Since this field is only used by netfs_prepare_read_iterator() when
called by netfs_readahead(), we can simply pass it as parameter. This
shrinks the struct from 576 to 568 bytes.
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250519134813.2975312-8-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.com>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
This shrinks `struct netfs_io_stream` from 104 to 96 bytes and `struct
netfs_io_request` from 600 to 576 bytes.
[DH: Modified as the patch to turn netfs_io_request::error into a short
was removed from the set]
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250519134813.2975312-7-dhowells@redhat.com
cc: Paulo Alcantara <pc@manguebit.com>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
uaudio_transfer_buffer_setup() allocates a buffer for the subs->dev
device, and the returned address for the buffer is a CPU local virtual
address that may or may not be in the linear mapping, as well as a DMA
address token that is accessible by the USB device, and this in turn
may or may not correspond to the physical address.
The use in the driver however assumes that these addresses are the
linear map and the CPU physical address, respectively. Both are
nonportable here, but in the end only the virtual address gets
used by converting it to a physical address that gets mapped into
a second iommu.
Make this more explicit by pulling the conversion out first
and warning if it is not part of the linear map, and using the
actual physical address to map into the iommu in place of the
dma address that may already be iommu-mapped into the usb host.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20250513123442.159936-4-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The info->xfer_buf_cpu member is set to a NULL value because the
allocation happens in a different function and is only assigned
to the function argument but never passed back.
Pass it by reference instead to have a handle that can actually be
freed by the final usb_free_coherent() call.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20250513123442.159936-3-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
While trying to understand a bug in the audio offload code, I had
to spend extra time due to unfortunate nameing of local variables
and struct members.
Change these to more conventional names that reflect the actual
usage:
- pointers to the CPU virtual addresses of a dma buffer get a
_cpu suffix to disambiguate them for MMIO virtual addresses
- MMIO virtual addresses that are mapped explicitly through
the IOMMU get a _iova suffix consistently, rather than a
mix of iova and va.
- DMA addresses (dma_addr_t) that are in a device address
space (linear or IOMMU) get a _dma suffix in place of the
_pa suffix.
- CPU physical (phys_addr_t) addresses get a _pa suffix.
There is still a mixup with dma addresses here that I address
in another patch.
No functional changes are intended here.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20250513123442.159936-2-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If an error occurs after a successful qc_usb_audio_offload_init_qmi_dev()
call, qc_usb_audio_cleanup_qmi_dev() should be called to release some
resources as already done in the remove function.
Add the missing qc_usb_audio_cleanup_qmi_dev().
Fixes: 326bbc3482 ("ALSA: usb-audio: qcom: Introduce QC USB SND offloading support")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/335f54da099240d9b6c7aca0397c7d8c6bb629ac.1746785961.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This is a preparation patch for the introduction of CAN XL.
CAN FD and CAN XL uses similar bittiming parameters. Add one level of
nesting for all the CAN FD parameters. Typically:
priv->can.data_bittiming;
becomes:
priv->can.fd.data_bittiming;
This way, the CAN XL equivalent (to be introduced later) would be:
priv->can.xl.data_bittiming;
Add the new struct data_bittiming_params which contains all the data
bittiming parameters, including the TDC and the callback functions.
This done, update all the CAN FD drivers to make use of the new
layout.
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250501171213.2161572-2-mailhol.vincent@wanadoo.fr
[mkl: fix rcar_canfd]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Biju Das <biju.das.jz@bp.renesas.com> says:
The CAN-FD module on RZ/G3E is very similar to the one on both R-Car V4H
and RZ/G2L, but differs in some hardware parameters:
* No external clock, but instead has ram clock.
* Support up to 6 channels.
* 20 interrupts.
v8->v9:
* Collected tags.
* Added missing header bitfield.h.
* Fixed logical error ch->BIT(ch) in rcar_canfd_global_error().
* Removed unneeded double space in rcar_canfd_setrnc().
* Updated commit description in patch#15.
v7->v8:
* Collected tags.
* Updated commit description for patch#{5,9,15,16,17}.
* Replaced the macro RCANFD_GERFL_EEF0_7->RCANFD_GERFL_EEF.
* Dropped the redundant macro RCANFD_GERFL_EEF(ch).
* Added patch for dropping the mask operation in RCANFD_GAFLCFG_SETRNC
macro.
* Converted RCANFD_GAFLCFG_SETRNC->rcar_canfd_setrnc().
* Updated RCANFD_GAFLCFG macro by replacing the parameter ch->w, where w
is the GAFLCFG index used in the hardware manual.
* Renamed the parameter x->page_num in RCANFD_GAFLECTR_AFLPN macro to
make it clear.
* Renamed the parameter x->cftml in RCANFD_CFCC_CFTML macro to make it
clear.
* Updated {rzg2l,car_gen3_hw_info} with ch_interface_mode = 0.
* Updated {rzg2l,rcar_gen3}_hw_info with shared_can_regs = 0.
* Started using struct rcanfd_regs instead of LUT for reg offsets.
* Started using struct rcar_canfd_shift_data instead of LUT for shift
data.
* Renamed only_internal_clks->external_clk to avoid negation.
* Updated rcar_canfd_hw_info tables with external_clk entries.
* Replaced 10->sizeof(name) in scnprintf().
v6->v7:
* Collected tags
* Replaced 'aswell'->'as well' in patch#11 commit description.
v5->v6:
* Replaced RCANFD_RNC_PER_REG macro with rnc_stride variable.
* Updated commit description for patch#7 and #8
* Dropped mask_table:
AFLPN_MASK is replaced by max_aflpn variable.
CFTML_MASK is replaced by max_cftml variable.
BITTIMING MASK's are replaced by {nom,data}_bittiming variables.
* Collected tag from Geert.
v4->v5:
* Collected tag from Geert.
* The rules for R-Car Gen3/4 could be kept together, reducing the number
of lines. Similar change for rzg2l-canfd aswell.
* Keeping interrupts and resets together allows to keep a clear
separation between RZ/G2L and RZ/G3E, at the expense of only
a single line.
* Retained the tags for binding patches as it is trivial changes.
* Dropped the unused macro RCANFD_GAFLCFG_GETRNC.
* Updated macro RCANFD_GERFL_ERR by using gpriv->channels_mask and
dropped unused macro RCANFD_GERFL_EEF0_7.
* Replaced RNC mask in RCANFD_GAFLCFG_SETRNC macro by using
info->num_supported_rules variable.
* Updated the macro RCANFD_GAFLCFG by using info->rnc_field_width
variable.
* Updated shift value in RCANFD_GAFLCFG_SETRNC macro by using a formula
(32 - (n % rnc_per_reg + 1) * field_width).
* Replaced the variable name shared_can_reg->shared_can_regs.
* Improved commit description for patch{#11,#12}by replacing has->have.
* Dropped RCANFD_EEF_MASK and RCANFD_RNC_MASK as it is taken
care by gpriv->channels_mask and info->num_supported_rules.
* Dropped RCANFD_FIRST_RNC_SH and RCANFD_SECOND_RNC_SH by using a
formula (32 - (n % rnc_per_reg + 1) * rnc_field_width.
* Improved commit description by "All SoCs supports extenal clock"->
"All existing SoCs support an external clock".
* Updated error description in probe as "cannot get enabled ram clock"
* Updated r9a09g047_hw_info table.
v3->v4:
* Added Rb tag from Rob for patch#2.
* Added prefix RCANFD_* to enum rcar_canfd_reg_offset_id.
* Added prefix RCANFD_* to enum rcar_canfd_mask_id.
* Added prefix RCANFD_* to enum rcar_canfd_shift_id.
v2->v3:
* Collected tags.
* Dropped reg_gen4() and is_gen4() by adding mask_table, shift_table,
regs, ch_interface_mode and shared_can_reg variables to
struct rcar_canfd_hw_info.
v1->v2:
* Split the series with fixes patch separately.
* Added patch for Simplify rcar_canfd_probe() using
of_get_available_child_by_name() as dependency patch hit on can-next.
* Added Rb tag from Vincent Mailhol.
* Dropped redundant comment from commit description for patch#3.
Link: https://patch.msgid.link/20250417054320.14100-1-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
The CAN-FD IP found on the RZ/G3E SoC is similar to R-Car Gen4, but
it has no external clock instead it has clk_ram, it has 6 channels
and supports 20 interrupts. Add support for RZ/G3E CAN-FD driver.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-20-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Currently multi_channel_irqs has only 2 channels. But RZ/G3E has six
channels. Enhance multi_channel_irqs handling to support more than two
channels.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-19-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
All existing SoCs support an external clock, but RZ/G3E has only internal
clocks. Add external_clk variable to struct rcar_canfd_hw_info to handle
this difference.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-18-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
R-Car Gen3 and Gen4 have some differences in the shift bits. Introduce a
struct rcar_canfd_shift_data to hold these values and add the struct
rcar_canfd_shift_data variable sh to struct rcar_canfd_hw_info to handle
these differences. After this, drop the unused functions reg_gen4() and
is_gen4().
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-17-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
R-Car Gen3 and Gen4 have some differences in the register offsets. Add
struct rcanfd_regs variable regs to the struct rcar_canfd_hw_info to
handle these differences.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-16-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
R-Car Gen4 has shared regs for both CAN-FD and Classical CAN operations.
Add shared_can_regs variable to struct rcar_canfd_hw_info to handle this
difference.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-15-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
R-Car Gen4 has channel specific interface mode bit for setting CAN-FD or
Classical CAN mode whereas on R-Car Gen3 it is global. Add a
ch_interface_mode variable to struct rcar_canfd_hw_info to handle this
difference.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-14-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Both R-Car Gen4 and R-Car Gen3 have different bit timing parameters
Add {nom,data}_bittiming variables to struct rcar_canfd_hw_info to
handle this difference.
Since the mask used in the macros are max value - 1, replace that
as well.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-13-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
R-Car Gen3 has CFTML max positional value is 15 whereas on R-Car Gen4 it
is 31. Add a max_cftml variable to struct rcar_canfd_hw_info to handle
this difference.
While at it, rename the parameter x->cftml in RCANFD_CFCC_CFTML macro to
make it clear.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-12-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
R-Car Gen3 has maximum acceptance filter list page number of 31 whereas on
R-Car Gen4 it is 127. Add max_aflpn variable to struct rcar_canfd_hw_info
in order to support RZ/G3E that has max AFLPN of 63.
While at it, rename the parameter x->page_num in RCANFD_GAFLECTR_AFLPN
macro to make it clear.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-11-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
The shift and w value in rcar_canfd_setrnc() are dictated by the
field width:
- R-Car Gen4 packs 2 values in a 32-bit word, using a field width
of 16 bits,
- R-Car Gen3 packs up to 4 values in a 32-bit word, using a field
width of 8 bits.
Add rnc_field_width variable to struct rcar_canfd_hw_info to handle this
difference. The rnc_stride is 32 / rnc_field_width and the index parameter
w is calculated by ch / rnc_stride. The shift value in rcar_canfd_setrnc()
is computed by using (32 - (ch % rnc_stride + 1) * rnc_field_width).
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-10-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Update RCANFD_GAFLCFG macro by replacing the parameter ch->w, where w is
the GAFLCFG index used in the hardware manual.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-9-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Add rcar_canfd_setrnc() to replace the macro RCANFD_GAFLCFG_SETRNC.
While at it, replace int->unsigned int for local variables offset, page
and num_rules in rcar_canfd_configure_afl_rules().
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-8-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Drop the mask operation in RCANFD_GAFLCFG_SETRNC macro as the num_rules
can never be larger than number of supported rules.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-7-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Replace the macro RCANFD_GERFL_EEF0_7->RCANFD_GERFL_EEF. The macros
RCANFD_GERFL_EEF* in RCANFD_GERFL_ERR can be replaced by FIELD_PREP() and
drop the redundant macro RCANFD_GERFL_EEF(ch).
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20250417054320.14100-6-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Drop the unused macro RCANFD_GAFLCFG_GETRNC.
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-5-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Simplify rcar_canfd_probe() using of_get_available_child_by_name().
While at it, move of_node_put(child) inside the if block to avoid
additional check if of_child is NULL.
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-4-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Document support for the CAN-FD Interface on the RZ/G3E (R9A09G047) SoC,
which supports up to six channels.
The CAN-FD module on RZ/G3E is very similar to the one on both R-Car V4H
and RZ/G2L, but differs in some hardware parameters:
* No external clock, but instead has ram clock.
* Support up to 6 channels.
* 20 interrupts.
Reviewed-by: "Rob Herring (Arm)" <robh@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-3-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
RZ/G3E SoC has 20 interrupts, 2 resets and 6 channels that need more
branching with conditional schema. Simplify the conditional schema with
if statements rather than the complex if-else statements to prepare for
supporting RZ/G3E SoC.
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250417054320.14100-2-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Bring in the netfs API documentation updates which had been in the
vfs-6.16.misc branch for most of this cycle. So don't needlessly rewrite
the vfs-6.16.misc by dropping it from that branch and moving it to
vfs-6.16.netfs. Simply merge vfs-6.16.misc into vfs-6.16.netfs.
Signed-off-by: Christian Brauner <brauner@kernel.org>
Board files are deprecated by DT, and the last user of
nvmem_add_cell_table() was removed by commit 2af4fcc0d3 ("ARM:
davinci: remove unused board support") in v6.3. Hence remove all
support for nvmem cell tables, and update the documentation.
Device drivers can still register a single cell using
nvmem_add_one_cell() (which was not documented before).
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Srinivas Kandagatla <srini@kernel.org>
Link: https://lore.kernel.org/r/20250509122452.11827-2-srini@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Commit 29be47fcd6 ("nvmem: zynqmp_nvmem: zynqmp_nvmem_probe cleanup")
changed the driver to expect the device pointer to be passed as the
"context", but in nvmem the context parameter comes from nvmem_config.priv
which is never set - Leading to null pointer exceptions when the device is
accessed.
Fixes: 29be47fcd6 ("nvmem: zynqmp_nvmem: zynqmp_nvmem_probe cleanup")
Cc: stable <stable@kernel.org>
Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
Reviewed-by: Michal Simek <michal.simek@amd.com>
Tested-by: Michal Simek <michal.simek@amd.com>
Signed-off-by: Srinivas Kandagatla <srini@kernel.org>
Link: https://lore.kernel.org/r/20250509122407.11763-3-srini@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Over last year, several patches for drivers/mux/ were not picked up,
even after multiple pings or resends, so mark the mux subsystem as odd
fixes to clarify actual status of lack of maintainers with dedicated
time and indicate that someone could help here.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250501175303.144102-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The active reference lifecycle provides the break/unbreak mechanism but
the active reference is not truly active after unbreak -- callers don't
use it afterwards but it's important for proper pairing of kn->active
counting. Assuming this mechanism is in place, the WARN check in
kernfs_should_drain_open_files() is too sensitive -- it may transiently
catch those (rightful) callers between
kernfs_unbreak_active_protection() and kernfs_put_active() as found out by Chen
Ridong:
kernfs_remove_by_name_ns kernfs_get_active // active=1
__kernfs_remove // active=0x80000002
kernfs_drain ...
wait_event
//waiting (active == 0x80000001)
kernfs_break_active_protection
// active = 0x80000001
// continue
kernfs_unbreak_active_protection
// active = 0x80000002
...
kernfs_should_drain_open_files
// warning occurs
kernfs_put_active
To avoid the false positives (mind panic_on_warn) remove the check altogether.
(This is meant as quick fix, I think active reference break/unbreak may be
simplified with larger rework.)
Fixes: bdb2fd7fc5 ("kernfs: Skip kernfs_drain_open_files() more aggressively")
Link: https://lore.kernel.org/r/kmmrseckjctb4gxcx2rdminrjnq2b4ipf7562nvfd432ld5v5m@2byj5eedkb2o/
Cc: Chen Ridong <chenridong@huawei.com>
Signed-off-by: Michal Koutný <mkoutny@suse.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20250505121201.879823-1-mkoutny@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
I'm no longer able to perform this role since I left IBM.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/8734czh8yg.fsf@mpe.ellerman.id.au
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Usual mixed bag.
adi,ad4851
- Avoid a buffer overrun due to bug in pointer arithmetic.
adi,ad7173
- Fix compiling if gpiolib is not enabled
adi,ad7606
- Fix raw reads for 18-bit chips by ensuring we mask out upper bits
as some SPI controllers do not do so for 18bit words.
- Fix wrong masking for register writes.
adi,ad7944
- Mask high bits for raw reads.
adi,axi-adc
- Add check on whether the busy flag has cleared before first access.
invensense,icm42600
- Fix the temperature offset to take scale into account.
nxp,fxls8962af
- Fix temperature to be in milli degrees Celsius not degrees.
- Fix sign of temperature channel.
-----BEGIN PGP SIGNATURE-----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=mGH+
-----END PGP SIGNATURE-----
Merge tag 'iio-fixes-for-6.15b' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/jic23/iio into char-misc-next
Jonathan writes:
IIO: 2nd set of fixes for 6.15 (or 6.16 merge window)
Usual mixed bag.
adi,ad4851
- Avoid a buffer overrun due to bug in pointer arithmetic.
adi,ad7173
- Fix compiling if gpiolib is not enabled
adi,ad7606
- Fix raw reads for 18-bit chips by ensuring we mask out upper bits
as some SPI controllers do not do so for 18bit words.
- Fix wrong masking for register writes.
adi,ad7944
- Mask high bits for raw reads.
adi,axi-adc
- Add check on whether the busy flag has cleared before first access.
invensense,icm42600
- Fix the temperature offset to take scale into account.
nxp,fxls8962af
- Fix temperature to be in milli degrees Celsius not degrees.
- Fix sign of temperature channel.
* tag 'iio-fixes-for-6.15b' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/jic23/iio:
iio: accel: fxls8962af: Fix temperature scan element sign
iio: accel: fxls8962af: Fix temperature calculation
iio: adc: ad7944: mask high bits on direct read
iio: adc: ad4851: fix ad4858 chan pointer handling
iio: imu: inv_icm42600: Fix temperature calculation
iio: dac: adi-axi-dac: fix bus read
iio: adc: ad7606_spi: fix reg write value mask
iio: adc: ad7606: fix raw read for 18-bit chips
iio: adc: ad7173: fix compiling without gpiolib
-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.
Use the `DEFINE_RAW_FLEX()` helper for on-stack definitions of
a flexible structure where the size of the flexible-array member
is known at compile-time, and refactor the rest of the code,
accordingly.
So, with these changes, fix the following warnings:
drivers/w1/w1_netlink.c:198:31: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/w1/w1_netlink.c:219:31: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
Reviewed-by: Kees Cook <kees@kernel.org>
Signed-off-by: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/Z_RflBe5iDGTMFjV@kspp
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250513105326.27385-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Few cleanups and fixes for the mux drivers:
1. Simplify with spi_get_device_match_data().
2. Fix -Wunused-const-variable and -Wvoid-pointer-to-enum-cast warnings.
3. GPIO mux: add optional regulator for Lenovo T14s laptop headset.
4. MMIO mux: avoid using syscon's device_node_to_regmap(), due to
changes in the syscon code.
-----BEGIN PGP SIGNATURE-----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=s41I
-----END PGP SIGNATURE-----
Merge tag 'mux-drv-6.16' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/krzk/linux into char-misc-next
Krzysztof writes:
Mux drivers for v6.16
Few cleanups and fixes for the mux drivers:
1. Simplify with spi_get_device_match_data().
2. Fix -Wunused-const-variable and -Wvoid-pointer-to-enum-cast warnings.
3. GPIO mux: add optional regulator for Lenovo T14s laptop headset.
4. MMIO mux: avoid using syscon's device_node_to_regmap(), due to
changes in the syscon code.
* tag 'mux-drv-6.16' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/krzk/linux:
mux: adgs1408: fix Wvoid-pointer-to-enum-cast warning
mux: gpio: add optional regulator support
dt-bindings: mux: add optional regulator binding to gpio mux
mux: mmio: Do not use syscon helper to build regmap
mux: adg792a: remove incorrect of_match_ptr annotation
mux: adgs1408: simplify with spi_get_device_match_data()
mux: mmio: Add missing word in error message
========
- Fix conflict between MHI power up and SYSERR state transitions by issuing MHI
reset only if the device is in SYSERR state while in SBL/PBL EEs. The device
won't respond to reset if it is not in SYSERR state in SBL/PBL EEs.
- Remove redundant call to pci_assign_resource() since PCI core calls this API
internally.
- Add Telit FN920C04 modem which is based on Qcom SDX35 chipset.
-----BEGIN PGP SIGNATURE-----
iQEzBAABCgAdFiEEZ6VDKoFIy9ikWCeXVZ8R5v6RzvUFAmgkccoACgkQVZ8R5v6R
zvVsEQf9GXTqSPGHK0VaoUKECp/3PDchVp3OTLmlJVwtPr4OZ+eWdGoVpoZqlZo5
NsOsL+9n1y65WKg25y4KDDPGhhInYxppM61MOIa6BCEMacYC9sLC2K8EqVExQxob
JRcmymgWYXB7romLRj3CmQ83Y3lIdRxg/9rsfTzEWQA/Cnr6IyNtec21afFPynfK
B1urgeR+7RBSzHqtP3zvBS+gu5BObq9ypDzu6+TPVIssTVioGh2XkstSGKPvPcpv
hmdXVS55/AI7jIrhUnDh3D5KvO1HY2YD2DlIH6wZ845kYugkXyVp3xEdTol+2Ueh
Tz00iM8f9FWMEBIREk+GduAcutXaXg==
=T9jj
-----END PGP SIGNATURE-----
Merge tag 'mhi-for-v6.16' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/mani/mhi into char-misc-next
Manivannan writes:
MHI Host
========
- Fix conflict between MHI power up and SYSERR state transitions by issuing MHI
reset only if the device is in SYSERR state while in SBL/PBL EEs. The device
won't respond to reset if it is not in SYSERR state in SBL/PBL EEs.
- Remove redundant call to pci_assign_resource() since PCI core calls this API
internally.
- Add Telit FN920C04 modem which is based on Qcom SDX35 chipset.
* tag 'mhi-for-v6.16' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/mani/mhi:
bus: mhi: host: pci_generic: Add Telit FN920C04 modem support
bus: mhi: host: pci_generic: Remove redundant assign resource usage
bus: mhi: host: Fix conflict between power_up and SYSERR
============
- Increment the rd_offset after writing the buffer to avoid MHI host accessing
the incomplete/wrong buffer element.
-----BEGIN PGP SIGNATURE-----
iQEzBAABCgAdFiEEZ6VDKoFIy9ikWCeXVZ8R5v6RzvUFAmgkX2wACgkQVZ8R5v6R
zvXKMAf6AmmnJrSKXBWkEP8LcPlO4Ml/qaQR6Iym50gpc4dARdZTDY0qMxFDwlgV
Wl1Ppqgn3gdxfq85F2HTjlzXnpXzJPEmtQoQ4DdF0Lmv7T628cpwu24v7w2DOInZ
flnT4kOpGxMuG6nzRdA0VJ8MYnOZzE9wvM2xNHsgLCDIMFi+iZAi1XsCE2RQc1SQ
4/XqS/aDTlNkdUp5QcPERLn8mwpqlUmvg9ZBjBeczdZ+I0mnUHjr8sty/oaRVaNq
CxRZpVN5w3SK1CNwtZTvgVvloRHD+EZxymx4k6zRTtL29PZaYOdI5g1+zcb2XnrC
giSNTVym9FJhxuwqoVDYFmVRFIjp2w==
=J7N1
-----END PGP SIGNATURE-----
Merge tag 'mhi-fixes-for-v6.15' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/mani/mhi into char-misc-next
Manivannan writes:
MHI Endpoint
============
- Increment the rd_offset after writing the buffer to avoid MHI host accessing
the incomplete/wrong buffer element.
* tag 'mhi-fixes-for-v6.15' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/mani/mhi:
bus: mhi: ep: Update read pointer only after buffer is written
- Peter hands over the maintain role of m10bmc-sec driver to Matthew.
- Qasim's change fix potential NULL pointer for fpga test.
All patches have been reviewed on the mailing list, and have been in the
last linux-next releases (as part of our for-next branch).
Signed-off-by: Xu Yilun <yilun.xu@intel.com>
-----BEGIN PGP SIGNATURE-----
iIkEABYIADEWIQSgSJpClIeaArXyudb8twOBpKCM2gUCaCDOLBMceWlsdW4ueHVA
aW50ZWwuY29tAAoJEPy3A4GkoIza47QA/0ktlQtDL6FP1Y+1zR+7ouVYhQrqFdBx
owEuiuOUp7o8AP0a7ah1cQhXavXkO4oYK5wLHzkB2ywyBEVUOuL36AEMCQ==
=vW2j
-----END PGP SIGNATURE-----
Merge tag 'fpga-for-6.16-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/fpga/linux-fpga into char-misc-next
Xu writes:
FPGA Manager changes for 6.16-rc1
- Peter hands over the maintain role of m10bmc-sec driver to Matthew.
- Qasim's change fix potential NULL pointer for fpga test.
All patches have been reviewed on the mailing list, and have been in the
last linux-next releases (as part of our for-next branch).
Signed-off-by: Xu Yilun <yilun.xu@intel.com>
* tag 'fpga-for-6.16-rc1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/fpga/linux-fpga:
fpga: fix potential null pointer deref in fpga_mgr_test_img_load_sgt()
fpga: m10bmc-sec: change contact for secure update driver
An update to allow for larger count values in interrupt-cnt.
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQSNN83d4NIlKPjon7a1SFbKvhIjKwUCaCBJQgAKCRC1SFbKvhIj
K//PAQC/De1TRyz47rMwHg3agdFZOiSKO7X0QqHBdX1lLpMgRQEAgcaxB+cYap9b
8OfCqmvhbgO7YBZSRLslirC5fwlApA4=
=N5JS
-----END PGP SIGNATURE-----
Merge tag 'counter-updates-for-6.16' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/wbg/counter into char-misc-next
William writes:
Counter updates for 6.16
An update to allow for larger count values in interrupt-cnt.
* tag 'counter-updates-for-6.16' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/wbg/counter:
counter: interrupt-cnt: Convert atomic_t -> atomic_long_t
