Ricky Wu [Mon, 16 Jun 2025 06:49:56 +0000 (14:49 +0800)]
mmc: rtsx_usb_sdmmc: Add 74 clocks in poweron flow
To conform with SD spec definition, that the host must provide at least 74
clocks before issuing first command, let's add these clock cycles at
MMC_POWER_UP.
Ulf Hansson [Tue, 10 Jun 2025 11:16:26 +0000 (13:16 +0200)]
mmc: rtsx_usb_sdmmc: Re-work the code in sd_set_power_mode()
It's only at MMC_POWER_OFF and at MMC_POWER_UP when some operations must be
carried out in sd_set_power_mode(). The code is a bit obfuscated in this
regards. Let's convert it into a switch-case-clause to make this clear.
Ulf Hansson [Tue, 10 Jun 2025 11:16:25 +0000 (13:16 +0200)]
mmc: rtsx_usb_sdmmc: Convert sd_set_power_mode() into void
The sdmmc_set_ios() is the only caller of sd_set_power_mode() and it
ignores the return code. Let's therefore convert sd_set_power_mode() into a
void function instead.
Ulf Hansson [Tue, 10 Jun 2025 11:16:23 +0000 (13:16 +0200)]
mmc: rtsx_usb_sdmmc: Fix error-path in sd_set_power_mode()
In the error path of sd_set_power_mode() we don't update host->power_mode,
which could lead to an imbalance of the runtime PM usage count. Fix this by
always updating host->power_mode.
mmc: host: renesas_sdhi: Fix incorrect auto retuning for an SDIO card
This host controller is possible to change incorrect tap if an SDIO
card is used because DAT1 is used for interrupt signal on SDIO standard
but the controller doesn't take care of it. So, in the worst case,
this behavior causes a CRC error.
To resolve the issue, this driver uses manual correction mode instead
of auto correction if an SDIO card is used. Also, even if DAT1 is
mismatched on an SDIO card, this driver will not change the TAP.
Frank Li [Tue, 3 Jun 2025 15:22:45 +0000 (11:22 -0400)]
dt-bindings: mmc: mxs-mmc: change ref to mmc-controller-common.yaml from mmc-controller.yaml
Change ref to mmc-controller-common.yaml from mmc-controller.yaml because
imx23/imx28 use dual mode controller (spi and mmc). So default dts node
name use spi instead of mmc. The legacy reason, it use difference
compatible string to distringuish work mode (spi / mmc).
Fix below CHECK_DTB warnings:
arch/arm/boot/dts/nxp/mxs/imx23-olinuxino.dtb: spi@80010000 (fsl,imx23-mmc): $nodename:0: 'spi@80010000' does not match '^mmc(@.*)?$'
Binbin Zhou [Sat, 7 Jun 2025 07:35:43 +0000 (15:35 +0800)]
mmc: sdhci-pltfm: Drop the use of sdhci_pltfm_free()
Since the devm_mmc_alloc_host() helper is already in use,
sdhci_pltfm_free() is no longer needed.
To avoid causing drivers that still use sdhci_pltfm_free() to fail to
compile, it has been temporarily set to empty. And it will be removed
when there are no longer any callers.
Binbin Zhou [Sat, 7 Jun 2025 07:33:34 +0000 (15:33 +0800)]
mmc: sdhci: Use devm_mmc_alloc_host() helper
Use new function devm_mmc_alloc_host() to simplify the code.
Although sdhci_free_host() is no longer needed, to avoid drivers that still
use this function from failing to compile, sdhci_free_host() is temporarily
set to empty. Finally, it will be removed when there are no more callers.
Yixun Lan [Fri, 23 May 2025 14:46:32 +0000 (22:46 +0800)]
mmc: sdhci-of-k1: disable HW busy detection
It doesn't make sense to enable HW busy detection in pre_select_hs400(),
while disable it later in post_select_hs400(). And the reason behind this
isn't clear. Therefore, let's disable it for now.
Luke Wang [Wed, 21 May 2025 02:55:02 +0000 (10:55 +0800)]
mmc: sdhci-esdhc-imx: optimize clock loopback selection with dummy pad support
For legacy platforms without dummy pad:
When clock <= 100MHz: Set ESDHC_MIX_CTRL_FBCLK_SEL to 0 (external clock
pad loopback) for better bus clock proximity.
When clock > 100MHz: Set ESDHC_MIX_CTRL_FBCLK_SEL to 1 (internal clock
loopback) to avoid signal reflection noise at high frequency.
For i.MX94/95 with dummy pad support:
Keep ESDHC_MIX_CTRL_FBCLK_SEL at 0 for all speed mode. Hardware
automatically substitutes clock pad loopback with dummy pad loopback
when available, eliminating signal reflections while preserving better
bus clock proximity.
i.MX reference manual specifies that internal clock loopback should be
used for SDR104/HS200/HS400 modes. Move ESDHC_MIX_CTRL_FBCLK_SEL
configuration into the timing selection function to:
1. Explicitly set internal loopback path for SDR104/HS200/HS400 modes
2. Avoid redundant bit manipulation across multiple functions
Preserve ESDHC_MIX_CTRL_FBCLK_SEL during system resume for SDIO devices
with MMC_PM_KEEP_POWER and MMC_PM_WAKE_SDIO_IRQ flag, as the controller
might lose register state during suspend while skipping card
re-initialization.
Haibo Chen [Wed, 21 May 2025 03:31:34 +0000 (11:31 +0800)]
mmc: sdhci-esdhc-imx: Don't change pinctrl in suspend if wakeup source
The pinctrl sleep state may config the pin mux to certain function to save
power in system suspend. Unfortunately this doesn't work if usdhc is used
as a wakeup source, like waking up on SDIO irqs or card-detect irqs. In
these cases, we need pin mux to be configured to usdhc function pad.
The issue is found on imx93-11x11-evk board, where WiFI over SDIO with
in-band irqs fails to wakeup the system, because the DATA[1] pin has been
set to GPIO function.
To fix the problem, don't change the pinctrl state in suspend if there is a
system wakeup enabled.
Linus Torvalds [Sun, 22 Jun 2025 17:50:36 +0000 (10:50 -0700)]
Merge tag 'i2c-for-6.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux
Pull i2c fixes from Wolfram Sang:
- subsystem: convert drivers to use recent callbacks of struct
i2c_algorithm A typical after-rc1 cleanup, which I couldn't send in
time for rc2
- tegra: fix YAML conversion of device tree bindings
- k1: re-add a check which got lost during upstreaming
* tag 'i2c-for-6.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
i2c: k1: check for transfer error
i2c: use inclusive callbacks in struct i2c_algorithm
dt-bindings: i2c: nvidia,tegra20-i2c: Specify the required properties
Linus Torvalds [Sun, 22 Jun 2025 17:30:44 +0000 (10:30 -0700)]
Merge tag 'x86_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Borislav Petkov:
- Make sure the array tracking which kernel text positions need to be
alternatives-patched doesn't get mishandled by out-of-order
modifications, leading to it overflowing and causing page faults when
patching
- Avoid an infinite loop when early code does a ranged TLB invalidation
before the broadcast TLB invalidation count of how many pages it can
flush, has been read from CPUID
- Fix a CONFIG_MODULES typo
- Disable broadcast TLB invalidation when PTI is enabled to avoid an
overflow of the bitmap tracking dynamic ASIDs which need to be
flushed when the kernel switches between the user and kernel address
space
- Handle the case of a CPU going offline and thus reporting zeroes when
reading top-level events in the resctrl code
* tag 'x86_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/alternatives: Fix int3 handling failure from broken text_poke array
x86/mm: Fix early boot use of INVPLGB
x86/its: Fix an ifdef typo in its_alloc()
x86/mm: Disable INVLPGB when PTI is enabled
x86,fs/resctrl: Remove inappropriate references to cacheinfo in the resctrl subsystem
Linus Torvalds [Sun, 22 Jun 2025 17:17:51 +0000 (10:17 -0700)]
Merge tag 'irq_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq fixes from Borislav Petkov:
- Fix missing prototypes warnings
- Properly initialize work context when allocating it
- Remove a method tracking when managed interrupts are suspended during
hotplug, in favor of the code using a IRQ disable depth tracking now,
and have interrupts get properly enabled again on restore
- Make sure multiple CPUs getting hotplugged don't cause wrong tracking
of the managed IRQ disable depth
* tag 'irq_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip/ath79-misc: Fix missing prototypes warnings
genirq/irq_sim: Initialize work context pointers properly
genirq/cpuhotplug: Restore affinity even for suspended IRQ
genirq/cpuhotplug: Rebalance managed interrupts across multi-CPU hotplug
Linus Torvalds [Sun, 22 Jun 2025 17:11:45 +0000 (10:11 -0700)]
Merge tag 'perf_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Borislav Petkov:
- Avoid a crash on a heterogeneous machine where not all cores support
the same hw events features
- Avoid a deadlock when throttling events
- Document the perf event states more
- Make sure a number of perf paths switching off or rescheduling events
call perf_cgroup_event_disable()
- Make sure perf does task sampling before its userspace mapping is
torn down, and not after
* tag 'perf_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel: Fix crash in icl_update_topdown_event()
perf: Fix the throttle error of some clock events
perf: Add comment to enum perf_event_state
perf/core: Fix WARN in perf_cgroup_switch()
perf: Fix dangling cgroup pointer in cpuctx
perf: Fix cgroup state vs ERROR
perf: Fix sample vs do_exit()
Linus Torvalds [Sun, 22 Jun 2025 17:09:23 +0000 (10:09 -0700)]
Merge tag 'locking_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking fixes from Borislav Petkov:
- Make sure the switch to the global hash is requested always under a
lock so that two threads requesting that simultaneously cannot get to
inconsistent state
- Reject negative NUMA nodes earlier in the futex NUMA interface
handling code
- Selftests fixes
* tag 'locking_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
futex: Verify under the lock if hash can be replaced
futex: Handle invalid node numbers supplied by user
selftests/futex: Set the home_node in futex_numa_mpol
selftests/futex: getopt() requires int as return value.
* tag 'edac_urgent_for_v6.16_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras:
EDAC/igen6: Fix NULL pointer dereference
EDAC/amd64: Correct number of UMCs for family 19h models 70h-7fh
Linus Torvalds [Sun, 22 Jun 2025 16:46:11 +0000 (09:46 -0700)]
Merge tag 'v6.16-rc2-smb3-client-fixes-v2' of git://git.samba.org/sfrench/cifs-2.6
Pull smb client fixes from Steve French:
- Multichannel channel allocation fix for Kerberos mounts
- Two reconnect fixes
- Fix netfs_writepages crash with smbdirect/RDMA
- Directory caching fix
- Three minor cleanup fixes
- Log error when close cached dirs fails
* tag 'v6.16-rc2-smb3-client-fixes-v2' of git://git.samba.org/sfrench/cifs-2.6:
smb: minor fix to use SMB2_NTLMV2_SESSKEY_SIZE for auth_key size
smb: minor fix to use sizeof to initialize flags_string buffer
smb: Use loff_t for directory position in cached_dirents
smb: Log an error when close_all_cached_dirs fails
cifs: Fix prepare_write to negotiate wsize if needed
smb: client: fix max_sge overflow in smb_extract_folioq_to_rdma()
smb: client: fix first command failure during re-negotiation
cifs: Remove duplicate fattr->cf_dtype assignment from wsl_to_fattr() function
smb: fix secondary channel creation issue with kerberos by populating hostname when adding channels
Alex Elder [Mon, 16 Jun 2025 12:51:36 +0000 (07:51 -0500)]
i2c: k1: check for transfer error
If spacemit_i2c_xfer_msg() times out waiting for a message transfer to
complete, or if the hardware reports an error, it returns a negative
error code (-ETIMEDOUT, -EAGAIN, -ENXIO. or -EIO).
The sole caller of spacemit_i2c_xfer_msg() is spacemit_i2c_xfer(),
which is the i2c_algorithm->xfer callback function. It currently
does not save the value returned by spacemit_i2c_xfer_msg().
The result is that transfer errors go unreported, and a caller
has no indication anything is wrong.
When this code was out for review, the return value *was* checked
in early versions. But for some reason, that assignment got dropped
between versions 5 and 6 of the series, perhaps related to reworking
the code to merge spacemit_i2c_xfer_core() into spacemit_i2c_xfer().
Simply assigning the value returned to "ret" fixes the problem.
Fixes: 5ea558473fa31 ("i2c: spacemit: add support for SpacemiT K1 SoC") Signed-off-by: Alex Elder <elder@riscstar.com> Cc: <stable@vger.kernel.org> # v6.15+ Reviewed-by: Troy Mitchell <troymitchell988@gmail.com> Link: https://lore.kernel.org/r/20250616125137.1555453-1-elder@riscstar.com Signed-off-by: Andi Shyti <andi@smida.it> Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Linus Torvalds [Sat, 21 Jun 2025 16:20:15 +0000 (09:20 -0700)]
Merge tag 'nfsd-6.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux
Pull nfsd fixes from Chuck Lever:
- Two fixes for commits in the nfsd-6.16 merge
- One fix for the recently-added NFSD netlink facility
- One fix for a remote SunRPC crasher
* tag 'nfsd-6.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux:
sunrpc: handle SVC_GARBAGE during svc auth processing as auth error
nfsd: use threads array as-is in netlink interface
SUNRPC: Cleanup/fix initial rq_pages allocation
NFSD: Avoid corruption of a referring call list
Bharath SM [Thu, 19 Jun 2025 15:35:34 +0000 (21:05 +0530)]
smb: minor fix to use SMB2_NTLMV2_SESSKEY_SIZE for auth_key size
Replaced hardcoded value 16 with SMB2_NTLMV2_SESSKEY_SIZE
in the auth_key definition and memcpy call.
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org> Signed-off-by: Bharath SM <bharathsm@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
Bharath SM [Thu, 19 Jun 2025 15:35:33 +0000 (21:05 +0530)]
smb: minor fix to use sizeof to initialize flags_string buffer
Replaced hardcoded length with sizeof(flags_string).
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org> Signed-off-by: Bharath SM <bharathsm@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
Bharath SM [Thu, 19 Jun 2025 15:35:32 +0000 (21:05 +0530)]
smb: Use loff_t for directory position in cached_dirents
Change the pos field in struct cached_dirents from int to loff_t
to support large directory offsets. This avoids overflow and
matches kernel conventions for directory positions.
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org> Signed-off-by: Bharath SM <bharathsm@microsoft.com> Signed-off-by: Steve French <stfrench@microsoft.com>
Paul Aurich [Wed, 20 Nov 2024 16:01:54 +0000 (08:01 -0800)]
smb: Log an error when close_all_cached_dirs fails
Under low-memory conditions, close_all_cached_dirs() can't move the
dentries to a separate list to dput() them once the locks are dropped.
This will result in a "Dentry still in use" error, so add an error
message that makes it clear this is what happened:
[ 495.281119] CIFS: VFS: \\otters.example.com\share Out of memory while dropping dentries
[ 495.281595] ------------[ cut here ]------------
[ 495.281887] BUG: Dentry ffff888115531138{i=78,n=/} still in use (2) [unmount of cifs cifs]
[ 495.282391] WARNING: CPU: 1 PID: 2329 at fs/dcache.c:1536 umount_check+0xc8/0xf0
Also, bail out of looping through all tcons as soon as a single
allocation fails, since we're already in trouble, and kmalloc() attempts
for subseqeuent tcons are likely to fail just like the first one did.
Signed-off-by: Paul Aurich <paul@darkrain42.org> Acked-by: Bharath SM <bharathsm@microsoft.com> Suggested-by: Ruben Devos <rdevos@oxya.com> Cc: stable@vger.kernel.org Signed-off-by: Steve French <stfrench@microsoft.com>
projects / thirdparty / linux.git / log
