Merge power management utilities and documentation updates for 6.3-rc1:

 - Modify some power management utilities to use the canonical ftrace
   path (Ross Zwisler).

 - Correct spelling problems for Documentation/power/ as reported by
   codespell (Randy Dunlap).

* pm-tools:
  PM: tools: use canonical ftrace path

* pm-docs:
  Documentation: power: correct spelling

Merge updates of the powercap framework, generic PM domains, Energy
Model and operating performance points for 6.3-rc1:

 - Fix possible name leak in powercap_register_zone() (Yang Yingliang).

 - Add Meteor Lake and Emerald Rapids support to the intel_rapl power
   capping driver (Zhang Rui).

 - Modify the idle_inject power capping facility to support 100% idle
   injection (Srinivas Pandruvada).

 - Fix large time windows handling in the intel_rapl power capping
   driver (Zhang Rui).

 - Fix memory leaks with using debugfs_lookup() in the generic PM
   domains and Energy Model code (Greg Kroah-Hartman).

 - Add missing 'cache-unified' property in example for kryo OPP bindings
   (Rob Herring).

 - Fix error checking in opp_migrate_dentry() (Qi Zheng).

 - Remove "select SRCU" (Paul E. McKenney).

 - Let qcom,opp-fuse-level be a 2-long array for qcom SoCs (Konrad
   Dybcio).

* powercap:
  powercap: intel_rapl: Fix handling for large time window
  powercap: idle_inject: Support 100% idle injection
  powercap: intel_rapl: add support for Emerald Rapids
  powercap: intel_rapl: add support for Meteor Lake
  powercap: fix possible name leak in powercap_register_zone()

* pm-domains:
  PM: domains: fix memory leak with using debugfs_lookup()

* pm-em:
  PM: EM: fix memory leak with using debugfs_lookup()

* pm-opp:
  OPP: fix error checking in opp_migrate_dentry()
  dt-bindings: opp: v2-qcom-level: Let qcom,opp-fuse-level be a 2-long array
  drivers/opp: Remove "select SRCU"
  dt-bindings: opp: opp-v2-kryo-cpu: Add missing 'cache-unified' property in example

Merge cpuidle updates, PM core updates and changes related to system
sleep handling for 6.3-rc1:

 - Make the TEO cpuidle governor check CPU utilization in order to refine
   idle state selection (Kajetan Puchalski).

 - Make Kconfig select the haltpoll cpuidle governor when the haltpoll
   cpuidle driver is selected and replace a default_idle() call in that
   driver with arch_cpu_idle() which allows MWAIT to be used (Li
   RongQing).

 - Add Emerald Rapids Xeon support to the intel_idle driver (Artem
   Bityutskiy).

 - Add ARCH_SUSPEND_POSSIBLE dependencies for ARMv4 cpuidle drivers to
   avoid randconfig build failures (Arnd Bergmann).

 - Make kobj_type structures used in the cpuidle sysfs interface
   constant (Thomas Weißschuh).

 - Make the cpuidle driver registration code update microsecond values
   of idle state parameters in accordance with their nanosecond values
   if they are provided (Rafael Wysocki).

 - Make the PSCI cpuidle driver prevent topology CPUs from being
   suspended on PREEMPT_RT (Krzysztof Kozlowski).

 - Document that pm_runtime_force_suspend() cannot be used with
   DPM_FLAG_SMART_SUSPEND (Richard Fitzgerald).

 - Add EXPORT macros for exporting PM functions from drivers (Richard
   Fitzgerald).

 - Drop "select SRCU" from system sleep Kconfig (Paul E. McKenney).

 - Remove /** from non-kernel-doc comments in hibernation code (Randy
   Dunlap).

* pm-cpuidle:
  cpuidle: psci: Do not suspend topology CPUs on PREEMPT_RT
  cpuidle: driver: Update microsecond values of state parameters as needed
  cpuidle: sysfs: make kobj_type structures constant
  cpuidle: add ARCH_SUSPEND_POSSIBLE dependencies
  intel_idle: add Emerald Rapids Xeon support
  cpuidle-haltpoll: Replace default_idle() with arch_cpu_idle()
  cpuidle-haltpoll: select haltpoll governor
  cpuidle: teo: Introduce util-awareness
  cpuidle: teo: Optionally skip polling states in teo_find_shallower_state()

* pm-core:
  PM: Add EXPORT macros for exporting PM functions
  PM: runtime: Document that force_suspend() is incompatible with SMART_SUSPEND

* pm-sleep:
  PM: sleep: Remove "select SRCU"
  PM: hibernate: swap: don't use /** for non-kernel-doc comments

kernel test robot reported htmldocs warning:

Documentation/admin-guide/pm/amd-pstate.rst:343: WARNING: duplicate label admin-guide/pm/amd-pstate:user space interface in ``sysfs``, other instance in Documentation/admin-guide/pm/amd-pstate.rst

The documentation contains two sections with the same "User Space Interface
in ``sysfs``" title. The first one deals with per-policy sysfs and the
second one is about general attributes (currently only global attributes
are documented).

Disambiguate title text of both sections to fix the warning.

Link: https://lore.kernel.org/linux-doc/202302151041.0SWs1RHK-lkp@intel.com/
Fixes: b9e6a2d4 ("Documentation: amd-pstate: introduce new global sysfs attributes")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Wyes Karny <wyes.karny@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

`amd_pstate_set_epp` function uses `cppc_req_cached` and `epp` variable
to update the MSR_AMD_CPPC_REQ register for AMD MSR systems. The recent
commit 7cca9a98 ("cpufreq: amd-pstate: avoid uninitialized variable
use") changed the sequence of updating cppc_req_cached and writing the
MSR_AMD_CPPC_REQ. Therefore while switching from powersave to
performance governor and vice-versa in active mode MSR_AMD_CPPC_REQ is
set with the previous cached value. To fix this: first update the
`cppc_req_cached` variable and then call `amd_pstate_set_epp` function.

 - Before commit 7cca9a98 ("cpufreq: amd-pstate: avoid uninitialized
   variable use"):

With powersave governor:
[    1.652743] amd_pstate_epp_init: writing to cppc_req_cached = 0x1eff
[    1.652744] amd_pstate_set_epp: writing cppc_req_cached = 0x1eff
[    1.652746] amd_pstate_set_epp: writing min_perf = 30, des_perf = 0, max_perf = 255, epp = 0

Changing to performance governor:
[  300.493842] amd_pstate_epp_init: writing to cppc_req_cached = 0xffff
[  300.493846] amd_pstate_set_epp: writing cppc_req_cached = 0xffff
[  300.493847] amd_pstate_set_epp: writing min_perf = 255, des_perf = 0, max_perf = 255, epp = 0

 - After commit 7cca9a98 ("cpufreq: amd-pstate: avoid uninitialized
   variable use"):

With powersave governor:
[    1.646037] amd_pstate_set_epp: writing cppc_req_cached = 0xffff
[    1.646038] amd_pstate_set_epp: writing min_perf = 255, des_perf = 0, max_perf = 255, epp = 0
[    1.646042] amd_pstate_epp_init: writing to cppc_req_cached = 0x1eff

Changing to performance governor:
[  687.117401] amd_pstate_set_epp: writing cppc_req_cached = 0x1eff
[  687.117405] amd_pstate_set_epp: writing min_perf = 30, des_perf = 0, max_perf = 255, epp = 0
[  687.117419] amd_pstate_epp_init: writing to cppc_req_cached = 0xffff

 - After this fix:

With powersave governor:
[    2.525717] amd_pstate_epp_init: writing to cppc_req_cached = 0x1eff
[    2.525720] amd_pstate_set_epp: writing cppc_req_cached = 0x1eff
[    2.525722] amd_pstate_set_epp: writing min_perf = 30, des_perf = 0, max_perf = 255, epp = 0

Changing to performance governor:
[ 3440.152468] amd_pstate_epp_init: writing to cppc_req_cached = 0xffff
[ 3440.152473] amd_pstate_set_epp: writing cppc_req_cached = 0xffff
[ 3440.152474] amd_pstate_set_epp: writing min_perf = 255, des_perf = 0, max_perf = 255, epp = 0

Fixes: 7cca9a98 ("cpufreq: amd-pstate: avoid uninitialized variable use")
Signed-off-by: Wyes Karny <wyes.karny@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Pull OPP (Operating Performance Points) updates for 6.3 from Viresh
Kumar:

"- Add missing 'cache-unified' property in example for kryo OPP bindings
   (Rob Herring).

 - Fix error checking in opp_migrate_dentry() (Qi Zheng).

 - Remove "select SRCU" (Paul E. McKenney).

 - Let qcom,opp-fuse-level be a 2-long array for qcom SoCs (Konrad
   Dybcio)."

* tag 'opp-updates-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
  OPP: fix error checking in opp_migrate_dentry()
  dt-bindings: opp: v2-qcom-level: Let qcom,opp-fuse-level be a 2-long array
  drivers/opp: Remove "select SRCU"
  dt-bindings: opp: opp-v2-kryo-cpu: Add missing 'cache-unified' property in example

Pull cpufreq ARM updates for 6.3 from Viresh Kumar:

"- Enable thermal cooling for Tegra194 (Yi-Wei Wang).

 - Register module device table and add missing compatibles for
   cpufreq-qcom-hw (Nícolas F. R. A. Prado, Abel Vesa and Luca Weiss).

 - Various dt binding updates for qcom-cpufreq-nvmem and opp-v2-kryo-cpu
   (Christian Marangi)."

* tag 'cpufreq-arm-updates-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
  dt-bindings: opp: opp-v2-kryo-cpu: enlarge opp-supported-hw maximum
  dt-bindings: cpufreq: qcom-cpufreq-nvmem: make cpr bindings optional
  dt-bindings: cpufreq: qcom-cpufreq-nvmem: specify supported opp tables
  dt-bindings: cpufreq: cpufreq-qcom-hw: Add SM8550 compatible
  dt-bindings: cpufreq: cpufreq-qcom-hw: Add missing compatibles
  cpufreq: mediatek-hw: Register to module device table
  cpufreq: tegra194: Enable CPUFREQ thermal cooling

of_device_get_match_data() may return NULL, so add a check to prevent
potential null pointer dereference.

Issue reported by Qualcomm's internal static analysis tool.

Fixes: 4f796170 ("cpufreq: qcom-hw: Move soc_data to struct qcom_cpufreq")
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Enlarge opp-supported-hw maximum value. In recent SoC we started
matching more bit and we currently match mask of 112. The old maximum of
7 was good for old SoC that didn't had complex id, but now this is
limiting and we need to enlarge it to support more variants.

Document all the various mask that can be used and limit them to only
reasonable values instead of using a generic maximum limit.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

The qcom-cpufreq-nvmem driver supports 2 kind of devices:
- pre-cpr that doesn't have power-domains and base everything on nvmem
  cells and multiple named microvolt bindings.
  Doesn't need required-opp binding in the opp nodes as they are only
  used for genpd based devices.
- cpr-based that require power-domain in the cpu nodes and use various
  source to decide the correct voltage and freq
  Require required-opp binding since they need to be linked to the
  related opp-level.

When the schema was introduced, it was wrongly set to always require these
binding but this is not the case for pre-cpr devices.

Make the power-domain and the required-opp optional and set them required
only for qcs404 based devices.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

Add additional info on what opp tables the defined devices in this schema
supports (operating-points-v2-kryo-cpu and operating-points-v2-qcom-level)
and reference them.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>

Add a pair of macros for exporting functions only if CONFIG_PM
is enabled.

The naming follows the style of the standard EXPORT_SYMBOL_*()
macros that they replace.

Sometimes a module wants to export PM functions directly to other
drivers, not a complete struct dev_pm_ops. A typical example is
where a core library exports the generic (shared) implementation
and calling code wraps one or more of these in custom code.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

The runtime Power Management of CPU topology is not compatible with
PREEMPT_RT:

 1. Core cpuidle path disables IRQs.
 2. Core cpuidle calls cpuidle-psci.
 3. cpuidle-psci in __psci_enter_domain_idle_state() calls
    pm_runtime_put_sync_suspend() and pm_runtime_get_sync() which use
    spinlocks (which are sleeping on PREEMPT_RT).

Deep sleep modes are not a priority of Realtime kernels because the
latencies might become unpredictable.  On the other hand the PSCI CPU
idle power domain is a parent of other devices and power domain
controllers, thus it cannot be simply skipped (e.g. on Qualcomm SM8250).

Disable the idle callbacks in cpuidle-psci and mark the domain as
always on.  This is a trade-off between making PREEMPT_RT working and
still having a proper power domain hierarchy in the system.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Adrien Thierry <athierry@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

The obsolete cpufreq driver was removed, drop the platform device
and data accordingly.

Link: https://lore.kernel.org/all/20230112135342.3927338-1-keguang.zhang@gmail.comSigned-off-by: Keguang Zhang <keguang.zhang@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

When setting the power limit time window, software updates the 'y' bits
and 'f' bits in the power limit register, and the value hardware takes
follows the formula below

	Time window = 2 ^ y * (1 + f / 4) * Time_Unit

When handling large time window input from userspace, using left
shifting breaks in two cases:

 1. when ilog2(value) is bigger than 31, in expression "1 << y", left
    shifting by more than 31 bits has undefined behavior. This breaks
    'y'. For example, on an Alderlake platform, "1 << 32" returns 1.

 2. when ilog2(value) equals 31, "1 << 31" returns negative value
    because '1' is recognized as signed int. And this breaks 'f'.

Given that 'y' has 5 bits and hardware can never take a value larger
than 31, fix the first problem by clamp the time window to the maximum
possible value that the hardware can take.

Fix the second problem by using unsigned bit left shift.

Note that hardware has its own maximum time window limitation, which
may be lower than the time window value retrieved from the power limit
register. When this happens, hardware clamps the input to its maximum
time window limitation. That is why a software clamp is preferred to
handle the problem on hand.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
[ rjw: Adjusted the comment added by this change ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

If the cpuidle driver provides the target residency and exit latency in
nanoseconds, the corresponding values in microseconds need to be set to
reflect the provided numbers in order for the sysfs interface to show
them correctly, so make __cpuidle_driver_init() do that.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>

Both Rich Felker and Yoshinori Sato haven't done any work on arch/sh
for a while. As I have been maintaining Debian's sh4 port since 2014,
I am interested to keep the architecture alive.
Signed-off-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Acked-by: Yoshinori Sato <ysato@users.sourceforge.jp>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Pull tracing fix from Steven Rostedt:
 "Fix showing of TASK_COMM_LEN instead of its value

  The TASK_COMM_LEN was converted from a macro into an enum so that BTF
  would have access to it. But this unfortunately caused TASK_COMM_LEN
  to display in the format fields of trace events, as they are created
  by the TRACE_EVENT() macro and such, macros convert to their values,
  where as enums do not.

  To handle this, instead of using the field itself to be display, save
  the value of the array size as another field in the trace_event_fields
  structure, and use that instead.

  Not only does this fix the issue, but also converts the other trace
  events that have this same problem (but were not breaking tooling).

  With this change, the original work around b3bc8547 ("tracing:
  Have TRACE_DEFINE_ENUM affect trace event types as well") could be
  reverted (but that should be done in the merge window)"

* tag 'trace-v6.2-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Fix TASK_COMM_LEN in trace event format file

Pull btrfs fixes from David Sterba:

 - one more fix for a tree-log 'write time corruption' report, update
   the last dir index directly and don't keep in the log context

 - do VFS-level inode lock around FIEMAP to prevent a deadlock with
   concurrent fsync, the extent-level lock is not sufficient

 - don't cache a single-device filesystem device to avoid cases when a
   loop device is reformatted and the entry gets stale

* tag 'for-6.2-rc7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: free device in btrfs_close_devices for a single device filesystem
  btrfs: lock the inode in shared mode before starting fiemap
  btrfs: simplify update of last_dir_index_offset when logging a directory

Pull USB fixes from Greg KH:
 "Here are 2 small USB driver fixes that resolve some reported
  regressions and one new device quirk. Specifically these are:

   - new quirk for Alcor Link AK9563 smartcard reader

   - revert of u_ether gadget change in 6.2-rc1 that caused problems

   - typec pin probe fix

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

* tag 'usb-6.2-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
  usb: core: add quirk for Alcor Link AK9563 smartcard reader
  usb: typec: altmodes/displayport: Fix probe pin assign check
  Revert "usb: gadget: u_ether: Do not make UDC parent of the net device"

Pull EFI fix from Ard Biesheuvel:
 "A fix from Darren to widen the SMBIOS match for detecting Ampere Altra
  machines with problematic firmware. In the mean time, we are working
  on a more precise check, but this is still work in progress"

* tag 'efi-fixes-for-v6.2-4' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi:
  arm64: efi: Force the use of SetVirtualAddressMap() on eMAG and Altra Max machines

Pull powerpc fixes from Michael Ellerman:

 - Fix interrupt exit race with security mitigation switching.

 - Don't select ARCH_WANTS_NO_INSTR until warnings are fixed.

 - Build fix for CONFIG_NUMA=n.

Thanks to Nicholas Piggin, Randy Dunlap, and Sachin Sant.

* tag 'powerpc-6.2-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/64s/interrupt: Fix interrupt exit race with security mitigation switch
  powerpc/kexec_file: fix implicit decl error
  powerpc: Don't select ARCH_WANTS_NO_INSTR

When we upgraded our kernel, we started seeing some page corruption like
the following consistently:

  BUG: Bad page state in process ganesha.nfsd  pfn:1304ca
  page:0000000022261c55 refcount:0 mapcount:-128 mapping:0000000000000000 index:0x0 pfn:0x1304ca
  flags: 0x17ffffc0000000()
  raw: 0017ffffc0000000 ffff8a513ffd4c98 ffffeee24b35ec08 0000000000000000
  raw: 0000000000000000 0000000000000001 00000000ffffff7f 0000000000000000
  page dumped because: nonzero mapcount
  CPU: 0 PID: 15567 Comm: ganesha.nfsd Kdump: loaded Tainted: P    B      O      5.10.158-1.nutanix.20221209.el7.x86_64 #1
  Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/05/2016
  Call Trace:
   dump_stack+0x74/0x96
   bad_page.cold+0x63/0x94
   check_new_page_bad+0x6d/0x80
   rmqueue+0x46e/0x970
   get_page_from_freelist+0xcb/0x3f0
   ? _cond_resched+0x19/0x40
   __alloc_pages_nodemask+0x164/0x300
   alloc_pages_current+0x87/0xf0
   skb_page_frag_refill+0x84/0x110
   ...

Sometimes, it would also show up as corruption in the free list pointer
and cause crashes.

After bisecting the issue, we found the issue started from commit
e320d301 ("mm/page_alloc.c: fix freeing non-compound pages"):

	if (put_page_testzero(page))
		free_the_page(page, order);
	else if (!PageHead(page))
		while (order-- > 0)
			free_the_page(page + (1 << order), order);

So the problem is the check PageHead is racy because at this point we
already dropped our reference to the page.  So even if we came in with
compound page, the page can already be freed and PageHead can return
false and we will end up freeing all the tail pages causing double free.

Fixes: e320d301 ("mm/page_alloc.c: fix freeing non-compound pages")
Link: https://lore.kernel.org/lkml/BYAPR02MB448855960A9656EEA81141FC94D99@BYAPR02MB4488.namprd02.prod.outlook.com/
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@vger.kernel.org
Signed-off-by: Chunwei Chen <david.chen@nutanix.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

After commit 3087c61e ("tools/testing/selftests/bpf: replace open-coded 16 with TASK_COMM_LEN"),
the content of the format file under
/sys/kernel/tracing/events/task/task_newtask was changed from
  field:char comm[16];    offset:12;    size:16;    signed:0;
to
  field:char comm[TASK_COMM_LEN];    offset:12;    size:16;    signed:0;

John reported that this change breaks older versions of perfetto.
Then Mathieu pointed out that this behavioral change was caused by the
use of __stringify(_len), which happens to work on macros, but not on enum
labels. And he also gave the suggestion on how to fix it:
  :One possible solution to make this more robust would be to extend
  :struct trace_event_fields with one more field that indicates the length
  :of an array as an actual integer, without storing it in its stringified
  :form in the type, and do the formatting in f_show where it belongs.

The result as follows after this change,
$ cat /sys/kernel/tracing/events/task/task_newtask/format
        field:char comm[16];    offset:12;      size:16;        signed:0;

Link: https://lore.kernel.org/lkml/Y+QaZtz55LIirsUO@google.com/
Link: https://lore.kernel.org/linux-trace-kernel/20230210155921.4610-1-laoar.shao@gmail.com/
Link: https://lore.kernel.org/linux-trace-kernel/20230212151303.12353-1-laoar.shao@gmail.com

Cc: stable@vger.kernel.org
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Kajetan Puchalski <kajetan.puchalski@arm.com>
CC: Qais Yousef <qyousef@layalina.io>
Fixes: 3087c61e ("tools/testing/selftests/bpf: replace open-coded 16 with TASK_COMM_LEN")
Reported-by: John Stultz <jstultz@google.com>
Debugged-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

Pull spi fixes from Mark Brown:
 "A couple of hopefully final fixes for spi: one driver specific fix for
  an issue with very large transfers and a fix for an issue with the
  locking fixes in spidev merged earlier this release cycle which was
  missed"

* tag 'spi-fix-v6.2-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi:
  spi: spidev: fix a recursive locking error
  spi: dw: Fix wrong FIFO level setting for long xfers

Pull x86 fixes from Ingo Molnar:
 "Fix a kprobes bug, plus add a new Intel model number to the upstream
  <asm/intel-family.h> header for drivers to use"

* tag 'x86-urgent-2023-02-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Add Lunar Lake M
  x86/kprobes: Fix 1 byte conditional jump target

Pull locking fix from Ingo Molnar:
 "Fix an rtmutex missed-wakeup bug"

* tag 'locking-urgent-2023-02-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  rtmutex: Ensure that the top waiter is always woken up

Pull cxl fixes from Dan Williams:
 "Two fixups for CXL (Compute Express Link) in presence of passthrough
  decoders.

  This primarily helps developers using the QEMU CXL emulation, but with
  the impending arrival of CXL switches these types of topologies will
  be of interest to end users.

   - Fix a crash when shutting down regions in the presence of
     passthrough decoders

   - Fix region creation to understand passthrough decoders instead of
     the narrower definition of passthrough ports"

* tag 'cxl-fixes-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl:
  cxl/region: Fix passthrough-decoder detection
  cxl/region: Fix null pointer dereference for resetting decoder

Pull libnvdimm fixes from Dan Williams:
 "A fix for an issue that could causes users to inadvertantly reserve
  too much capacity when debugging the KMSAN and persistent memory
  namespace, a lockdep fix, and a kernel-doc build warning:

   - Resolve the conflict between KMSAN and NVDIMM with respect to
     reserving pmem namespace / volume capacity for larger sizeof(struct
     page)

   - Fix a lockdep warning in the the NFIT code

   - Fix a kernel-doc build warning"

* tag 'libnvdimm-fixes-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  nvdimm: Support sizeof(struct page) > MAX_STRUCT_PAGE_SIZE
  ACPI: NFIT: fix a potential deadlock during NFIT teardown
  dax: super.c: fix kernel-doc bad line warning

Pull memblock revert from Mike Rapoport:
 "Revert 'mm: Always release pages to the buddy allocator in
  memblock_free_late()'

  The pages being freed by memblock_free_late() have already been
  initialized, but if they are in the deferred init range,
  __free_one_page() might access nearby uninitialized pages when trying
  to coalesce buddies, which will cause a crash.

  A proper fix will be more involved so revert this change for the time
  being"

* tag 'fixes-2023-02-11' of git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock:
  Revert "mm: Always release pages to the buddy allocator in memblock_free_late()."

Pull clk fixes from Stephen Boyd:
 "Two clk driver fixes

   - Use devm_kasprintf() to avoid overflows when forming clk names in
     the Microchip PolarFire driver

   - Fix the pretty broken Ingenic JZ4760 M/N/OD calculation to actually
     work and find proper divisors"

* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux:
  clk: ingenic: jz4760: Update M/N/OD calculation algorithm
  clk: microchip: mpfs-ccc: Use devm_kasprintf() for allocating formatted strings

Pull pin control fixes from Linus Walleij:
 "Some assorted pin control fixes, the most interesting will be the
  Intel patch fixing a classic problem: laptop touchpad IRQs...

   - Some pin drive register fixes in the Mediatek driver.

   - Return proper error code in the Aspeed driver, and revert and
     ill-advised force-disablement patch that needs to be reworked.

   - Fix AMD driver debug output.

   - Fix potential NULL dereference in the Single driver.

   - Fix a group definition error in the Qualcomm SM8450 LPASS driver.

   - Restore pins used in direct IRQ mode in the Intel driver (This
     fixes some laptop touchpads!)"

* tag 'pinctrl-v6.2-3' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl:
  pinctrl: intel: Restore the pins that used to be in Direct IRQ mode
  pinctrl: qcom: sm8450-lpass-lpi: correct swr_rx_data group
  pinctrl: aspeed: Revert "Force to disable the function's signal"
  pinctrl: single: fix potential NULL dereference
  pinctrl: amd: Fix debug output for debounce time
  pinctrl: aspeed: Fix confusing types in return value
  pinctrl: mediatek: Fix the drive register definition of some Pins

Pull PCI fixes from Bjorn Helgaas:

 - Move to a shared PCI git tree (Bjorn Helgaas)

 - Add Krzysztof Wilczyński as another PCI maintainer (Lorenzo
   Pieralisi)

 - Revert a couple ASPM patches to fix suspend/resume regressions (Bjorn
   Helgaas)

* tag 'pci-v6.2-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci:
  Revert "PCI/ASPM: Refactor L1 PM Substates Control Register programming"
  Revert "PCI/ASPM: Save L1 PM Substates Capability for suspend/resume"
  MAINTAINERS: Promote Krzysztof to PCI controller maintainer
  MAINTAINERS: Move to shared PCI tree

This reverts commit 5e85eba6.

Thomas Witt reported that 5e85eba6 ("PCI/ASPM: Refactor L1 PM Substates
Control Register programming") broke suspend/resume on a Tuxedo
Infinitybook S 14 v5, which seems to use a Clevo L140CU Mainboard.

The main symptom is:

  iwlwifi 0000:02:00.0: Unable to change power state from D3hot to D0, device inaccessible
  nvme 0000:03:00.0: Unable to change power state from D3hot to D0, device inaccessible

and the machine is only partially usable after resume.  It can't run dmesg
and can't do a clean reboot.  This happens on every suspend/resume cycle.

Revert 5e85eba6 until we can figure out the root cause.

Fixes: 5e85eba6 ("PCI/ASPM: Refactor L1 PM Substates Control Register programming")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216877Reported-by: Thomas Witt <kernel@witt.link>
Tested-by: Thomas Witt <kernel@witt.link>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org	# v6.1+
Cc: Vidya Sagar <vidyas@nvidia.com>

This reverts commit 4ff116d0.

Tasev Nikola and Mark Enriquez reported that resume from suspend was broken
in v6.1-rc1.  Tasev bisected to a47126ec ("PCI/PTM: Cache PTM
Capability offset"), but we can't figure out how that could be related.

Mark saw the same symptoms and bisected to 4ff116d0 ("PCI/ASPM: Save L1
PM Substates Capability for suspend/resume"), which does have a connection:
it restores L1 Substates configuration while ASPM L1 may be enabled:

  pci_restore_state
    pci_restore_aspm_l1ss_state
      aspm_program_l1ss
        pci_write_config_dword(PCI_L1SS_CTL1, ctl1)         # L1SS restore
    pci_restore_pcie_state
      pcie_capability_write_word(PCI_EXP_LNKCTL, cap[i++])  # L1 restore

which is a problem because PCIe r6.0, sec 5.5.4, requires that:

  If setting either or both of the enable bits for ASPM L1 PM
  Substates, both ports must be configured as described in this
  section while ASPM L1 is disabled.

Separately, Thomas Witt reported that 5e85eba6 ("PCI/ASPM: Refactor L1
PM Substates Control Register programming") broke suspend/resume, and it
depends on 4ff116d0.

Revert 4ff116d0 ("PCI/ASPM: Save L1 PM Substates Capability for
suspend/resume") to fix the resume issue and enable revert of 5e85eba6
to fix the issue Thomas reported.

Note that reverting 4ff116d0 means L1 Substates config may be lost on
suspend/resume.  As far as we know the system will use more power but will
still *work* correctly.

Fixes: 4ff116d0 ("PCI/ASPM: Save L1 PM Substates Capability for suspend/resume")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216782
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216877Reported-by: Tasev Nikola <tasev.stefanoska@skynet.be>
Reported-by: Mark Enriquez <enriquezmark36@gmail.com>
Reported-by: Thomas Witt <kernel@witt.link>
Tested-by: Mark Enriquez <enriquezmark36@gmail.com>
Tested-by: Thomas Witt <kernel@witt.link>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org	# v6.1+
Cc: Vidya Sagar <vidyas@nvidia.com>

Pull ARM SoC fixes from Arnd Bergmann:
 "All the changes this time are minor devicetree corrections, the
  majority being for 64-bit Rockchip SoC support. These are a couple of
  corrections for properties that are in violation of the binding, some
  that put the machine into safer operating points for the eMMC and
  thermal settings, and missing properties that prevented rk356x PCIe
  and ethernet from working correctly.

  The changes for amlogic and mediatek address incorrect properties that
  were preventing the display support on MT8195 and the MMC support on
  various Meson SoCs from working correctly.

  The stihxxx-b2120 change fixes the GPIO polarity for the DVB tuner to
  allow this to be used correctly after a futre driver change, though it
  has no effect on older kernels"

* tag 'soc-fixes-6.2-4' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc:
  arm64: dts: meson-gx: Make mmc host controller interrupts level-sensitive
  arm64: dts: meson-g12-common: Make mmc host controller interrupts level-sensitive
  arm64: dts: meson-axg: Make mmc host controller interrupts level-sensitive
  ARM: dts: stihxxx-b2120: fix polarity of reset line of tsin0 port
  arm64: dts: mediatek: mt8195: Fix vdosys* compatible strings
  arm64: dts: rockchip: align rk3399 DMC OPP table with bindings
  arm64: dts: rockchip: set sdmmc0 speed to sd-uhs-sdr50 on rock-3a
  arm64: dts: rockchip: fix probe of analog sound card on rock-3a
  arm64: dts: rockchip: add missing #interrupt-cells to rk356x pcie2x1
  arm64: dts: rockchip: fix input enable pinconf on rk3399
  ARM: dts: rockchip: add power-domains property to dp node on rk3288
  arm64: dts: rockchip: add io domain setting to rk3566-box-demo
  arm64: dts: rockchip: remove unsupported property from sdmmc2 for rock-3a
  arm64: dts: rockchip: drop unused LED mode property from rk3328-roc-cc
  arm64: dts: rockchip: reduce thermal limits on rk3399-pinephone-pro
  arm64: dts: rockchip: use correct reset names for rk3399 crypto nodes

Pull RISC-V fixes from Palmer Dabbelt:
 "This is a little bigger that I'd hope for this late in the cycle, but
  they're all pretty concrete fixes and the only one that's bigger than
  a few lines is pmdp_collapse_flush() (which is almost all
  boilerplate/comment). It's also all bug fixes for issues that have
  been around for a while.

  So I think it's not all that scary, just bad timing.

   - avoid partial TLB fences for huge pages, which are disallowed by
     the ISA

   - avoid missing a frame when dumping stacks

   - avoid misaligned accesses (and possibly overflows) in kprobes

   - fix a race condition in tracking page dirtiness"

* tag 'riscv-for-linus-6.2-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: Fixup race condition on PG_dcache_clean in flush_icache_pte
  riscv: kprobe: Fixup misaligned load text
  riscv: stacktrace: Fix missing the first frame
  riscv: mm: Implement pmdp_collapse_flush for THP

Pull ceph fix from Ilya Dryomov:
 "A fix for a pretty embarrassing omission in the session flush handler
  from Xiubo, marked for stable"

* tag 'ceph-for-6.2-rc8' of https://github.com/ceph/ceph-client:
  ceph: flush cap releases when the session is flushed