Prototype for allowing a user-provided list of isolated nodes to get
around the issue with r0/r1. Ugly and quite possibly fragile since I
don't really know what I'm doing with the module parameter parsing...

Not intended for general use.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>

Try to discover the DTC domain assignment with a "see where the
rollover goes" contrivance. It sort of works...

Signed-off-by: Robin Murphy <robin.murphy@arm.com>

Although since commit c5b15ddf ("perf/arm-cmn: Make cycle counts
less surprising") the dtc_cycles event now has the generally more useful
behaviour expected for bandwidth and frequency calculations, there are
still some potential niche uses for observing CMN's notion of "idle" via
DTC clock gating, at least on configurations with only one DTC domain.
Luckily things are now the right way round for the standard exclude_idle
attribute to seem a good enough fit, so we can wire that up.

This then allows fun tricks like getting a rough view of the level of
interconnect activity:

$ perf stat -r10 -a -earm_cmn_0/dtc_cycles/{,I} sleep 1

 Performance counter stats for 'system wide' (10 runs):

        1607593396      arm_cmn_0/dtc_cycles/        ( +-  0.01% )  (50.15%)
           9030986      arm_cmn_0/dtc_cycles/I       ( +- 15.08% )  (49.85%)

          1.005074 +- 0.000135 seconds time elapsed  ( +-  0.01% )

...seems like there's not much background traffic on this otherwise-idle
machine, and CMN-600's clock gating is doing a pretty good job!

Signed-off-by: Robin Murphy <robin.murphy@arm.com>

The r2p0 release of CMN S3 finally adds a visible indication of child
node isolation status, so we can support configurations with the feature
enabled. It also brings some functional PMU changes such that certain
events won't quite work properly as-is, but that's a job for another day.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>

CMN S3's DTM offset is different between r0px and r1p0, and it
turns out this was not a error in the earlier documentation, but
does actually exist in the design. Lovely.

Cc: stable@vger.kernel.org
Fixes: 0dc2f496 ("perf/arm-cmn: Support CMN S3")
Signed-off-by: Robin Murphy <robin.murphy@arm.com>

PMU drivers should set .suppress_bind_attrs so that userspace is denied
the opportunity to pull the driver out from underneath an in-use PMU
(with predictably unpleasant consequences). Somehow both the CMN and NI
drivers have managed to miss this; put that right.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>

Arnd reports that Clang's aggressive inlining of arm_cmn_discover() can
lead to stack frame size warnings, and while we could simply prevent
such inlining to hide the issue, it seems more productive to actually
heed the warning and do something about the overall stack footprint.
The xp_region array is already rather large, and CMN_MAX_XPS might only
grow larger in future, however it only serves as a convenience to save
repeating the first level's worth of register reads in the second pass
of discovery. There's no performance concern here, and it only takes a
small tweak to the flow to re-extract the offsets instead of stashing
them, so let's just do that and save several hundred bytes of stack.

Reported-by: Arnd Bergmann <arnd@kernel.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>

Although CMN-Skeena is mildly modified for the Morello hardware
architecture, it still identifies itself as CMN-600 r3p1. Since
there are also no documented changes to its PMU functionality,
we can make the PMU accessible via the standard CMN-600 binding.
In general, PMU registers are non-functional on CMN Fast Models,
so this is only meaningful for the real SDP hardware.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>

Deepak Pandey authored 6 years ago and Robin Murphy committed 4 months ago

The Arm N1SDP SoC suffers from some PCIe integration issues, most
prominently config space accesses to not existing BDFs being answered
with a bus abort, resulting in an SError.
To mitigate this, the firmware scans the bus before boot (catching the
SErrors) and creates a table with valid BDFs, which acts as a filter for
Linux' config space accesses.

Add code consulting the table as an ACPI PCIe quirk, also register the
corresponding device tree based description of the host controller.
Also fix the other two minor issues on the way, namely not being fully
ECAM compliant and config space accesses being restricted to 32-bit
accesses only.

This allows the Arm Neoverse N1SDP board to boot Linux without crashing
and to access *any* devices (there are no platform devices except UART).

Signed-off-by: Deepak Pandey <Deepak.Pandey@arm.com>
[Sudipto: extend to cover the CCIX root port as well]
Signed-off-by: Sudipto Paul <sudipto.paul@arm.com>
[Andre: fix coding style issues, rewrite some parts, add DT support]
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Change-Id: I1d3a4b9bf6b3b883d262e3c4ff1f88a0eb81c1fe
[rm: hack out problematic SR-IOV check]
Signed-off-by: Robin Murphy <robin.murphy@arm.com>

Pull turbostat updates from Len Brown:

 - Add initial DMR support, which required smarter RAPL probe

 - Fix AMD MSR RAPL energy reporting

 - Add RAPL power limit configuration output

 - Minor fixes

* tag 'turbostat-2025.06.08' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux:
  tools/power turbostat: version 2025.06.08
  tools/power turbostat: Add initial support for BartlettLake
  tools/power turbostat: Add initial support for DMR
  tools/power turbostat: Dump RAPL sysfs info
  tools/power turbostat: Avoid probing the same perf counters
  tools/power turbostat: Allow probing RAPL with platform_features->rapl_msrs cleared
  tools/power turbostat: Clean up add perf/msr counter logic
  tools/power turbostat: Introduce add_msr_counter()
  tools/power turbostat: Remove add_msr_perf_counter_()
  tools/power turbostat: Remove add_cstate_perf_counter_()
  tools/power turbostat: Remove add_rapl_perf_counter_()
  tools/power turbostat: Quit early for unsupported RAPL counters
  tools/power turbostat: Always check rapl_joules flag
  tools/power turbostat: Fix AMD package-energy reporting
  tools/power turbostat: Fix RAPL_GFX_ALL typo
  tools/power turbostat: Add Android support for MSR device handling
  tools/power turbostat.8: pm_domain wording fix
  tools/power turbostat.8: fix typo: idle_pct should be pct_idle

Pull timer cleanup from Thomas Gleixner:
 "The delayed from_timer() API cleanup:

  The renaming to the timer_*() namespace was delayed due massive
  conflicts against Linux-next. Now that everything is upstream finish
  the conversion"

* tag 'timers-cleanups-2025-06-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  treewide, timers: Rename from_timer() to timer_container_of()

Pull x86 fixes from Thomas Gleixner:
 "A small set of x86 fixes:

   - Cure IO bitmap inconsistencies

     A failed fork cleans up all resources of the newly created thread
     via exit_thread(). exit_thread() invokes io_bitmap_exit() which
     does the IO bitmap cleanups, which unfortunately assume that the
     cleanup is related to the current task, which is obviously bogus.

     Make it work correctly

   - A lockdep fix in the resctrl code removed the clearing of the
     command buffer in two places, which keeps stale error messages
     around. Bring them back.

   - Remove unused trace events"

* tag 'x86-urgent-2025-06-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  fs/resctrl: Restore the rdt_last_cmd_clear() calls after acquiring rdtgroup_mutex
  x86/iopl: Cure TIF_IO_BITMAP inconsistencies
  x86/fpu: Remove unused trace events

Pull timer fix from Thomas Gleixner:
 "Add the missing seq_file forward declaration in the timer namespace
  header"

* tag 'timers-urgent-2025-06-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timens: Add struct seq_file forward declaration

Add initial DMR support, which required smarter RAPL probe
Fix AMD MSR RAPL energy reporting
Add RAPL power limit configuration output
Minor fixes

Signed-off-by: Len Brown <len.brown@intel.com>

Add initial support for BartlettLake.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

Add initial support for DMR.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

for example:

intel-rapl:1: psys 28.0s:100W 976.0us:100W
intel-rapl:0: package-0 28.0s:57W,max:15W 2.4ms:57W
intel-rapl:0/intel-rapl:0:0: core disabled
intel-rapl:0/intel-rapl:0:1: uncore disabled
intel-rapl-mmio:0: package-0 28.0s:28W,max:15W 2.4ms:57W

[lenb: simplified format]

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

squish me

Signed-off-by: Len Brown <len.brown@intel.com>

For the RAPL package energy status counter, Intel and AMD share the same
perf_subsys and perf_name, but with different MSR addresses.

Both rapl_counter_arch_infos[0] and rapl_counter_arch_infos[1] are
introduced to describe this counter for different Vendors.

As a result, the perf counter is probed twice, and causes a failure in
in get_rapl_counters() because expected_read_size and actual_read_size
don't match.

Fix the problem by skipping the already probed counter.

Note, this is not a perfect fix. For example, if different
vendors/platforms use the same MSR value for different purpose, the code
can be fooled when it probes a rapl_counter_arch_infos[] entry that does
not belong to the running Vendor/Platform.

In a long run, better to put rapl_counter_arch_infos[] into the
platform_features so that this becomes Vendor/Platform specific.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

platform_features->rapl_msrs describes the RAPL MSRs supported. While
RAPL Perf counters can be exposed from different kernel backend drivers,
e.g. RAPL MSR I/F driver, or RAPL TPMI I/F driver.

Thus, turbostat should first blindly probe all the available RAPL Perf
counters, and falls back to the RAPL MSR counters if they are listed in
platform_features->rapl_msrs.

With this, platforms that don't have RAPL MSRs can clear the
platform_features->rapl_msrs bits and use RAPL Perf counters only.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

Increase the code readability by moving the no_perf/no_msr flag and the
cai->perf_name/cai->msr sanity checks into the counter probe functions.

No functional change.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

probe_rapl_msr() is reused for probing RAPL MSR counters, cstate MSR
counters and MPERF/APERF/SMI MSR counters, thus its name is misleading.

Similar to add_perf_counter(), introduce add_msr_counter() to probe a
counter via MSR. Introduce wrapper function add_rapl_msr_counter() at
the same time to add extra check for Zero return value for specified
RAPL counters.

No functional change intended.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

As the only caller of add_msr_perf_counter_(), add_msr_perf_counter()
just gives extra debug output on top. There is no need to keep both
functions.

Remove add_msr_perf_counter_() and move all the logic to
add_msr_perf_counter().

No functional change.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

As the only caller of add_cstate_perf_counter_(),
add_cstate_perf_counter() just gives extra debug output on top. There is
no need to keep both functions.

Remove add_cstate_perf_counter_() and move all the logic to
add_cstate_perf_counter().

No functional change.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

As the only caller of add_rapl_perf_counter_(), add_rapl_perf_counter()
just gives extra debug output on top. There is no need to keep both
functions.

Remove add_rapl_perf_counter_() and move all the logic to
add_rapl_perf_counter().

No functional change.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

Quit early for unsupported RAPL counters.

No functional change.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

rapl_joules bit should always be checked even if
platform_features->rapl_msrs is not set or no_msr flag is used.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

commit 05a2f07d ("tools/power turbostat: read RAPL counters via
perf") that adds support to read RAPL counters via perf defines the
notion of a RAPL domain_id which is set to physical_core_id on
platforms which support per_core_rapl counters (Eg: AMD processors
Family 17h onwards) and is set to the physical_package_id on all the
other platforms.

However, the physical_core_id is only unique within a package and on
platforms with multiple packages more than one core can have the same
physical_core_id and thus the same domain_id. (For eg, the first cores
of each package have the physical_core_id = 0). This results in all
these cores with the same physical_core_id using the same entry in the
rapl_counter_info_perdomain[]. Since rapl_perf_init() skips the
perf-initialization for cores whose domain_ids have already been
visited, cores that have the same physical_core_id always read the
perf file corresponding to the physical_core_id of the first package
and thus the package-energy is incorrectly reported to be the same
value for different packages.

Note: This issue only arises when RAPL counters are read via perf and
not when they are read via MSRs since in the latter case the MSRs are
read separately on each core.

Fix this issue by associating each CPU with rapl_core_id which is
unique across all the packages in the system.

Fixes: 05a2f07d ("tools/power turbostat: read RAPL counters via perf")
Signed-off-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Signed-off-by: Len Brown <len.brown@intel.com>

Fix typo in the currently unused RAPL_GFX_ALL macro definition.

Signed-off-by: Kaushlendra Kumar <kaushlendra.kumar@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

It uses /dev/msrN device paths on Android instead of /dev/cpu/N/msr,
updates error messages and permission checks to reflect the Android
device path, and wraps platform-specific code with #if defined(ANDROID)
to ensure correct behavior on both Android and non-Android systems.
These changes improve compatibility and usability of turbostat on
Android devices.

Signed-off-by: Kaushlendra Kumar <kaushlendra.kumar@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>

turbostat.8: clarify that uncore "domains" are Power Management domains,
aka pm_domains.

Signed-off-by: Len Brown <len.brown@intel.com>

idle_pct should be pct_idle

Signed-off-by: Len Brown <len.brown@intel.com>

Pull x86 perf fix from Thomas Gleixner:
 "A single fix for the x86 performance counters on Intel CPUs:

  The MSR offset calculations for fixed performance counters are stored
  at the wrong index in the configuration array causing the general
  purpose counter MSR offset to be overwritten, so both the general
  purpose and the fixed counters offsets are incorrect.

  Correct the array index calculation to fix that"

* tag 'perf-urgent-2025-06-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Fix incorrect MSR index calculations in intel_pmu_config_acr()

Pull irq fix from Thomas Gleixner:
 "A single fix for the PCI/MSI code:

  The conversion to per device MSI domains created a MSI domain with
  size 1 instead of sizing it to the maximum possible number of MSI
  interrupts for the device. This "worked" as the subsequent allocations
  resized the domain, but the recent change to move the prepare() call
  into the domain creation path broke this works by chance mechanism.

  Size the domain properly at creation time"

* tag 'irq-urgent-2025-06-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  PCI/MSI: Size device MSI domain with the maximum number of vectors

Pull mount fixes from Al Viro:
 "Various mount-related bugfixes:

   - split the do_move_mount() checks in subtree-of-our-ns and
     entire-anon cases and adapt detached mount propagation selftest for
     mount_setattr

   - allow clone_private_mount() for a path on real rootfs

   - fix a race in call of has_locked_children()

   - fix move_mount propagation graph breakage by MOVE_MOUNT_SET_GROUP

   - make sure clone_private_mnt() caller has CAP_SYS_ADMIN in the right
     userns

   - avoid false negatives in path_overmount()

   - don't leak MNT_LOCKED from parent to child in finish_automount()

   - do_change_type(): refuse to operate on unmounted/not ours mounts"

* tag 'pull-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  do_change_type(): refuse to operate on unmounted/not ours mounts
  clone_private_mnt(): make sure that caller has CAP_SYS_ADMIN in the right userns
  selftests/mount_setattr: adapt detached mount propagation test
  do_move_mount(): split the checks in subtree-of-our-ns and entire-anon cases
  fs: allow clone_private_mount() for a path on real rootfs
  fix propagation graph breakage by MOVE_MOUNT_SET_GROUP move_mount(2)
  finish_automount(): don't leak MNT_LOCKED from parent to child
  path_overmount(): avoid false negatives
  fs/fhandle.c: fix a race in call of has_locked_children()

Pull more smb client updates from Steve French:

 - multichannel/reconnect fixes

 - move smbdirect (smb over RDMA) defines to fs/smb/common so they will
   be able to be used in the future more broadly, and a documentation
   update explaining setting up smbdirect mounts

 - update email address for Paulo

* tag '6.16-rc-part2-smb3-client-fixes' of git://git.samba.org/sfrench/cifs-2.6:
  cifs: update internal version number
  MAINTAINERS, mailmap: Update Paulo Alcantara's email address
  cifs: add documentation for smbdirect setup
  cifs: do not disable interface polling on failure
  cifs: serialize other channels when query server interfaces is pending
  cifs: deal with the channel loading lag while picking channels
  smb: client: make use of common smbdirect_socket_parameters
  smb: smbdirect: introduce smbdirect_socket_parameters
  smb: client: make use of common smbdirect_socket
  smb: smbdirect: add smbdirect_socket.h
  smb: client: make use of common smbdirect.h
  smb: smbdirect: add smbdirect.h with public structures
  smb: client: make use of common smbdirect_pdu.h
  smb: smbdirect: add smbdirect_pdu.h with protocol definitions

Pull more tracing fixes from Steven Rostedt:

 - Fix regression of waiting a long time on updating trace event filters

   When the faultable trace points were added, it needed task trace RCU
   synchronization.

   This was added to the tracepoint_synchronize_unregister() function.
   The filter logic always called this function whenever it updated the
   trace event filters before freeing the old filters. This increased
   the time of "trace-cmd record" from taking 13 seconds to running over
   2 minutes to complete.

   Move the freeing of the filters to call_rcu*() logic, which brings
   the time back down to 13 seconds.

 - Fix ring_buffer_subbuf_order_set() error path lock protection

   The error path of the ring_buffer_subbuf_order_set() released the
   mutex too early and allowed subsequent accesses to setting the
   subbuffer size to corrupt the data and cause a bug.

   By moving the mutex locking to the end of the error path, it prevents
   the reentrant access to the critical data and also allows the
   function to convert the taking of the mutex over to the guard()
   logic.

 - Remove unused power management clock events

   The clock events were added in 2010 for power management. In 2011 arm
   used them. In 2013 the code they were used in was removed. These
   events have been wasting memory since then.

 - Fix sparse warnings

   There was a few places that sparse warned about trace_events_filter.c
   where file->filter was referenced directly, but it is annotated with
   an __rcu tag. Use the helper functions and fix them up to use
   rcu_dereference() properly.

* tag 'trace-v6.16-3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Add rcu annotation around file->filter accesses
  tracing: PM: Remove unused clock events
  ring-buffer: Fix buffer locking in ring_buffer_subbuf_order_set()
  tracing: Fix regression of filter waiting a long time on RCU synchronization

Move this API to the canonical timer_*() namespace.

[ tglx: Redone against pre rc1 ]

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/aB2X0jCKQO56WdMt@gmail.com

Pull Kbuild updates from Masahiro Yamada:

 - Add support for the EXPORT_SYMBOL_GPL_FOR_MODULES() macro, which
   exports a symbol only to specified modules

 - Improve ABI handling in gendwarfksyms

 - Forcibly link lib-y objects to vmlinux even if CONFIG_MODULES=n

 - Add checkers for redundant or missing <linux/export.h> inclusion

 - Deprecate the extra-y syntax

 - Fix a genksyms bug when including enum constants from *.symref files

* tag 'kbuild-v6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild: (28 commits)
  genksyms: Fix enum consts from a reference affecting new values
  arch: use always-$(KBUILD_BUILTIN) for vmlinux.lds
  kbuild: set y instead of 1 to KBUILD_{BUILTIN,MODULES}
  efi/libstub: use 'targets' instead of extra-y in Makefile
  module: make __mod_device_table__* symbols static
  scripts/misc-check: check unnecessary #include <linux/export.h> when W=1
  scripts/misc-check: check missing #include <linux/export.h> when W=1
  scripts/misc-check: add double-quotes to satisfy shellcheck
  kbuild: move W=1 check for scripts/misc-check to top-level Makefile
  scripts/tags.sh: allow to use alternative ctags implementation
  kconfig: introduce menu type enum
  docs: symbol-namespaces: fix reST warning with literal block
  kbuild: link lib-y objects to vmlinux forcibly even when CONFIG_MODULES=n
  tinyconfig: enable CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
  docs/core-api/symbol-namespaces: drop table of contents and section numbering
  modpost: check forbidden MODULE_IMPORT_NS("module:") at compile time
  kbuild: move kbuild syntax processing to scripts/Makefile.build
  Makefile: remove dependency on archscripts for header installation
  Documentation/kbuild: Add new gendwarfksyms kABI rules
  Documentation/kbuild: Drop section numbers
  ...

Pull sh updates from John Paul Adrian Glaubitz:

 - replace the __ASSEMBLY__ with __ASSEMBLER__ macro in all headers
   since the latter is now defined automatically by both GCC and Clang
   when compiling assembly code (Thomas Huth)

 - set the default SPI mode for the ecovec24 board which became
   necessary after a new mode member as added to the sh_msiof_spi_info
   struct in cf9e4784 ("spi: sh-msiof: Add slave mode support")
   (Geert Uytterhoeven)

 - remove unused variables in the kprobes code in
   kprobe_exceptions_notify() (Mike Rapoport)

* tag 'sh-for-v6.16-tag1' of git://git.kernel.org/pub/scm/linux/kernel/git/glaubitz/sh-linux:
  sh: kprobes: Remove unused variables in kprobe_exceptions_notify()
  sh: ecovec24: Make SPI mode explicit
  sh: Replace __ASSEMBLY__ with __ASSEMBLER__ in all headers