_size;
ret = perf_event__synthesize_sample(&event,
bts->branches_sample_type,
- 0, &sample);
+ /*read_format=*/0, /*branch_sample_type=*/0,
+ &sample);
if (ret)
return ret;
}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index fc9eec8b54b8..2dce6106c038 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1731,8 +1731,12 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
static int intel_pt_inject_event(union perf_event *event,
struct perf_sample *sample, u64 type)
{
- event->header.size = perf_event__sample_event_size(sample, type, 0);
- return perf_event__synthesize_sample(event, type, 0, sample);
+ event->header.type = PERF_RECORD_SAMPLE;
+ event->header.size = perf_event__sample_event_size(sample, type, /*read_format=*/0,
+ /*branch_sample_type=*/0);
+
+ return perf_event__synthesize_sample(event, type, /*read_format=*/0,
+ /*branch_sample_type=*/0, sample);
}
static inline int intel_pt_opt_inject(struct intel_pt *pt,
@@ -2486,7 +2490,7 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
intel_pt_add_xmm(intr_regs, pos, items, regs_mask);
}
- if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ if ((sample_type | evsel->synth_sample_type) & PERF_SAMPLE_BRANCH_STACK) {
if (items->mask[INTEL_PT_LBR_0_POS] ||
items->mask[INTEL_PT_LBR_1_POS] ||
items->mask[INTEL_PT_LBR_2_POS]) {
@@ -2557,7 +2561,8 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
sample.transaction = txn;
}
- ret = intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
+ ret = intel_pt_deliver_synth_event(pt, event, &sample,
+ sample_type | evsel->synth_sample_type);
perf_sample__exit(&sample);
return ret;
}
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 85bee747f4cd..2461f25a4d7d 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1455,7 +1455,8 @@ int perf_event__synthesize_stat_round(const struct perf_tool *tool,
return process(tool, (union perf_event *) &event, NULL, machine);
}
-size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format)
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format,
+ u64 branch_sample_type)
{
size_t sz, result = sizeof(struct perf_record_sample);
@@ -1515,8 +1516,10 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry);
- /* nr, hw_idx */
- sz += 2 * sizeof(u64);
+ /* nr */
+ sz += sizeof(u64);
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)
+ sz += sizeof(u64);
result += sz;
}
@@ -1605,7 +1608,7 @@ static __u64 *copy_read_group_values(__u64 *array, __u64 read_format,
}
int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
- const struct perf_sample *sample)
+ u64 branch_sample_type, const struct perf_sample *sample)
{
__u64 *array;
size_t sz;
@@ -1719,9 +1722,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry);
- /* nr, hw_idx */
- sz += 2 * sizeof(u64);
- memcpy(array, sample->branch_stack, sz);
+
+ *array++ = sample->branch_stack->nr;
+
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX) {
+ if (sample->no_hw_idx)
+ *array++ = 0;
+ else
+ *array++ = sample->branch_stack->hw_idx;
+ }
+
+ memcpy(array, perf_sample__branch_entries((struct perf_sample *)sample), sz);
array = (void *)array + sz;
}
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index b0edad0c3100..8c7f49f9ccf5 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -81,7 +81,8 @@ int perf_event__synthesize_mmap_events(const struct perf_tool *tool, union perf_
int perf_event__synthesize_modules(const struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_namespaces(const struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_cgroups(const struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample);
+int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format,
+ u64 branch_sample_type, const struct perf_sample *sample);
int perf_event__synthesize_stat_config(const struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
int perf_event__synthesize_stat_events(struct perf_stat_config *config, const struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);
int perf_event__synthesize_stat_round(const struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
@@ -97,7 +98,8 @@ void perf_event__synthesize_final_bpf_metadata(struct perf_session *session,
int perf_tool__process_synth_event(const struct perf_tool *tool, union perf_event *event, struct machine *machine, perf_event__handler_t process);
-size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, u64 read_format);
+size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
+ u64 read_format, u64 branch_sample_type);
int __machine__synthesize_threads(struct machine *machine, const struct perf_tool *tool,
struct target *target, struct perf_thread_map *threads,
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* [PATCH] arm64/entry: Fix arm64-specific rseq brokenness (was: Re: [REGRESSION] rseq: refactoring in v6.19 broke everyone on arm64) and tcmalloc everywhere
From: Mark Rutland @ 2026-04-24 16:45 UTC (permalink / raw)
To: Mathias Stearn, Linus Torvalds, Catalin Marinas, Will Deacon,
Thomas Gleixner, Mathieu Desnoyers, Peter Zijlstra
Cc: Boqun Feng, Paul E. McKenney, Chris Kennelly, Dmitry Vyukov,
regressions, linux-kernel, linux-arm-kernel, Ingo Molnar,
Jinjie Ruan, Blake Oler
In-Reply-To: <CAHnCjA25b+nO2n5CeifknSKHssJpPrjnf+dtr7UgzRw4Zgu=oA@mail.gmail.com>
Patch for the arm64-specific issue below. This doesn't fix the generic
cpu_id_start issue, but it brings arm64 into line with everyone else,
and it's the shape we'll need going forwards for other stuff anyway.
I've given it light testing with Mathias's reproducer and the
kselftests, which all pass.
I've also pushed it to my arm64/rseq branch:
https://git.kernel.org/pub/scm/linux/kernel/git/mark/linux.git/log/?h=arm64/rseq
Mark.
---->8----
From 79b65cbbfa20aa2cb0bc248591fab5459cdc101b Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 23 Apr 2026 16:51:12 +0100
Subject: [PATCH] arm64/entry: Fix arm64-specific rseq brokenness
Mathias Stearn reports that since v6.19, there are two big issues
affecting rseq:
(1) On arm64 specifically, rseq critical sections aren't aborted when
they should be.
(2) The 'cpu_id_start' field is no longer written by the kernel in all
cases it used to be, including some cases where TCMalloc depends on
the kernel clobbering the field.
This patch fixes issue #1. This patch DOES NOT fix issue #2, which will
need to be addressed by other patches.
The arm64-specific brokenness is a result of commits:
2fc0e4b4126c ("rseq: Record interrupt from user space")
39a167560a61 ("rseq: Optimize event setting")
The first commit failed to add a call to rseq_note_user_irq_entry() on
arm64. Thus arm64 never sets rseq_event::user_irq to record that it may
be necessary to abort an active rseq critical section upon return to
userspace. On its own, this commit had no functional impact as the value
of rseq_event::user_irq was not consumed.
The second commit relied upon rseq_event::user_irq to determine whether
or not to bother to perform rseq work when returning to userspace. As
rseq_event::user_irq wasn't set on arm64, this work would be skipped,
and consequently an active rseq critical section would not be aborted.
Fix this by giving arm64 syscall-specific entry/exit paths, and
performing the relevant logic in syscall and non-syscall paths,
including calling rseq_note_user_irq_entry() for non-syscall entry.
Currently arm64 cannot use syscall_enter_from_user_mode(),
syscall_exit_to_user_mode(), and irqentry_exit_to_user_mode(), due to
ordering constraints with exception masking, and risk of ABI breakage
for syscall tracing/audit/etc. For the moment the entry/exit logic is
left as arm64-specific, but mirroring the generic code.
I intend to follow up with refactoring/cleanup, as we did for kernel
mode entry paths in commit:
041aa7a85390 ("entry: Split preemption from irqentry_exit_to_kernel_mode()")
... which will allow arm64 to use the GENERIC_IRQ_ENTRY functions directly.
Fixes: 39a167560a61 ("rseq: Optimize event setting")
Reported-by: Mathias Stearn <mathias@mongodb.com>
Link: https://lore.kernel.org/regressions/CAHnCjA25b+nO2n5CeifknSKHssJpPrjnf+dtr7UgzRw4Zgu=oA@mail.gmail.com/
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Kennelly <ckennelly@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/entry-common.c | 29 ++++++++++++++++++++++-------
include/linux/irq-entry-common.h | 8 --------
include/linux/rseq_entry.h | 19 -------------------
3 files changed, 22 insertions(+), 34 deletions(-)
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index cb54335465f66..65ade1f1544f6 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -62,6 +62,12 @@ static void noinstr arm64_exit_to_kernel_mode(struct pt_regs *regs,
irqentry_exit_to_kernel_mode_after_preempt(regs, state);
}
+static __always_inline void arm64_syscall_enter_from_user_mode(struct pt_regs *regs)
+{
+ enter_from_user_mode(regs);
+ mte_disable_tco_entry(current);
+}
+
/*
* Handle IRQ/context state management when entering from user mode.
* Before this function is called it is not safe to call regular kernel code,
@@ -70,20 +76,29 @@ static void noinstr arm64_exit_to_kernel_mode(struct pt_regs *regs,
static __always_inline void arm64_enter_from_user_mode(struct pt_regs *regs)
{
enter_from_user_mode(regs);
+ rseq_note_user_irq_entry();
mte_disable_tco_entry(current);
sme_enter_from_user_mode();
}
+static __always_inline void arm64_syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+ local_irq_disable();
+ syscall_exit_to_user_mode_prepare(regs);
+ local_daif_mask();
+ mte_check_tfsr_exit();
+ exit_to_user_mode();
+}
+
/*
* Handle IRQ/context state management when exiting to user mode.
* After this function returns it is not safe to call regular kernel code,
* instrumentable code, or any code which may trigger an exception.
*/
-
static __always_inline void arm64_exit_to_user_mode(struct pt_regs *regs)
{
local_irq_disable();
- exit_to_user_mode_prepare_legacy(regs);
+ irqentry_exit_to_user_mode_prepare(regs);
local_daif_mask();
sme_exit_to_user_mode();
mte_check_tfsr_exit();
@@ -92,7 +107,7 @@ static __always_inline void arm64_exit_to_user_mode(struct pt_regs *regs)
asmlinkage void noinstr asm_exit_to_user_mode(struct pt_regs *regs)
{
- arm64_exit_to_user_mode(regs);
+ arm64_syscall_exit_to_user_mode(regs);
}
/*
@@ -716,12 +731,12 @@ static void noinstr el0_brk64(struct pt_regs *regs, unsigned long esr)
static void noinstr el0_svc(struct pt_regs *regs)
{
- arm64_enter_from_user_mode(regs);
+ arm64_syscall_enter_from_user_mode(regs);
cortex_a76_erratum_1463225_svc_handler();
fpsimd_syscall_enter();
local_daif_restore(DAIF_PROCCTX);
do_el0_svc(regs);
- arm64_exit_to_user_mode(regs);
+ arm64_syscall_exit_to_user_mode(regs);
fpsimd_syscall_exit();
}
@@ -868,11 +883,11 @@ static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr)
static void noinstr el0_svc_compat(struct pt_regs *regs)
{
- arm64_enter_from_user_mode(regs);
+ arm64_syscall_enter_from_user_mode(regs);
cortex_a76_erratum_1463225_svc_handler();
local_daif_restore(DAIF_PROCCTX);
do_el0_svc_compat(regs);
- arm64_exit_to_user_mode(regs);
+ arm64_syscall_exit_to_user_mode(regs);
}
static void noinstr el0_bkpt32(struct pt_regs *regs, unsigned long esr)
diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
index 167fba7dbf043..1fabf0f5ea8e7 100644
--- a/include/linux/irq-entry-common.h
+++ b/include/linux/irq-entry-common.h
@@ -218,14 +218,6 @@ static __always_inline void __exit_to_user_mode_validate(void)
lockdep_sys_exit();
}
-/* Temporary workaround to keep ARM64 alive */
-static __always_inline void exit_to_user_mode_prepare_legacy(struct pt_regs *regs)
-{
- __exit_to_user_mode_prepare(regs, EXIT_TO_USER_MODE_WORK);
- rseq_exit_to_user_mode_legacy();
- __exit_to_user_mode_validate();
-}
-
/**
* syscall_exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
* @regs: Pointer to pt_regs on entry stack
diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h
index f11ebd34f8b95..a3762410c4ab6 100644
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -753,24 +753,6 @@ static __always_inline void rseq_irqentry_exit_to_user_mode(void)
ev->events = 0;
}
-/* Required to keep ARM64 working */
-static __always_inline void rseq_exit_to_user_mode_legacy(void)
-{
- struct rseq_event *ev = ¤t->rseq.event;
-
- rseq_stat_inc(rseq_stats.exit);
-
- if (static_branch_unlikely(&rseq_debug_enabled))
- WARN_ON_ONCE(ev->sched_switch);
-
- /*
- * Ensure that event (especially user_irq) is cleared when the
- * interrupt did not result in a schedule and therefore the
- * rseq processing did not clear it.
- */
- ev->events = 0;
-}
-
void __rseq_debug_syscall_return(struct pt_regs *regs);
static __always_inline void rseq_debug_syscall_return(struct pt_regs *regs)
@@ -786,7 +768,6 @@ static inline bool rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned
}
static inline void rseq_syscall_exit_to_user_mode(void) { }
static inline void rseq_irqentry_exit_to_user_mode(void) { }
-static inline void rseq_exit_to_user_mode_legacy(void) { }
static inline void rseq_debug_syscall_return(struct pt_regs *regs) { }
static inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { return false; }
#endif /* !CONFIG_RSEQ */
--
2.30.2
^ permalink raw reply related
* Re: [PATCH v2] kselftest/arm64: Fix build failure with GCC-15
From: Catalin Marinas @ 2026-04-24 16:44 UTC (permalink / raw)
To: Mark Brown
Cc: Leo Yan, Will Deacon, Shuah Khan, Thiago Jung Bauermann,
linux-arm-kernel, linux-kselftest, linux-kernel
In-Reply-To: <63409143-f4eb-48c3-89de-1aef4fb57381@sirena.org.uk>
On Fri, Apr 24, 2026 at 05:07:42PM +0100, Mark Brown wrote:
> On Fri, Apr 24, 2026 at 04:51:24PM +0100, Catalin Marinas wrote:
> > On Wed, Apr 22, 2026 at 06:42:54PM +0100, Leo Yan wrote:
>
> > > Building on Debian sid with GCC 15 fails:
>
> > I think a better fix is to always define struct user_gcs and only
> > conditionally define NT_ARM_GCS (IOW, move the #endif higher).
>
> I've not actually double checked that everything is wired up properly
> but I believe these days this should actually pick up asm/ptrace.h from
> the headers_install target so a current kernel copy. We ought to be
> able to remove the local definition of struct user_gcs I think, there's
> still some weirdness with the NT_ definitions I can't remember but the
> struct should be fine.
OK, so it does look like it picks the kernel uapi/asm/ptrace.h. It
builds fine on Debian stable (no GCS anywhere) with including
asm/ptrace.h and removing struct user_gcs.
But I think we should include asm/ptrace.h in libc-gcs.h and not the
gcs-util.h header (for NT_ARM_GCS it's fine to keep in gcs-util.h).
--
Catalin
^ permalink raw reply
* Re: [PATCH] iommu/arm-smmu-v3: Allow disabling Stage 1 translation
From: Jason Gunthorpe @ 2026-04-24 16:39 UTC (permalink / raw)
To: Will Deacon
Cc: Evangelos Petrongonas, Robin Murphy, Joerg Roedel, Nicolin Chen,
Pranjal Shrivastava, Lu Baolu, linux-arm-kernel, iommu,
linux-kernel, nh-open-source, Zeev Zilberman
In-Reply-To: <aeuT1-TB6dOT5ZQ2@willie-the-truck>
On Fri, Apr 24, 2026 at 05:01:27PM +0100, Will Deacon wrote:
> On Fri, Apr 24, 2026 at 12:42:56PM -0300, Jason Gunthorpe wrote:
> > On Fri, Apr 24, 2026 at 04:16:17PM +0100, Will Deacon wrote:
> > > > > > STE/CD is pretty simple now, there is only one place to put the CMO
> > > > > > and the ordering is all handled with that shared code. We no longer
> > > > > > care about ordering beyond all the writes must be visible to HW before
> > > > > > issuing the CMDQ invalidation command - which is the same environment
> > > > > > as the pagetable.
> > > > >
> > > > > You presumably rely on 64-bit single-copy atomicity for hitless updates,
> > > > > no?
> > > >
> > > > Yes, just like the page table does..
> > > >
> > > > I hope that's not a problem or we have a issue with the PTW :)
> > >
> > > You trimmed the part from my reply where I think we _do_ have an issue
> > > with the PTW. Here it is again:
> > >
> > > The non-coherent case looks more fragile, because I don't _think_ the
> > > architecture provides any ordering or atomicity guarantees about cache
> > > cleaning to the PoC. Presumably, the correct sequence would be to write
> > > the PTE with the valid bit clear, do the CMO (with completion barrier),
> > > *then* write the bottom byte with the valid bit set and do another CMO.
> >
> > I wasn't sure if you are being serious.
> >
> > CMO + barriers must provide an ordering guarentee about cache cleaning
> > to POC otherwise the entire Linux DMA API is broken. dma_sync must
> > order with following device DMA. IMHO that's not negotiable for Linux.
>
> The problem is with concurrent DMA (from the page-table walker) and I
> don't see anything that guarantees that in the CPU architecture. I don't
> think the streaming DMA API pretends to handle that case, does it? It
> relies on a pretty rigid ownership concept from what I understand.
I think you pointed out two things, ordering and tearing.
Ordering is OK. If I write a PTE, dma_sync, then command a device to
use that IOVA the PTW must observe the new PTE value. Otherwise
dma_sync isn't doing what Linux requires.
Tearing is a different issue, if the device uses the IOVA and races
with the PTE write changing it then you say maybe it can mis-read it
with tearing.
However, this race only happens if the PTE is currently non-valid or
being changed to non-valid. Meaning randomly you will be getting an
invalid IOVA event.
In non-coherent mode we don't allow SVA and we don't allow VFIO. Only
the DMA API and drivers open coding things.
For VFIO and SVA, yes, we need the HW to work and properly, userspcae
can trigger invalid IOVA, we can't tolerate a corrupted PTE.
In embedded I suppose you could make an argument you don't care about
it since invalid IOVA would have to be caused by a buggy kernel
driver, it should never happen, and thus this is really a debug
feature. If the race will never be hit in a working system maybe it is
fine to leave it as is.
Would be good to document this detail :)
> Of course I'd rather that the architecture said that our current code
> is fine, but if it doesn't then I don't have much choice, really. At the
> very least, we should minimise the number of places where we rely on
> non-architected behaviour and so keeping the CDs and STEs non-cacheable
> remains my preference.
So, I am convinced, PTW has that escape above that doesn't apply to
STE/CD. Those can be accessed truely at any time and we can't ever
leave a 64 bit value in a strange state.
Jason
^ permalink raw reply
* Re: [PATCH] clk: bcm: rpi: Mark VEC clock as CLK_IGNORE_UNUSED
From: Stefan Wahren @ 2026-04-24 16:32 UTC (permalink / raw)
To: Maíra Canal, Michael Turquette, Stephen Boyd,
Florian Fainelli, Broadcom internal kernel review list,
Mark Brown, Maxime Ripard, Dom Cobley, Dave Stevenson
Cc: linux-clk, linux-rpi-kernel, linux-arm-kernel, kernel-dev
In-Reply-To: <20260401111416.562279-2-mcanal@igalia.com>
Am 01.04.26 um 13:13 schrieb Maíra Canal:
> On Raspberry Pi 3B, the VEC clock is used by the VideoCore firmware
> display driver, which remains active until the vc4 driver loads and
> sends NOTIFY_DISPLAY_DONE. If this clock is disabled during boot, a bus
> lockup happens and the firmware becomes unresponsive, causing a complete
> system lockup.
>
> Mark the VEC clock with CLK_IGNORE_UNUSED so it survives the unused
> clock disablement and remains available until the vc4 driver takes over
> display management.
>
> Fixes: 672299736af6 ("clk: bcm: rpi: Manage clock rate in prepare/unprepare callbacks")
> Reported-by: Mark Brown <broonie@kernel.org>
> Signed-off-by: Maíra Canal <mcanal@igalia.com>
FWIW:
Reviewed-by: Stefan Wahren <wahrenst@gmx.net>
^ permalink raw reply
* Re: [PATCH 3/8] firmware: sysfb: Make CONFIG_SYSFB a user-selectable option
From: Javier Martinez Canillas @ 2026-04-24 16:24 UTC (permalink / raw)
To: Thomas Zimmermann, Arnd Bergmann, Ard Biesheuvel,
Ilias Apalodimas, Huacai Chen, WANG Xuerui, Maarten Lankhorst,
Maxime Ripard, Dave Airlie, Simona Vetter, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, longli, Helge Deller
Cc: linux-arm-kernel, loongarch, linux-efi, linux-riscv, dri-devel,
linux-hyperv, linux-fbdev
In-Reply-To: <0156562f-5fcf-47ce-8fea-03345f2c3fe6@suse.de>
Thomas Zimmermann <tzimmermann@suse.de> writes:
Hello,
[...]
>>>>>> On Thu, Apr 2, 2026, at 11:09, Thomas Zimmermann wrote:
>>>>>> I don't really like this part of the series and would prefer
>>>>>> to keep CONFIG_SYSFB hidden as much as possible as an x86
I tend to agree with Arnd here, I'm also not seeing that much value on
making this symbol user selectable. For now I would just keep it hidden.
[...]
>> Yes, I saw that as well and don't have an immediate idea for how
>> to best do it. I saw that you already abstracted the access to
>> the screen_info members in drm_sysfb_screen_info.c, which I think
>> is a step in that direction.
>>
>> I also noticed that efidrm is mostly a subset of vesadrm, so
>> in theory they could be merged back into an x86 drm driver
>> along with the drm_sysfb_screen_info helpers, and have a non-x86
>> driver that constructs a drm_sysfb_device directly from the
>> EFI structures.
>
> I would not want to have a unifed driver for all-things-screen_info. The
> code that can easily be shared is already in the sysfb helpers. But I
> don't mind adding a separate driver for EFI's Graphics Output Protocol.
I agree. It is much more maintainable if we have dedicated DRM drivers that
use shared helpers, than attempting to have a driver for different platforms.
As Thomas explained, the maintance effort is small on the DRM side and he has
done a lot of work to split simpledrm in efidrm, vesadrm and ofdrm.
--
Best regards,
Javier Martinez Canillas
Core Platforms
Red Hat
^ permalink raw reply
* Re: [PATCH 15/15] arm64: dts: ti: beagley-ai: Enable HDMI display and audio
From: Robert Nelson @ 2026-04-24 16:16 UTC (permalink / raw)
To: Tomi Valkeinen
Cc: Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Lee Jones, Aradhya Bhatia, Nishanth Menon, Vignesh Raghavendra,
Swamil Jain, Devarsh Thakkar, Louis Chauvet, devicetree,
dri-devel, linux-kernel, linux-arm-kernel, Andrew Davis
In-Reply-To: <20260420-beagley-ai-display-v1-15-f628543dfd14@ideasonboard.com>
On Mon, Apr 20, 2026 at 8:04 AM Tomi Valkeinen
<tomi.valkeinen@ideasonboard.com> wrote:
>
> From: Andrew Davis <afd@ti.com>
>
> Enable HDMI support for BeagleY-AI platform. The display controller used is
> TIDSS and the HDMI bridge used is IT66122.
>
> Based on DT by: Robert Nelson <robertcnelson@gmail.com>
> Signed-off-by: Andrew Davis <afd@ti.com>
> Signed-off-by: Swamil Jain <s-jain1@ti.com>
> [tomi.valkeinen: cosmetic fixes]
> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Tested-by: Robert Nelson <robertcnelson@gmail.com>
Thank you for getting the display back end working on j722s family!
After this goes in, I need to submit the usb/usb-hub changes to enable
USB support...
Regards,
--
Robert Nelson
https://rcn-ee.com/
^ permalink raw reply
* Re: [RFC PATCH v3 3/4] Revert "tpm: tpm_crb_ffa: try to probe tpm_crb_ffa when it's built-in"
From: Sudeep Holla @ 2026-04-24 16:10 UTC (permalink / raw)
To: Jonathan McDowell
Cc: linux-security-module, linux-kernel, Sudeep Holla,
linux-integrity, linux-arm-kernel, kvmarm, paul, jmorris, serge,
zohar, roberto.sassu, dmitry.kasatkin, eric.snowberg, jarkko, jgg,
maz, oupton, joey.gouly, suzuki.poulose, yuzenghui,
catalin.marinas, will, noodles, sebastianene, Yeoreum Yun
In-Reply-To: <f8d6dcbeb5bf2d4316989d05dcaae20225774d51.1777036497.git.noodles@meta.com>
On Fri, Apr 24, 2026 at 02:24:30PM +0100, Jonathan McDowell wrote:
> From: Yeoreum Yun <yeoreum.yun@arm.com>
>
> This reverts commit 746d9e9f62a6e8ba0eba2b83fc61cfe7fa8797ce.
>
> Now that IMA will retry in the late_initcall_sync level if the TPM is
> not available at first, this change is no longer required.
>
Acked-by: Sudeep Holla <sudeep.holla@kernel.org>
--
Regards,
Sudeep
^ permalink raw reply
* Re: [RFC PATCH v3 4/4] Revert "firmware: arm_ffa: Change initcall level of ffa_init() to rootfs_initcall"
From: Sudeep Holla @ 2026-04-24 16:09 UTC (permalink / raw)
To: Jonathan McDowell
Cc: linux-security-module, linux-kernel, Sudeep Holla,
linux-integrity, linux-arm-kernel, kvmarm, paul, jmorris, serge,
zohar, roberto.sassu, dmitry.kasatkin, eric.snowberg, jarkko, jgg,
maz, oupton, joey.gouly, suzuki.poulose, yuzenghui,
catalin.marinas, will, noodles, sebastianene, Yeoreum Yun
In-Reply-To: <2e7b4dc552b45ddf14cc43bc449cbebb4ade0027.1777036497.git.noodles@meta.com>
On Fri, Apr 24, 2026 at 02:24:42PM +0100, Jonathan McDowell wrote:
> From: Yeoreum Yun <yeoreum.yun@arm.com>
>
> This reverts commit 0e0546eabcd6c19765a8dbf5b5db3723e7b0ea75, which was
> added to address ordering issues with the IMA LSM initialisation where
> the TPM would not be fully ready by the time IMA wanted it. This has
> been resolved within IMA by retrying setup during late_initcall_sync if
> the TPM is not available at first.
>
Reviewed-by: Sudeep Holla <sudeep.holla@kernel.org>
--
Regards,
Sudeep
^ permalink raw reply
* Re: [PATCH v2] kselftest/arm64: Fix build failure with GCC-15
From: Mark Brown @ 2026-04-24 16:07 UTC (permalink / raw)
To: Catalin Marinas
Cc: Leo Yan, Will Deacon, Shuah Khan, Thiago Jung Bauermann,
linux-arm-kernel, linux-kselftest, linux-kernel
In-Reply-To: <aeuRfEeOUWEHzPix@arm.com>
[-- Attachment #1: Type: text/plain, Size: 683 bytes --]
On Fri, Apr 24, 2026 at 04:51:24PM +0100, Catalin Marinas wrote:
> On Wed, Apr 22, 2026 at 06:42:54PM +0100, Leo Yan wrote:
> > Building on Debian sid with GCC 15 fails:
> I think a better fix is to always define struct user_gcs and only
> conditionally define NT_ARM_GCS (IOW, move the #endif higher).
I've not actually double checked that everything is wired up properly
but I believe these days this should actually pick up asm/ptrace.h from
the headers_install target so a current kernel copy. We ought to be
able to remove the local definition of struct user_gcs I think, there's
still some weirdness with the NT_ definitions I can't remember but the
struct should be fine.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* Re: [PATCH] iommu/arm-smmu-v3: Allow disabling Stage 1 translation
From: Will Deacon @ 2026-04-24 16:01 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Evangelos Petrongonas, Robin Murphy, Joerg Roedel, Nicolin Chen,
Pranjal Shrivastava, Lu Baolu, linux-arm-kernel, iommu,
linux-kernel, nh-open-source, Zeev Zilberman
In-Reply-To: <20260424154256.GF3611611@ziepe.ca>
On Fri, Apr 24, 2026 at 12:42:56PM -0300, Jason Gunthorpe wrote:
> On Fri, Apr 24, 2026 at 04:16:17PM +0100, Will Deacon wrote:
> > > > > STE/CD is pretty simple now, there is only one place to put the CMO
> > > > > and the ordering is all handled with that shared code. We no longer
> > > > > care about ordering beyond all the writes must be visible to HW before
> > > > > issuing the CMDQ invalidation command - which is the same environment
> > > > > as the pagetable.
> > > >
> > > > You presumably rely on 64-bit single-copy atomicity for hitless updates,
> > > > no?
> > >
> > > Yes, just like the page table does..
> > >
> > > I hope that's not a problem or we have a issue with the PTW :)
> >
> > You trimmed the part from my reply where I think we _do_ have an issue
> > with the PTW. Here it is again:
> >
> > The non-coherent case looks more fragile, because I don't _think_ the
> > architecture provides any ordering or atomicity guarantees about cache
> > cleaning to the PoC. Presumably, the correct sequence would be to write
> > the PTE with the valid bit clear, do the CMO (with completion barrier),
> > *then* write the bottom byte with the valid bit set and do another CMO.
>
> I wasn't sure if you are being serious.
>
> CMO + barriers must provide an ordering guarentee about cache cleaning
> to POC otherwise the entire Linux DMA API is broken. dma_sync must
> order with following device DMA. IMHO that's not negotiable for Linux.
The problem is with concurrent DMA (from the page-table walker) and I
don't see anything that guarantees that in the CPU architecture. I don't
think the streaming DMA API pretends to handle that case, does it? It
relies on a pretty rigid ownership concept from what I understand.
> All ARM iommus rely on 64 bit atomic non tearing. No bugs reported?
It's hard to judge as I don't think SMMUs tend to perform a lot of
speculative address translation when DMA isn't active.
> Any fix to that is going to have major performance downsides..
>
> I also strongly suspect it is provided on real HW. It would be hard to
> even build HW where <= 64 bit quanta can tear.
>
> Maybe this is something ARM should take a look at.
Yes, we should ask. Maybe I missed something in the Arm ARM, but I can
also seeing it being a pain to specify this behaviour all the way out to
the PoC and I wouldn't be so bold as to say that it's hard to build HW
that would exhibit problems here.
> > > And if Samiullah can tackle dma_alloc_coherent then maybe the whole
> > > question is moot.
> >
> > Yes, that would be great, but we probably need to fix the page-table
> > code too.
>
> You really want to deal with the likely perf regressions that would
> cause on Android/etc?
Of course I'd rather that the architecture said that our current code
is fine, but if it doesn't then I don't have much choice, really. At the
very least, we should minimise the number of places where we rely on
non-architected behaviour and so keeping the CDs and STEs non-cacheable
remains my preference.
Will
^ permalink raw reply
* Re: [PATCH v2] kselftest/arm64: Fix build failure with GCC-15
From: Catalin Marinas @ 2026-04-24 15:51 UTC (permalink / raw)
To: Leo Yan
Cc: Will Deacon, Shuah Khan, Mark Brown, Thiago Jung Bauermann,
linux-arm-kernel, linux-kselftest, linux-kernel
In-Reply-To: <20260422-selftests_arm64_gcc15-v2-1-c0134de8838a@arm.com>
On Wed, Apr 22, 2026 at 06:42:54PM +0100, Leo Yan wrote:
> Building on Debian sid with GCC 15 fails:
>
> CC libc-gcs
> libc-gcs.c: In function 'ptrace_read_write':
> libc-gcs.c:142:25: error: storage size of 'child_gcs' isn't known
> 142 | struct user_gcs child_gcs;
> | ^~~~~~~~~
> libc-gcs.c:142:25: warning: unused variable 'child_gcs' [-Wunused-variable]
>
> For GCC-15, NT_ARM_GCS is defined in the libc header, causing gcs-util.h
> to skip its fallback definition of struct user_gcs. This leads to the
> compiler error.
>
> Fix this by including <asm/ptrace.h> to provide the proper definition.
This is not caused by GCC-15 as it doesn't provide these headers. AFAICT
on Debian we have NT_ARM_GCS coming from glibc and user_gcs from the
kernel asm/ptrace.h uapi header (linux-libc-dev). We also have
NT_ARM_GCS in linux/elf.h as part of the kernel headers.
While the kernel exposed the macro and structure in the same commit, I
don't think it is required distros to align the glibc macro with the
linux headers. Glibc does not even use the kernel's linux/elf.h for the
macros, it just adds the definitions when they turn up in a released
kernel.
So you can have a glibc that defines NT_ARM_GCS but a linux-libc-dev
package that is not up to date to include struct user_gcs.
I think a better fix is to always define struct user_gcs and only
conditionally define NT_ARM_GCS (IOW, move the #endif higher).
--
Catalin
^ permalink raw reply
* [PATCH v5 8/8] arm64: dts: amlogic: t7: khadas-vim4: Add fan cooling to thermal zones
From: Ronald Claveau via B4 Relay @ 2026-04-24 15:45 UTC (permalink / raw)
To: Guillaume La Roque, Rafael J. Wysocki, Daniel Lezcano, Zhang Rui,
Lukasz Luba, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Neil Armstrong, Kevin Hilman, Jerome Brunet, Martin Blumenstingl
Cc: linux-pm, linux-amlogic, devicetree, linux-kernel,
linux-arm-kernel, Ronald Claveau
In-Reply-To: <20260424-add-thermal-t7-vim4-v5-0-9040ca36afe2@aliel.fr>
From: Ronald Claveau <linux-kernel-dev@aliel.fr>
Add an active trip at 50°C to all six thermal zones and map it to the
khadas_mcu fan controller, using cooling states 30 to 100.
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Ronald Claveau <linux-kernel-dev@aliel.fr>
---
.../dts/amlogic/amlogic-t7-a311d2-khadas-vim4.dts | 102 +++++++++++++++++++++
1 file changed, 102 insertions(+)
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-t7-a311d2-khadas-vim4.dts b/arch/arm64/boot/dts/amlogic/amlogic-t7-a311d2-khadas-vim4.dts
index 5d7f5390f3a66..ba9219073dd0a 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-t7-a311d2-khadas-vim4.dts
+++ b/arch/arm64/boot/dts/amlogic/amlogic-t7-a311d2-khadas-vim4.dts
@@ -157,6 +157,74 @@ wifi32k: wifi32k {
};
};
+&a53_thermal {
+ trips {
+ a53_active: a53-active {
+ temperature = <50000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "active";
+ };
+ };
+
+ cooling-maps {
+ map {
+ trip = <&a53_active>;
+ cooling-device = <&khadas_mcu 30 100>;
+ };
+ };
+};
+
+&a73_thermal {
+ trips {
+ a73_active: a73-active {
+ temperature = <50000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "active";
+ };
+ };
+
+ cooling-maps {
+ map {
+ trip = <&a73_active>;
+ cooling-device = <&khadas_mcu 30 100>;
+ };
+ };
+};
+
+&gpu_thermal {
+ trips {
+ gpu_active: gpu-active {
+ temperature = <50000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "active";
+ };
+ };
+
+ cooling-maps {
+ map {
+ trip = <&gpu_active>;
+ cooling-device = <&khadas_mcu 30 100>;
+ };
+ };
+};
+
+&hevc_thermal {
+ trips {
+ hevc_active: hevc-active {
+ temperature = <50000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "active";
+ };
+ };
+
+ cooling-maps {
+ map {
+ trip = <&hevc_active>;
+ cooling-device = <&khadas_mcu 30 100>;
+ };
+ };
+};
+
&i2c_m_ao_a {
status = "okay";
pinctrl-0 = <&i2c0_ao_d_pins>;
@@ -170,6 +238,23 @@ khadas_mcu: system-controller@18 {
};
};
+&nna_thermal {
+ trips {
+ nna_active: nna-active {
+ temperature = <50000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "active";
+ };
+ };
+
+ cooling-maps {
+ map {
+ trip = <&nna_active>;
+ cooling-device = <&khadas_mcu 30 100>;
+ };
+ };
+};
+
&pwm_ab {
status = "okay";
pinctrl-0 = <&pwm_a_pins>;
@@ -266,3 +351,20 @@ &uart_a {
clocks = <&xtal>, <&xtal>, <&xtal>;
clock-names = "xtal", "pclk", "baud";
};
+
+&vpu_thermal {
+ trips {
+ vpu_active: vpu-active {
+ temperature = <50000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "active";
+ };
+ };
+
+ cooling-maps {
+ map {
+ trip = <&vpu_active>;
+ cooling-device = <&khadas_mcu 30 100>;
+ };
+ };
+};
--
2.49.0
^ permalink raw reply related
* [PATCH v5 7/8] arm64: dts: amlogic: t7: Add thermal zones
From: Ronald Claveau via B4 Relay @ 2026-04-24 15:45 UTC (permalink / raw)
To: Guillaume La Roque, Rafael J. Wysocki, Daniel Lezcano, Zhang Rui,
Lukasz Luba, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Neil Armstrong, Kevin Hilman, Jerome Brunet, Martin Blumenstingl
Cc: linux-pm, linux-amlogic, devicetree, linux-kernel,
linux-arm-kernel, Ronald Claveau
In-Reply-To: <20260424-add-thermal-t7-vim4-v5-0-9040ca36afe2@aliel.fr>
From: Ronald Claveau <linux-kernel-dev@aliel.fr>
Add thermal zones for all six sensors: a53, a73, gpu, nna, vpu, and hevc.
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Ronald Claveau <linux-kernel-dev@aliel.fr>
---
arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi | 179 ++++++++++++++++++++++++++++
1 file changed, 179 insertions(+)
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
index 62f259b2b17d2..c6ea0f20a879f 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
+++ b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
@@ -9,6 +9,7 @@
#include <dt-bindings/clock/amlogic,t7-scmi.h>
#include <dt-bindings/clock/amlogic,t7-pll-clkc.h>
#include <dt-bindings/clock/amlogic,t7-peripherals-clkc.h>
+#include <dt-bindings/thermal/thermal.h>
/ {
interrupt-parent = <&gic>;
@@ -829,6 +830,184 @@ hevc_tsensor: temperature-sensor@9a000 {
amlogic,secure-monitor = <&sm 5>;
};
};
+ };
+
+ thermal-zones {
+ a53_thermal: a53-thermal {
+ polling-delay = <1000>;
+ polling-delay-passive = <100>;
+ thermal-sensors = <&a53_tsensor>;
+
+ trips {
+ a53_passive: a53-passive {
+ temperature = <85000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ };
+
+ a53_hot: a53-hot {
+ temperature = <95000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "hot";
+ };
+
+ a53_critical: a53-critical {
+ temperature = <110000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "critical";
+ };
+ };
+
+ cooling-maps {
+ map-a53 {
+ trip = <&a53_passive>;
+ cooling-device =
+ <&cpu100 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu101 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu102 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu103 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+ };
+ };
+ };
+
+ a73_thermal: a73-thermal {
+ polling-delay = <1000>;
+ polling-delay-passive = <100>;
+ thermal-sensors = <&a73_tsensor>;
+
+ trips {
+ a73_passive: a73-passive {
+ temperature = <85000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ };
+
+ a73_hot: a73-hot {
+ temperature = <95000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "hot";
+ };
+
+ a73_critical: a73-critical {
+ temperature = <110000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "critical";
+ };
+ };
+
+ cooling-maps {
+ map-a73 {
+ trip = <&a73_passive>;
+ cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+ };
+ };
+ };
+
+ gpu_thermal: gpu-thermal {
+ polling-delay = <1000>;
+ polling-delay-passive = <100>;
+ thermal-sensors = <&gpu_tsensor>;
+
+ trips {
+ gpu_passive: gpu-passive {
+ temperature = <95000>;
+ hysteresis = <5000>;
+ type = "passive";
+ };
+
+ gpu_hot: gpu-hot {
+ temperature = <105000>;
+ hysteresis = <5000>;
+ type = "passive";
+ };
+ gpu_critical: gpu-critical {
+ temperature = <115000>;
+ hysteresis = <1000>;
+ type = "critical";
+ };
+ };
+ };
+
+ hevc_thermal: hevc-thermal {
+ polling-delay = <1000>;
+ polling-delay-passive = <100>;
+ thermal-sensors = <&hevc_tsensor>;
+
+ trips {
+ hevc_passive: hevc-passive {
+ temperature = <95000>;
+ hysteresis = <5000>;
+ type = "passive";
+ };
+
+ hevc_hot: hevc-hot {
+ temperature = <105000>;
+ hysteresis = <5000>;
+ type = "passive";
+ };
+
+ hevc_critical: hevc-critical {
+ temperature = <115000>;
+ hysteresis = <1000>;
+ type = "critical";
+ };
+ };
+ };
+
+ nna_thermal: nna-thermal {
+ polling-delay = <1000>;
+ polling-delay-passive = <100>;
+ thermal-sensors = <&nna_tsensor>;
+
+ trips {
+ nna_passive: nna-passive {
+ temperature = <95000>;
+ hysteresis = <5000>;
+ type = "passive";
+ };
+
+ nna_hot: nna-hot {
+ temperature = <105000>;
+ hysteresis = <5000>;
+ type = "passive";
+ };
+
+ nna_critical: nna-critical {
+ temperature = <115000>;
+ hysteresis = <1000>;
+ type = "critical";
+ };
+ };
+ };
+
+ vpu_thermal: vpu-thermal {
+ polling-delay = <1000>;
+ polling-delay-passive = <100>;
+ thermal-sensors = <&vpu_tsensor>;
+
+ trips {
+ vpu_passive: vpu-passive {
+ temperature = <95000>;
+ hysteresis = <5000>;
+ type = "passive";
+ };
+
+ vpu_hot: vpu-hot {
+ temperature = <105000>;
+ hysteresis = <5000>;
+ type = "passive";
+ };
+
+ vpu_critical: vpu-critical {
+ temperature = <115000>;
+ hysteresis = <1000>;
+ type = "critical";
+ };
+ };
+ };
};
};
--
2.49.0
^ permalink raw reply related
* [PATCH v5 1/8] dt-bindings: thermal: amlogic: Add support for T7
From: Ronald Claveau via B4 Relay @ 2026-04-24 15:45 UTC (permalink / raw)
To: Guillaume La Roque, Rafael J. Wysocki, Daniel Lezcano, Zhang Rui,
Lukasz Luba, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Neil Armstrong, Kevin Hilman, Jerome Brunet, Martin Blumenstingl
Cc: linux-pm, linux-amlogic, devicetree, linux-kernel,
linux-arm-kernel, Ronald Claveau, Conor Dooley
In-Reply-To: <20260424-add-thermal-t7-vim4-v5-0-9040ca36afe2@aliel.fr>
From: Ronald Claveau <linux-kernel-dev@aliel.fr>
Add the amlogic,t7-thermal compatible for the Amlogic T7 thermal sensor.
Unlike existing variants which use a phandle to the ao-secure syscon,
the T7 relies on a secure monitor interface described by a phandle and
a sensor index argument.
The T7 integrates multiple thermal sensors, all accessed through the
same SMC call. The sensor index argument is required to identify which
sensor's calibration data the secure monitor should return, as a single
SM_THERMAL_CALIB_READ command serves all of them.
Introduce the amlogic,secure-monitor property as a phandle-array and
make amlogic,ao-secure or amlogic,secure-monitor conditionally required
depending on the compatible.
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Ronald Claveau <linux-kernel-dev@aliel.fr>
---
.../bindings/thermal/amlogic,thermal.yaml | 37 ++++++++++++++++++++--
1 file changed, 35 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml b/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml
index 70b273271754b..e28612510d679 100644
--- a/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml
+++ b/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml
@@ -21,7 +21,9 @@ properties:
- amlogic,g12a-cpu-thermal
- amlogic,g12a-ddr-thermal
- const: amlogic,g12a-thermal
- - const: amlogic,a1-cpu-thermal
+ - enum:
+ - amlogic,a1-cpu-thermal
+ - amlogic,t7-thermal
reg:
maxItems: 1
@@ -42,12 +44,34 @@ properties:
'#thermal-sensor-cells':
const: 0
+ amlogic,secure-monitor:
+ description: phandle to the secure monitor
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ items:
+ - items:
+ - description: phandle to the secure monitor
+ - description: sensor index to get specific calibration data
+
required:
- compatible
- reg
- interrupts
- clocks
- - amlogic,ao-secure
+
+allOf:
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - amlogic,a1-cpu-thermal
+ - amlogic,g12a-thermal
+ then:
+ required:
+ - amlogic,ao-secure
+ else:
+ required:
+ - amlogic,secure-monitor
unevaluatedProperties: false
@@ -62,4 +86,13 @@ examples:
#thermal-sensor-cells = <0>;
amlogic,ao-secure = <&sec_AO>;
};
+ - |
+ temperature-sensor@20000 {
+ compatible = "amlogic,t7-thermal";
+ reg = <0x0 0x20000 0x0 0x50>;
+ interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc_periphs CLKID_TS>;
+ #thermal-sensor-cells = <0>;
+ amlogic,secure-monitor = <&sm 1>;
+ };
...
--
2.49.0
^ permalink raw reply related
* [PATCH v5 5/8] arm64: dts: amlogic: t7: Add cooling cells to all CPUs
From: Ronald Claveau via B4 Relay @ 2026-04-24 15:45 UTC (permalink / raw)
To: Guillaume La Roque, Rafael J. Wysocki, Daniel Lezcano, Zhang Rui,
Lukasz Luba, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Neil Armstrong, Kevin Hilman, Jerome Brunet, Martin Blumenstingl
Cc: linux-pm, linux-amlogic, devicetree, linux-kernel,
linux-arm-kernel, Ronald Claveau
In-Reply-To: <20260424-add-thermal-t7-vim4-v5-0-9040ca36afe2@aliel.fr>
From: Ronald Claveau <linux-kernel-dev@aliel.fr>
Add #cooling-cells = <2> to all CPU nodes (both little and big cluster)
to allow them to be used as cooling devices in thermal zone mappings.
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Ronald Claveau <linux-kernel-dev@aliel.fr>
---
arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
index 560c9dce35266..7aec65f036a9c 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
+++ b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
@@ -63,6 +63,7 @@ cpu100: cpu@100 {
i-cache-size = <0x8000>;
i-cache-sets = <32>;
next-level-cache = <&l2_cache_l>;
+ #cooling-cells = <2>;
};
cpu101: cpu@101 {
@@ -77,6 +78,7 @@ cpu101: cpu@101 {
i-cache-size = <0x8000>;
i-cache-sets = <32>;
next-level-cache = <&l2_cache_l>;
+ #cooling-cells = <2>;
};
cpu102: cpu@102 {
@@ -91,6 +93,7 @@ cpu102: cpu@102 {
i-cache-size = <0x8000>;
i-cache-sets = <32>;
next-level-cache = <&l2_cache_l>;
+ #cooling-cells = <2>;
};
cpu103: cpu@103 {
@@ -105,6 +108,7 @@ cpu103: cpu@103 {
i-cache-size = <0x8000>;
i-cache-sets = <32>;
next-level-cache = <&l2_cache_l>;
+ #cooling-cells = <2>;
};
cpu0: cpu@0 {
@@ -119,6 +123,7 @@ cpu0: cpu@0 {
i-cache-size = <0x10000>;
i-cache-sets = <64>;
next-level-cache = <&l2_cache_b>;
+ #cooling-cells = <2>;
};
cpu1: cpu@1 {
@@ -133,6 +138,7 @@ cpu1: cpu@1 {
i-cache-size = <0x10000>;
i-cache-sets = <64>;
next-level-cache = <&l2_cache_b>;
+ #cooling-cells = <2>;
};
cpu2: cpu@2 {
@@ -147,6 +153,7 @@ cpu2: cpu@2 {
i-cache-size = <0x10000>;
i-cache-sets = <64>;
next-level-cache = <&l2_cache_b>;
+ #cooling-cells = <2>;
};
cpu3: cpu@3 {
@@ -161,6 +168,7 @@ cpu3: cpu@3 {
i-cache-size = <0x10000>;
i-cache-sets = <64>;
next-level-cache = <&l2_cache_b>;
+ #cooling-cells = <2>;
};
l2_cache_l: l2-cache-cluster0 {
--
2.49.0
^ permalink raw reply related
* [PATCH v5 4/8] thermal: amlogic: Add support for secure monitor calibration readout
From: Ronald Claveau via B4 Relay @ 2026-04-24 15:45 UTC (permalink / raw)
To: Guillaume La Roque, Rafael J. Wysocki, Daniel Lezcano, Zhang Rui,
Lukasz Luba, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Neil Armstrong, Kevin Hilman, Jerome Brunet, Martin Blumenstingl
Cc: linux-pm, linux-amlogic, devicetree, linux-kernel,
linux-arm-kernel, Ronald Claveau
In-Reply-To: <20260424-add-thermal-t7-vim4-v5-0-9040ca36afe2@aliel.fr>
From: Ronald Claveau <linux-kernel-dev@aliel.fr>
Some SoCs (e.g. T7) expose thermal calibration data through the secure
monitor rather than a directly accessible eFuse register. Add a use_sm
flag to amlogic_thermal_data to select this path, and retrieve the
firmware handle and tsensor_id from the "amlogic,secure-monitor" DT
phandle with one fixed argument.
Also introduce the amlogic,t7-thermal compatible using this new path.
While refactoring, fix a pre-existing bug where
amlogic_thermal_initialize() was called after
devm_thermal_of_zone_register(), causing the thermal framework to
read an uninitialized trim_info on zone registration.
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Ronald Claveau <linux-kernel-dev@aliel.fr>
---
drivers/thermal/amlogic_thermal.c | 112 ++++++++++++++++++++++++++++----------
1 file changed, 82 insertions(+), 30 deletions(-)
diff --git a/drivers/thermal/amlogic_thermal.c b/drivers/thermal/amlogic_thermal.c
index 5448d772db12a..a0b530624b60c 100644
--- a/drivers/thermal/amlogic_thermal.c
+++ b/drivers/thermal/amlogic_thermal.c
@@ -25,6 +25,7 @@
#include <linux/platform_device.h>
#include <linux/regmap.h>
#include <linux/thermal.h>
+#include <linux/firmware/meson/meson_sm.h>
#include "thermal_hwmon.h"
@@ -84,12 +85,14 @@ struct amlogic_thermal_soc_calib_data {
* @u_efuse_off: register offset to read fused calibration value
* @calibration_parameters: calibration parameters structure pointer
* @regmap_config: regmap config for the device
+ * @use_sm: read data from secure monitor instead of efuse
* This structure is required for configuration of amlogic thermal driver.
*/
struct amlogic_thermal_data {
int u_efuse_off;
const struct amlogic_thermal_soc_calib_data *calibration_parameters;
const struct regmap_config *regmap_config;
+ bool use_sm;
};
struct amlogic_thermal {
@@ -100,6 +103,8 @@ struct amlogic_thermal {
struct clk *clk;
struct thermal_zone_device *tzd;
u32 trim_info;
+ struct meson_sm_firmware *sm_fw;
+ u32 tsensor_id;
};
/*
@@ -133,26 +138,6 @@ static int amlogic_thermal_code_to_millicelsius(struct amlogic_thermal *pdata,
return temp;
}
-static int amlogic_thermal_initialize(struct amlogic_thermal *pdata)
-{
- int ret = 0;
- int ver;
-
- regmap_read(pdata->sec_ao_map, pdata->data->u_efuse_off,
- &pdata->trim_info);
-
- ver = TSENSOR_TRIM_VERSION(pdata->trim_info);
-
- if ((ver & TSENSOR_TRIM_CALIB_VALID_MASK) == 0) {
- ret = -EINVAL;
- dev_err(&pdata->pdev->dev,
- "tsensor thermal calibration not supported: 0x%x!\n",
- ver);
- }
-
- return ret;
-}
-
static int amlogic_thermal_enable(struct amlogic_thermal *data)
{
int ret;
@@ -190,6 +175,67 @@ static int amlogic_thermal_get_temp(struct thermal_zone_device *tz, int *temp)
return 0;
}
+static int amlogic_thermal_probe_sm(struct platform_device *pdev,
+ struct amlogic_thermal *pdata)
+{
+ struct device *dev = &pdev->dev;
+ struct of_phandle_args ph_args;
+ int ret;
+
+ ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node,
+ "amlogic,secure-monitor",
+ 1, 0, &ph_args);
+ if (ret)
+ return ret;
+
+ if (!ph_args.np) {
+ dev_err(dev, "Failed to parse secure monitor phandle\n");
+ return -ENODEV;
+ }
+
+ pdata->sm_fw = meson_sm_get(ph_args.np);
+ of_node_put(ph_args.np);
+ if (!pdata->sm_fw) {
+ dev_err(dev, "Failed to get secure monitor firmware\n");
+ return -EPROBE_DEFER;
+ }
+
+ pdata->tsensor_id = ph_args.args[0];
+
+ return meson_sm_get_thermal_calib(pdata->sm_fw,
+ &pdata->trim_info,
+ pdata->tsensor_id);
+}
+
+static int amlogic_thermal_probe_syscon(struct platform_device *pdev,
+ struct amlogic_thermal *pdata)
+{
+ struct device *dev = &pdev->dev;
+ int ver;
+
+ pdata->sec_ao_map =
+ syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+ "amlogic,ao-secure");
+ if (IS_ERR(pdata->sec_ao_map)) {
+ dev_err(dev, "syscon regmap lookup failed.\n");
+ return PTR_ERR(pdata->sec_ao_map);
+ }
+
+ regmap_read(pdata->sec_ao_map, pdata->data->u_efuse_off,
+ &pdata->trim_info);
+
+ ver = TSENSOR_TRIM_VERSION(pdata->trim_info);
+
+ if ((ver & TSENSOR_TRIM_CALIB_VALID_MASK) == 0) {
+ dev_err(&pdata->pdev->dev,
+ "tsensor thermal calibration not supported: 0x%x!\n",
+ ver);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static const struct thermal_zone_device_ops amlogic_thermal_ops = {
.get_temp = amlogic_thermal_get_temp,
};
@@ -226,6 +272,12 @@ static const struct amlogic_thermal_data amlogic_thermal_a1_cpu_param = {
.regmap_config = &amlogic_thermal_regmap_config_g12a,
};
+static const struct amlogic_thermal_data amlogic_thermal_t7_param = {
+ .use_sm = true,
+ .calibration_parameters = &amlogic_thermal_g12a,
+ .regmap_config = &amlogic_thermal_regmap_config_g12a,
+};
+
static const struct of_device_id of_amlogic_thermal_match[] = {
{
.compatible = "amlogic,g12a-ddr-thermal",
@@ -239,6 +291,10 @@ static const struct of_device_id of_amlogic_thermal_match[] = {
.compatible = "amlogic,a1-cpu-thermal",
.data = &amlogic_thermal_a1_cpu_param,
},
+ {
+ .compatible = "amlogic,t7-thermal",
+ .data = &amlogic_thermal_t7_param,
+ },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, of_amlogic_thermal_match);
@@ -271,12 +327,12 @@ static int amlogic_thermal_probe(struct platform_device *pdev)
if (IS_ERR(pdata->clk))
return dev_err_probe(dev, PTR_ERR(pdata->clk), "failed to get clock\n");
- pdata->sec_ao_map = syscon_regmap_lookup_by_phandle
- (pdev->dev.of_node, "amlogic,ao-secure");
- if (IS_ERR(pdata->sec_ao_map)) {
- dev_err(dev, "syscon regmap lookup failed.\n");
- return PTR_ERR(pdata->sec_ao_map);
- }
+ if (pdata->data->use_sm)
+ ret = amlogic_thermal_probe_sm(pdev, pdata);
+ else
+ ret = amlogic_thermal_probe_syscon(pdev, pdata);
+ if (ret)
+ return ret;
pdata->tzd = devm_thermal_of_zone_register(&pdev->dev,
0,
@@ -290,10 +346,6 @@ static int amlogic_thermal_probe(struct platform_device *pdev)
devm_thermal_add_hwmon_sysfs(&pdev->dev, pdata->tzd);
- ret = amlogic_thermal_initialize(pdata);
- if (ret)
- return ret;
-
ret = amlogic_thermal_enable(pdata);
return ret;
--
2.49.0
^ permalink raw reply related
* [PATCH v5 6/8] arm64: dts: amlogic: t7: Add thermal sensor nodes
From: Ronald Claveau via B4 Relay @ 2026-04-24 15:45 UTC (permalink / raw)
To: Guillaume La Roque, Rafael J. Wysocki, Daniel Lezcano, Zhang Rui,
Lukasz Luba, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Neil Armstrong, Kevin Hilman, Jerome Brunet, Martin Blumenstingl
Cc: linux-pm, linux-amlogic, devicetree, linux-kernel,
linux-arm-kernel, Ronald Claveau
In-Reply-To: <20260424-add-thermal-t7-vim4-v5-0-9040ca36afe2@aliel.fr>
From: Ronald Claveau <linux-kernel-dev@aliel.fr>
Add six temperature sensor nodes using the amlogic,t7-thermal compatible:
a73, a53, gpu, nna, vpu, and hevc. Each sensor retrieves its calibration
data from the secure monitor via the amlogic,secure-monitor phandle with
the corresponding tsensor_id argument.
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Ronald Claveau <linux-kernel-dev@aliel.fr>
---
arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi | 58 +++++++++++++++++++++++++++++
1 file changed, 58 insertions(+)
diff --git a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
index 7aec65f036a9c..62f259b2b17d2 100644
--- a/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
+++ b/arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi
@@ -656,6 +656,24 @@ sec_ao: ao-secure@10220 {
amlogic,has-chip-id;
};
+ a73_tsensor: temperature-sensor@20000 {
+ compatible = "amlogic,t7-thermal";
+ reg = <0x0 0x20000 0x0 0x50>;
+ interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc_periphs CLKID_TS>;
+ #thermal-sensor-cells = <0>;
+ amlogic,secure-monitor = <&sm 1>;
+ };
+
+ a53_tsensor: temperature-sensor@22000 {
+ compatible = "amlogic,t7-thermal";
+ reg = <0x0 0x22000 0x0 0x50>;
+ interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc_periphs CLKID_TS>;
+ #thermal-sensor-cells = <0>;
+ amlogic,secure-monitor = <&sm 2>;
+ };
+
pwm_ao_ef: pwm@30000 {
compatible = "amlogic,t7-pwm", "amlogic,meson-s4-pwm";
reg = <0x0 0x30000 0x0 0x24>;
@@ -770,6 +788,46 @@ sd_emmc_c: mmc@8c000 {
assigned-clock-parents = <&xtal>;
status = "disabled";
};
+
+ gpu_tsensor: temperature-sensor@94000 {
+ compatible = "amlogic,t7-thermal";
+ reg = <0x0 0x94000 0x0 0x50>;
+ interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc_periphs CLKID_TS>;
+ power-domains = <&pwrc PWRC_T7_MALI_TOP_ID>;
+ #thermal-sensor-cells = <0>;
+ amlogic,secure-monitor = <&sm 3>;
+ };
+
+ nna_tsensor: temperature-sensor@96000 {
+ compatible = "amlogic,t7-thermal";
+ reg = <0x0 0x96000 0x0 0x50>;
+ interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc_periphs CLKID_TS>;
+ power-domains = <&pwrc PWRC_T7_NNA_TOP_ID>;
+ #thermal-sensor-cells = <0>;
+ amlogic,secure-monitor = <&sm 4>;
+ };
+
+ vpu_tsensor: temperature-sensor@98000 {
+ compatible = "amlogic,t7-thermal";
+ reg = <0x0 0x98000 0x0 0x50>;
+ interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc_periphs CLKID_TS>;
+ power-domains = <&pwrc PWRC_T7_VPU_HDMI_ID>;
+ #thermal-sensor-cells = <0>;
+ amlogic,secure-monitor = <&sm 6>;
+ };
+
+ hevc_tsensor: temperature-sensor@9a000 {
+ compatible = "amlogic,t7-thermal";
+ reg = <0x0 0x9a000 0x0 0x50>;
+ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc_periphs CLKID_TS>;
+ power-domains = <&pwrc PWRC_T7_DOS_HEVC_ID>;
+ #thermal-sensor-cells = <0>;
+ amlogic,secure-monitor = <&sm 5>;
+ };
};
};
--
2.49.0
^ permalink raw reply related
* [PATCH v5 0/8] arm64: amlogic: T7 thermal support
From: Ronald Claveau via B4 Relay @ 2026-04-24 15:45 UTC (permalink / raw)
To: Guillaume La Roque, Rafael J. Wysocki, Daniel Lezcano, Zhang Rui,
Lukasz Luba, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Neil Armstrong, Kevin Hilman, Jerome Brunet, Martin Blumenstingl
Cc: linux-pm, linux-amlogic, devicetree, linux-kernel,
linux-arm-kernel, Ronald Claveau, Conor Dooley
This series adds thermal monitoring support for the Amlogic T7 SoC,
used on the Khadas VIM4 board.
The T7 exposes six thermal sensors (a53, a73, gpu, nna, vpu, hevc),
each accessible through the secure monitor firmware interface rather
than a directly mapped eFuse register as on older SoCs.
The series is organized as follows:
- Patch 1 extends the amlogic,t7-thermal DT binding to describe the
new amlogic,secure-monitor property.
- Patches 2-3 extend the Meson secure monitor driver to expose a
thermal calibration read command (SMC ID 0x82000047).
- Patch 4 adds the secure monitor readout path to the amlogic thermal
driver and introduces the amlogic,t7-thermal compatible.
- Patches 5-7 wire up the T7 DTSI with CPU cooling cells, sensor
nodes, and thermal zones.
- Patch 8 extends the Khadas VIM4 DTS to map all thermal zones to the
on-board MCU fan controller (states 30–100, corresponding to the
FAN_CTRL register range 0x1E–0x64).
Signed-off-by: Ronald Claveau <linux-kernel-dev@aliel.fr>
---
Changes in v5:
- PATCH 4: Remove unnecessary variable and coding style alignment
according to Neil's feedback.
- Link to v4: https://lore.kernel.org/r/20260423-add-thermal-t7-vim4-v4-0-d4c1528d5044@aliel.fr
Changes in v4:
- PATCH 4: Extract SM and syscon setup into amlogic_thermal_probe_sm() and
amlogic_thermal_probe_syscon() removing amlogic_thermal_initialize()
from Daniel's feedback.
Also fix pre-existing bug: move calibration readout before
devm_thermal_of_zone_register() to avoid reading uninitialized
trim_info, according to Daniel's feedback.
- Link to v3: https://lore.kernel.org/r/20260421-add-thermal-t7-vim4-v3-0-a2e7215ed003@aliel.fr
Changes in v3:
- PATCH 1: Replace second if check by an else statement.
Remove unnecessary label in example according to Conor's feedback
- Link to v2: https://lore.kernel.org/r/20260413-add-thermal-t7-vim4-v2-0-1002d90a0602@aliel.fr
Changes in v2:
- PATCH 1: change two const entries to enum, explain why sensor index is needed
reorder conditional compatible for required, and fallback only according to
Krzysztof's feedback.
- PATCH 3: Add kerneldoc for meson_sm_get_thermal_calib exported function
according to Krzysztof's feedback.
- Link to v1: https://lore.kernel.org/r/20260410-add-thermal-t7-vim4-v1-0-19f2b8da74d7@aliel.fr
---
Ronald Claveau (8):
dt-bindings: thermal: amlogic: Add support for T7
firmware: meson: sm: Thermal calibration read via secure monitor
firmware: meson: sm: Add thermal calibration SMC call
thermal: amlogic: Add support for secure monitor calibration readout
arm64: dts: amlogic: t7: Add cooling cells to all CPUs
arm64: dts: amlogic: t7: Add thermal sensor nodes
arm64: dts: amlogic: t7: Add thermal zones
arm64: dts: amlogic: t7: khadas-vim4: Add fan cooling to thermal zones
.../bindings/thermal/amlogic,thermal.yaml | 37 +++-
.../dts/amlogic/amlogic-t7-a311d2-khadas-vim4.dts | 102 +++++++++
arch/arm64/boot/dts/amlogic/amlogic-t7.dtsi | 245 +++++++++++++++++++++
drivers/firmware/meson/meson_sm.c | 29 ++-
drivers/thermal/amlogic_thermal.c | 112 +++++++---
include/linux/firmware/meson/meson_sm.h | 3 +
6 files changed, 491 insertions(+), 37 deletions(-)
---
base-commit: f7b64ed948718290209074a50bb0df17e5944873
change-id: 20260410-add-thermal-t7-vim4-00e571badcc1
prerequisite-message-id: <20260326092645.1053261-1-jian.hu@amlogic.com>
prerequisite-patch-id: f03a086b4137158412b2d47b3de793b858de8dde
prerequisite-patch-id: 123970c9b29c2090440f2fd71c85d3c6fd8e36de
prerequisite-patch-id: 3e2e56b0926ba327b520f935df4ced5089bbe503
prerequisite-patch-id: 65a5d76ffdbc9b3aab3385bb65cb027004c30e7e
prerequisite-patch-id: 237269801826dd3ad7fb16eb4d7d6d4eab504278
prerequisite-patch-id: 57e9b08a968aedf543d3d0d56cf1ca4db20b2a16
prerequisite-change-id: 20260326-add-bcm43752-compatible-e264a4f7973a:v2
prerequisite-patch-id: cd98b74fa56af72af2553f391c400981d83cd4f4
prerequisite-patch-id: b730f5e42be1d89d193e63a0265495cdbf2c7d7b
prerequisite-change-id: 20260330-fix-invalid-property-bbe54d933f71:v2
prerequisite-patch-id: 8d675e7a239985c762843515b241f0a2f45f9c92
prerequisite-change-id: 20260331-fix-aml-t7-null-reset-2b608ebf9da4:v1
prerequisite-patch-id: 5b5de77af11747ce964404fb827d2ee2bff47ea5
prerequisite-patch-id: 1e37fc75fed1e533adee0f3e7e6ead1f8ff3c55c
prerequisite-patch-id: 65a5d76ffdbc9b3aab3385bb65cb027004c30e7e
prerequisite-patch-id: 2daf583fb5e7449a02bd217d8aca330171b598aa
prerequisite-patch-id: 237269801826dd3ad7fb16eb4d7d6d4eab504278
prerequisite-patch-id: d1ddf9b7710e91f8062de83bd7ba55afb2c4c112
prerequisite-patch-id: 57e9b08a968aedf543d3d0d56cf1ca4db20b2a16
prerequisite-patch-id: cd98b74fa56af72af2553f391c400981d83cd4f4
prerequisite-patch-id: b730f5e42be1d89d193e63a0265495cdbf2c7d7b
prerequisite-patch-id: 9debd88fa60febed9cd7208f86603b4c2d270520
prerequisite-patch-id: 314ef9ff0c4d1d15dab1dea9d92aa065f1eac3e9
prerequisite-change-id: 20260402-add-mcu-fan-khadas-vim4-ac1cbe553c9b:v5
prerequisite-patch-id: f03a086b4137158412b2d47b3de793b858de8dde
prerequisite-patch-id: 123970c9b29c2090440f2fd71c85d3c6fd8e36de
prerequisite-patch-id: 3e2e56b0926ba327b520f935df4ced5089bbe503
prerequisite-patch-id: 65a5d76ffdbc9b3aab3385bb65cb027004c30e7e
prerequisite-patch-id: 237269801826dd3ad7fb16eb4d7d6d4eab504278
prerequisite-patch-id: 57e9b08a968aedf543d3d0d56cf1ca4db20b2a16
prerequisite-patch-id: cd98b74fa56af72af2553f391c400981d83cd4f4
prerequisite-patch-id: b730f5e42be1d89d193e63a0265495cdbf2c7d7b
prerequisite-patch-id: 8d675e7a239985c762843515b241f0a2f45f9c92
prerequisite-patch-id: 9debd88fa60febed9cd7208f86603b4c2d270520
prerequisite-patch-id: 314ef9ff0c4d1d15dab1dea9d92aa065f1eac3e9
prerequisite-patch-id: e6a1b58b91a877504a12ae68bee71eb4e496c33b
prerequisite-patch-id: 406f88d7dabd3a870b358fb53c21686f29eb32b7
prerequisite-patch-id: d7a75ae3be0f54e0a7e81ccb0043a2f05423c9d0
prerequisite-patch-id: 5e19dc5ace12b532284246f5c2ff3f214d8a9c4f
prerequisite-patch-id: 06e85862f502b682dac8a0932986d43f0bb82770
prerequisite-patch-id: 4809bbedf79f59e1abc52c17cffc0b1bbb43d365
prerequisite-patch-id: c050e8bac4b5491f6c7008a5ccb26f20fad38b46
prerequisite-patch-id: 30677db8fc57270787245103c0d5acf8791307b0
Best regards,
--
Ronald Claveau <linux-kernel-dev@aliel.fr>
^ permalink raw reply
* [PATCH v5 2/8] firmware: meson: sm: Thermal calibration read via secure monitor
From: Ronald Claveau via B4 Relay @ 2026-04-24 15:45 UTC (permalink / raw)
To: Guillaume La Roque, Rafael J. Wysocki, Daniel Lezcano, Zhang Rui,
Lukasz Luba, Rob Herring, Krzysztof Kozlowski, Conor Dooley,
Neil Armstrong, Kevin Hilman, Jerome Brunet, Martin Blumenstingl
Cc: linux-pm, linux-amlogic, devicetree, linux-kernel,
linux-arm-kernel, Ronald Claveau
In-Reply-To: <20260424-add-thermal-t7-vim4-v5-0-9040ca36afe2@aliel.fr>
From: Ronald Claveau <linux-kernel-dev@aliel.fr>
Add SM_THERMAL_CALIB_READ to the secure monitor command enum and
introduce meson_sm_get_thermal_calib() to allow drivers to retrieve
thermal sensor calibration data through the firmware interface.
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Ronald Claveau <linux-kernel-dev@aliel.fr>
---
include/linux/firmware/meson/meson_sm.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/include/linux/firmware/meson/meson_sm.h b/include/linux/firmware/meson/meson_sm.h
index 8eaf8922ab020..3ebc2bd9a9760 100644
--- a/include/linux/firmware/meson/meson_sm.h
+++ b/include/linux/firmware/meson/meson_sm.h
@@ -12,6 +12,7 @@ enum {
SM_EFUSE_WRITE,
SM_EFUSE_USER_MAX,
SM_GET_CHIP_ID,
+ SM_THERMAL_CALIB_READ,
SM_A1_PWRC_SET,
SM_A1_PWRC_GET,
};
@@ -27,5 +28,7 @@ int meson_sm_call_read(struct meson_sm_firmware *fw, void *buffer,
unsigned int bsize, unsigned int cmd_index, u32 arg0,
u32 arg1, u32 arg2, u32 arg3, u32 arg4);
struct meson_sm_firmware *meson_sm_get(struct device_node *firmware_node);
+int meson_sm_get_thermal_calib(struct meson_sm_firmware *fw, u32 *trim_info,
+ u32 tsensor_id);
#endif /* _MESON_SM_FW_H_ */
--
2.49.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox