Provide a driver api for reporting device statistics required by the
"Implementation Requirements" section of the PSP Architecture
Specification. Use a warning to ensure drivers report stats required
by the spec.
Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Link: https://patch.msgid.link/20251106002608.1578518-4-daniel.zahka@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Track and report stats common to all psp devices from the core. A
'stale-event' is when the core marks the rx state of an active
psp_assoc as incapable of authenticating psp encapsulated data.
Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Link: https://patch.msgid.link/20251106002608.1578518-2-daniel.zahka@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
All three members are effectively of type bool, so make this explicit
and shrink size of struct fixed_phy_status.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/9eca3d7e-fa64-4724-8fdc-f2c1a8f2ae8f@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Parthiban Veerasooran says:
====================
net: phy: Add Open Alliance TC14 10Base-T1S PHY cable diagnostic support
This patch series adds Open Alliance TC14 (OATC14) 10BASE-T1S cable
diagnostic feature support to the Linux kernel PHY subsystem and enable
this feature for Microchip LAN867x Rev.D0 PHYs. These patches provide
standardized cable test functionality for 10BASE-T1S Ethernet PHYs,
allowing users to perform cable diagnostics via ethtool.
Patch Summary:
1. add OATC14 10BASE-T1S PHY cable diagnostic support
- Implements support for the OATC14 cable diagnostic feature in
Clause 45 PHYs.
- Adds functions to start a cable test and retrieve its status,
mapping hardware results to ethtool codes.
- Exports these functions for use by PHY drivers.
- Open Alliance TC14 10BASE-T1S Advanced Diagnostic PHY Features.
https://opensig.org/wp-content/uploads/2025/06/OPEN_Alliance_10BASE-T1S_Advanced_PHY_features_for-automotive_Ethernet_V2.1b.pdf
2. add cable diagnostic support for LAN867x Rev.D0
- Integrates the generic OATC14 cable test functions into the
Microchip LAN867x Rev.D0 PHY driver.
- Enables ethtool cable diagnostics for this PHY, improving
troubleshooting and maintenance.
====================
Link: https://patch.msgid.link/20251105051213.50443-1-parthiban.veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Enable Open Alliance TC14 (OATC14) 10Base-T1S cable diagnostic feature
for Microchip LAN867x Rev.D0 PHY by implementing `cable_test_start` and
`cable_test_get_status` using the generic C45 functions. This allows the
`ethtool` utility to perform cable diagnostic tests directly on the PHY,
improving network troubleshooting and maintenance.
Signed-off-by: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
Link: https://patch.msgid.link/20251105051213.50443-3-parthiban.veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add support for Open Alliance TC14 (OATC14) 10BASE-T1S PHYs cable
diagnostic feature.
This patch implements:
- genphy_c45_oatc14_cable_test_start() to initiate a cable test
- genphy_c45_oatc14_cable_test_get_status() to retrieve test results
- Helper function to map PHY cable test status to ethtool result codes
- Function declarations and exports for use by PHY drivers
This enables ethtool to report ok, open, short, and undetectable cable
conditions on OATC14 10Base-T1S PHYs.
Open Alliance TC14 10BASE-T1S Advanced Diagnostic PHY Features
Specification ref:
https://opensig.org/wp-content/uploads/2025/06/OPEN_Alliance_10BASE-T1S_Advanced_PHY_features_for-automotive_Ethernet_V2.1b.pdf
Signed-off-by: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
Link: https://patch.msgid.link/20251105051213.50443-2-parthiban.veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Once the netshaper is created for MANA, the current bandwidth
is reported in debugfs like this:
$ sudo ./tools/net/ynl/pyynl/cli.py \
--spec Documentation/netlink/specs/net_shaper.yaml \
--do set \
--json '{"ifindex":'3',
"handle":{ "scope": "netdev", "id":'1' },
"bw-max": 200000000 }'
None
$ sudo cat /sys/kernel/debug/mana/1/vport0/current_speed
200
After the shaper is deleted, it is expected to report
the maximum speed supported by the SKU. But currently it is
reporting 0, which is incorrect.
Fix this inconsistency, by resetting apc->speed to apc->max_speed
during deletion of the shaper object. This will improve
readability and debuggability.
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/1762369468-32570-1-git-send-email-ernis@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
EN7581 and AN7583 SoCs are capable of DMA mapping non-linear tx skbs on
non-consecutive DMA descriptors. This feature is useful when multiple
flows are queued on the same hw tx queue since it allows to fully utilize
the available tx DMA descriptors and to avoid the starvation of
high-priority flow we have in the current codebase due to head-of-line
blocking introduced by low-priority flows.
Tested-by: Xuegang Lu <xuegang.lu@airoha.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20251106-airoha-tx-linked-list-v2-1-0706d4a322bd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
It seems that most of the tests prepare the interfaces once before the test
run (setup_prepare()), rely on setup_wait() to wait for link and only then
run the test(s).
local_termination brings the physical interfaces down and up during test
run but never wait for them to come up. If the auto-negotiation takes
some seconds, first test packets are being lost, which leads to
false-negative test results.
Use setup_wait() in run_test() to make sure auto-negotiation has been
completed after all simple_if_init() calls on physical interfaces and test
packets will not be lost because of the race against link establishment.
Fixes: 90b9566aa5 ("selftests: forwarding: add a test for local_termination.sh")
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Link: https://patch.msgid.link/20251106161213.459501-1-alexander.sverdlin@siemens.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TCP SACK compression has been added in 2018 in commit
5d9f4262b7 ("tcp: add SACK compression").
It is working great for WAN flows (with large RTT).
Wifi in particular gets a significant boost _when_ ACK are suppressed.
Add a new sysctl so that we can tune the very conservative 5 % value
that has been used so far in this formula, so that small RTT flows
can benefit from this feature.
delay = min ( 5 % of RTT, 1 ms)
This patch adds new tcp_comp_sack_rtt_percent sysctl
to ease experiments and tuning.
Given that we cap the delay to 1ms (tcp_comp_sack_delay_ns sysctl),
set the default value to 33 %.
Quoting Neal Cardwell ( https://lore.kernel.org/netdev/CADVnQymZ1tFnEA1Q=vtECs0=Db7zHQ8=+WCQtnhHFVbEOzjVnQ@mail.gmail.com/ )
The rationale for 33% is basically to try to facilitate pipelining,
where there are always at least 3 ACKs and 3 GSO/TSO skbs per SRTT, so
that the path can maintain a budget for 3 full-sized GSO/TSO skbs "in
flight" at all times:
+ 1 skb in the qdisc waiting to be sent by the NIC next
+ 1 skb being sent by the NIC (being serialized by the NIC out onto the wire)
+ 1 skb being received and aggregated by the receiver machine's
aggregation mechanism (some combination of LRO, GRO, and sack
compression)
Note that this is basically the same magic number (3) and the same
rationales as:
(a) tcp_tso_should_defer() ensuring that we defer sending data for no
longer than cwnd/tcp_tso_win_divisor (where tcp_tso_win_divisor = 3),
and
(b) bbr_quantization_budget() ensuring that cwnd is at least 3 GSO/TSO
skbs to maintain pipelining and full throughput at low RTTs
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20251106115236.3450026-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The `len` member of the sk_buff is an unsigned int. This is cast to
`ssize_t` (a signed type) for the first sk_buff in the comparison,
but not the second sk_buff. On 32-bit systems, this can result in
an integer underflow for certain values because unsigned arithmetic
is being used.
This appears to be an oversight: if the intention was to use unsigned
arithmetic, then the first cast would have been omitted. The change
ensures both len values are cast to `ssize_t`.
The underflow causes an issue with ktls when multiple TLS PDUs are
included in a single TCP segment. The mainline kernel does not use
strparser for ktls anymore, but this is still useful for other
features that still use strparser, and for backporting.
Signed-off-by: Nate Karstens <nate.karstens@garmin.com>
Cc: stable@vger.kernel.org
Fixes: 43a0c6751a ("strparser: Stream parser for messages")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20251106222835.1871628-1-nate.karstens@garmin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Kuniyuki Iwashima says:
====================
tcp: Clean up SYN+ACK RTO code and apply max RTO.
Patch 1 - 4 are misc cleanup.
Patch 5 applies max RTO to non-TFO SYN+ACK.
Patch 6 adds a test for max RTO of SYN+ACK.
====================
Link: https://patch.msgid.link/20251106003357.273403-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This script sets net.ipv4.tcp_rto_max_ms to 1000 and checks
if SYN+ACK RTO is capped at 1s for TFO and non-TFO.
Without the previous patch, the max RTO is applied to TFO
SYN+ACK only, and non-TFO SYN+ACK RTO increases exponentially.
# selftests: net/packetdrill: tcp_rto_synack_rto_max.pkt
# TAP version 13
# 1..2
# tcp_rto_synack_rto_max.pkt:46: error handling packet: timing error:
expected outbound packet at 5.091936 sec but happened at 6.107826 sec; tolerance 0.127974 sec
# script packet: 5.091936 S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
# actual packet: 6.107826 S. 0:0(0) ack 1 win 65535 <mss 1460,nop,nop,sackOK>
# not ok 1 ipv4
# tcp_rto_synack_rto_max.pkt:46: error handling packet: timing error:
expected outbound packet at 5.075901 sec but happened at 6.091841 sec; tolerance 0.127976 sec
# script packet: 5.075901 S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK>
# actual packet: 6.091841 S. 0:0(0) ack 1 win 65535 <mss 1460,nop,nop,sackOK>
# not ok 2 ipv6
# # Totals: pass:0 fail:2 xfail:0 xpass:0 skip:0 error:0
not ok 49 selftests: net/packetdrill: tcp_rto_synack_rto_max.pkt # exit=1
With the previous patch, all SYN+ACKs are retransmitted
after 1s.
# selftests: net/packetdrill: tcp_rto_synack_rto_max.pkt
# TAP version 13
# 1..2
# ok 1 ipv4
# ok 2 ipv6
# # Totals: pass:2 fail:0 xfail:0 xpass:0 skip:0 error:0
ok 49 selftests: net/packetdrill: tcp_rto_synack_rto_max.pkt
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251106003357.273403-7-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since commit 54a378f434 ("tcp: add the ability to control
max RTO"), TFO SYN+ACK RTO is capped by the TFO full sk's
inet_csk(sk)->icsk_rto_max.
The value is inherited from the parent listener.
Let's apply the same cap to non-TFO SYN+ACK.
Note that req->rsk_listener is always non-NULL when we call
tcp_reqsk_timeout() in reqsk_timer_handler() or tcp_check_req().
It could be NULL for SYN cookie req, but we do not use
req->timeout then.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251106003357.273403-6-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
reqsk_timeout() is always called with @timeout being TCP_RTO_MAX.
Let's remove the arg.
As a prep for the next patch, reqsk_timeout() is moved to tcp.h
and renamed to tcp_reqsk_timeout().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251106003357.273403-5-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit 5903123f66 ("tcp: Use BPF timeout setting for SYN ACK
RTO") introduced req->timeout and initialised it in 3 places:
1. reqsk_alloc() sets 0
2. inet_reqsk_alloc() sets TCP_TIMEOUT_INIT
3. tcp_conn_request() sets tcp_timeout_init()
1. has been always redundant as 2. overwrites it immediately.
2. was necessary for TFO SYN+ACK but is no longer needed after
commit 8ea731d4c2 ("tcp: Make SYN ACK RTO tunable by BPF
programs with TFO").
3. was moved to reqsk_queue_hash_req() in the previous patch.
Now, we always initialise req->timeout just before scheduling
the SYN+ACK timer:
* For non-TFO SYN+ACK : reqsk_queue_hash_req()
* For TFO SYN+ACK : tcp_fastopen_create_child()
Let's remove the redundant initialisation of req->timeout in
reqsk_alloc() and inet_reqsk_alloc().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251106003357.273403-4-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
inet_csk_reqsk_queue_hash_add() is no longer shared by DCCP.
We do not need to pass req->timeout down to reqsk_queue_hash_req().
Let's move tcp_timeout_init() from tcp_conn_request() to
reqsk_queue_hash_req().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251106003357.273403-3-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since DCCP has been removed, we do not need to use
request_sock_ops.syn_ack_timeout().
Let's call tcp_syn_ack_timeout() directly.
Now other function pointers of request_sock_ops are
protocol-dependent.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251106003357.273403-2-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Define DTS nodes to enable support for QSPI on the K1 SoC, including the
pin control configuration used. Enable QSPI on the Banana Pi BPI-F3 board.
Signed-off-by: Alex Elder <elder@riscstar.com>
Link: https://lore.kernel.org/r/20251027133008.360237-9-elder@riscstar.com
Signed-off-by: Yixun Lan <dlan@gentoo.org>
After commit 44aa25c000 ("riscv: asm: use .insn for making custom
instructions"), builds using LLVM older that 19 or binutils older than
2.38 fail with:
arch/riscv/include/asm/vdso/processor.h: Assembler messages:
arch/riscv/include/asm/vdso/processor.h:27: Error: unrecognized opcode `0x100000f'
arch/riscv/include/asm/vdso/processor.h:27: Error: unrecognized opcode `0x100000f'
arch/riscv/include/asm/vdso/processor.h:27: Error: unrecognized opcode `0x100000f'
arch/riscv/include/asm/vdso/processor.h:27: Error: unrecognized opcode `0x100000f'
make[4]: *** [scripts/Makefile.build:287: arch/riscv/kernel/vdso/vgettimeofday.o] Error 1
In file included from <built-in>:4:
In file included from lib/vdso/gettimeofday.c:6:
In file included from include/vdso/datapage.h:21:
In file included from include/vdso/processor.h:10:
arch/riscv/include/asm/vdso/processor.h:23:2: error: expected instruction format
23 | ALT_RISCV_PAUSE();
| ^
arch/riscv/include/asm/errata_list.h:47:3: note: expanded from macro 'ALT_RISCV_PAUSE'
47 | RISCV_PAUSE, /* Original RISC‑V pause insn */ \
| ^
arch/riscv/include/asm/insn-def.h:259:21: note: expanded from macro 'RISCV_PAUSE'
259 | #define RISCV_PAUSE ASM_INSN_I("0x100000f")
| ^
arch/riscv/include/asm/asm.h:16:26: note: expanded from macro 'ASM_INSN_I'
16 | #define ASM_INSN_I(__x) ".insn " __x
| ^
<inline asm>:5:7: note: instantiated into assembly here
5 | .insn 0x100000f
| ^
binutils gained support for '.insn <value>' in 2.38 [1] and LLVM gained
support in 19 [2]. Adjust the test for CONFIG_AS_HAS_INSN to ensure that
all versions of .insn are supported before being used.
Fixes: 44aa25c000 ("riscv: asm: use .insn for making custom instructions")
Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=a262b82fdbf4cda3b0648b1adc32245ca3f78b7a [1]
Link: 2a086dce69 [2]
Suggested-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://patch.msgid.link/20251107-riscv-fix-new-insn-usage-v1-1-9a186c5928a0@kernel.org
Signed-off-by: Paul Walmsley <pjw@kernel.org>
The value of KBUILD_IMAGE is derived from $(boot-image-y),
so there's no need for redundant checks before this.
Signed-off-by: Feng Jiang <jiangfeng@kylinos.cn>
Reviewed-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Link: https://lore.kernel.org/r/20251029094429.553842-2-jiangfeng@kylinos.cn
Signed-off-by: Paul Walmsley <pjw@kernel.org>
According to the explanation in commit ef10bdf9c3 ("riscv:
Kconfig.socs: Split ARCH_CANAAN and SOC_CANAAN_K210"),
loader.bin is a special feature of the Canaan K210 and
is not applicable to other SoCs.
Fixes: e79dfcbfb9 ("riscv: make image compression configurable")
Signed-off-by: Feng Jiang <jiangfeng@kylinos.cn>
Reviewed-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
Link: https://lore.kernel.org/r/20251029094429.553842-1-jiangfeng@kylinos.cn
Signed-off-by: Paul Walmsley <pjw@kernel.org>
There is a report of io_estimate_bvec_size() truncating the calculated
number of segments that leads to corruption issues. Check it doesn't
overflow "int"s used later. Rough but simple, can be improved on top.
Cc: stable@vger.kernel.org
Fixes: 9ef4cbbcb4 ("io_uring: add infra for importing vectored reg buffers")
Reported-by: Google Big Sleep <big-sleep-vuln-reports+bigsleep-458654612@google.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Günther Noack <gnoack@google.com>
Tested-by: Günther Noack <gnoack@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There are a few remaining cases where we *do* want to use `as`,
because we specifically want to strip the data that does not fit into
the destination type. Comment these uses to clear confusion about the
intent.
Acked-by: Danilo Krummrich <dakr@kernel.org>
[acourbot@nvidia.com: fix merge conflicts after rebase.]
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Message-ID: <20251029-nova-as-v3-6-6a30c7333ad9@nvidia.com>
Use the newly-introduced `num` module to replace the use of `as`
wherever it is safe to do. This ensures that a given conversion cannot
lose data if its source or destination type ever changes.
Acked-by: Danilo Krummrich <dakr@kernel.org>
[acourbot@nvidia.com: fix merge conflicts after rebase.]
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Message-ID: <20251029-nova-as-v3-5-6a30c7333ad9@nvidia.com>
The core library's `From` implementations do not cover conversions
that are not portable or future-proof. For instance, even though it is
safe today, `From<usize>` is not implemented for `u64` because of the
possibility to support larger-than-64bit architectures in the future.
However, the kernel supports a narrower set of architectures, and in the
case of Nova we only support 64-bit. This makes it helpful and desirable
to provide more infallible conversions, lest we need to rely on the `as`
keyword and carry the risk of silently losing data.
Thus, introduce a new module `num` that provides safe const functions
performing more conversions allowed by the build target, as well as
`FromSafeCast` and `IntoSafeCast` traits that are just extensions of
`From` and `Into` to conversions that are known to be lossless.
Suggested-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/rust-for-linux/DDK4KADWJHMG.1FUPL3SDR26XF@kernel.org/
Acked-by: Danilo Krummrich <dakr@kernel.org>
[acourbot@nvidia.com: fix merge conflicts after rebase.]
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Message-ID: <20251029-nova-as-v3-4-6a30c7333ad9@nvidia.com>
sched:
- Fix deadlock
amdgpu:
- Reset fixes
- Misc fixes
- Panel scaling fixes
- HDMI fix
- S0ix fixes
- Hibernation fix
- Secure display fix
- Suspend fix
- MST fix
amdkfd:
- Process cleanup fix
xe:
- Fix missing synchronization on unbind
- Fix device shutdown when doing FLR
- Fix user fence signaling order
i915:
- Avoid lock inversion when pinning to GGTT on CHV/BXT+VTD
- Fix conversion between clock ticks and nanoseconds
mediatek:
- Disable AFBC support on Mediatek DRM driver
- Add pm_runtime support for GCE power control
imagination:
- kconfig: Fix dependencies
nouveau:
- Set DMA mask earlier
- Advertize correct modifiers for GB20x
pixpaper:
- kconfig: Fix dependencies
-----BEGIN PGP SIGNATURE-----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=COpG
-----END PGP SIGNATURE-----
Merge tag 'drm-fixes-2025-11-08' of https://gitlab.freedesktop.org/drm/kernel
Pull drm fixes from Dave Airlie:
"Back from travel, thanks to Simona for handling things. regular fixes,
seems about the right size, but spread out a bit.
amdgpu has the usual range of fixes, xe has a few fixes, and nouveau
has a couple of fixes, one for blackwell modifiers on 8/16 bit
surfaces.
Otherwise a few small fixes for mediatek, sched, imagination and
pixpaper.
sched:
- Fix deadlock
amdgpu:
- Reset fixes
- Misc fixes
- Panel scaling fixes
- HDMI fix
- S0ix fixes
- Hibernation fix
- Secure display fix
- Suspend fix
- MST fix
amdkfd:
- Process cleanup fix
xe:
- Fix missing synchronization on unbind
- Fix device shutdown when doing FLR
- Fix user fence signaling order
i915:
- Avoid lock inversion when pinning to GGTT on CHV/BXT+VTD
- Fix conversion between clock ticks and nanoseconds
mediatek:
- Disable AFBC support on Mediatek DRM driver
- Add pm_runtime support for GCE power control
imagination:
- kconfig: Fix dependencies
nouveau:
- Set DMA mask earlier
- Advertize correct modifiers for GB20x
pixpaper:
- kconfig: Fix dependencies"
* tag 'drm-fixes-2025-11-08' of https://gitlab.freedesktop.org/drm/kernel: (26 commits)
drm/xe: Enforce correct user fence signaling order using
drm/xe: Do clean shutdown also when using flr
drm/xe: Move declarations under conditional branch
drm/xe/guc: Synchronize Dead CT worker with unbind
drm/amd/display: Enable mst when it's detected but yet to be initialized
drm/amdgpu: Fix wait after reset sequence in S3
drm/amd: Fix suspend failure with secure display TA
drm/amdgpu: fix gpu page fault after hibernation on PF passthrough
drm/tiny: pixpaper: add explicit dependency on MMU
drm/nouveau: Advertise correct modifiers on GB20x
drm: define NVIDIA DRM format modifiers for GB20x
drm/nouveau: set DMA mask before creating the flush page
drm/sched: Fix deadlock in drm_sched_entity_kill_jobs_cb
drm/amd/display: Fix NULL deref in debugfs odm_combine_segments
drm/amdkfd: Don't clear PT after process killed
drm/amdgpu/smu: Handle S0ix for vangogh
drm/amdgpu: Drop PMFW RLC notifier from amdgpu_device_suspend()
drm/amd/display: Fix black screen with HDMI outputs
drm/amd/display: Don't stretch non-native images by default in eDP
drm/amd/pm: fix missing device_attr cleanup in amdgpu_pm_sysfs_init()
...
Whenever there's audit context, __audit_inode_child() gets called
numerous times, which can lead to high latency in scenarios that
create too many sysfs/debugfs entries at once, for instance, upon
device_add_disk() invocation.
# uname -r
6.18.0-rc2+
# auditctl -a always,exit -F path=/tmp -k foo
# time insmod loop max_loop=1000
real 0m46.676s
user 0m0.000s
sys 0m46.405s
# perf record -a insmod loop max_loop=1000
# perf report --stdio |grep __audit_inode_child
32.73% insmod [kernel.kallsyms] [k] __audit_inode_child
__audit_inode_child() searches for both the parent and the child
in two different loops that iterate over the same list. This
process can be optimized by merging these into a single loop,
without changing the function behavior or affecting the code's
readability.
This patch merges the two loops that walk through the list
context->names_list into a single loop. This optimization resulted
in around 51% performance enhancement for the benchmark.
# uname -r
6.18.0-rc2-enhancedv3+
# auditctl -a always,exit -F path=/tmp -k foo
# time insmod loop max_loop=1000
real 0m22.899s
user 0m0.001s
sys 0m22.652s
Signed-off-by: Ricardo Robaina <rrobaina@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Replace kmalloc+memset by kzalloc for better readability and simplicity.
This addresses the warning below:
WARNING: kzalloc should be used for data, instead of kmalloc/memset
Signed-off-by: Gongwei Li <ligongwei@kylinos.cn>
[PM: subject and description tweaks]
Signed-off-by: Paul Moore <paul@paul-moore.com>
Add an ability to be able to compose perf_tools, by having one perform
an action and then calling a delegate. Currently the perf_tools have
if-then-elses setting the callback and then if-then-elses within the
callback. Understanding the behavior is complex as it is in two places
and logic for numerous operations, within things like perf inject, is
interwoven. By chaining perf_tools together based on command line
options this kind of code can be avoided.
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Getting context for what a tool is doing, such as the perf_inject
instance, using container_of the tool is a common pattern in the
code. This isn't possible event_op2, event_op3 and event_op4 callbacks
as the tool isn't passed. Add the argument and then fix function
signatures to match. As tools maybe reading a tool from somewhere
else, change that code to use the passed in tool.
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
- fix crash triggered by unaligned access in parisc unwinder
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQS86RI+GtKfB8BJu973ErUQojoPXwUCaQ5IBgAKCRD3ErUQojoP
X0GaAP9K2e9TZyIB0cnPzk0+uWIa8Py1Pzfz6eTHjjb958W6JAEAwLexSNhqNoVo
TjjdThDqjWUG1AW3ptsa662x5v+/aAA=
=h5Vt
-----END PGP SIGNATURE-----
Merge tag 'parisc-for-6.18-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux
Pull parisc fix from Helge Deller:
- fix crash triggered by unaligned access in parisc unwinder
* tag 'parisc-for-6.18-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Avoid crash due to unaligned access in unwinder
Three fixes:
- Syzkaller found a case where maths overflows can cause divide by 0
- Typo in a compiler bug warning fix in the selftests broke the selftests
- type1 compatability had a mismatch when unmapping an already unmaped
range, it should succeed
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRRRCHOFoQz/8F5bUaFwuHvBreFYQUCaQ473AAKCRCFwuHvBreF
Ya8gAP9Qifu4AYobrhgD9rKKXLniGRejXUHBQ0G8y8y9sBHJdgEApwxzCUcI1jLZ
GTaPEABblBBWxUmN+Psya2Hm3Oa53AA=
=TJHp
-----END PGP SIGNATURE-----
Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd
Pull iommufd fixes from Jason Gunthorpe:
- Syzkaller found a case where maths overflows can cause divide by 0
- Typo in a compiler bug warning fix in the selftests broke the
selftests
- type1 compatability had a mismatch when unmapping an already unmapped
range, it should succeed
* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd:
iommufd: Make vfio_compat's unmap succeed if the range is already empty
iommufd/selftest: Fix ioctl return value in _test_cmd_trigger_vevents()
iommufd: Don't overflow during division for dirty tracking
Add proper error handling and resource cleanup to prevent memory leaks
in add_boot_memory_ranges(). The function now checks for NULL return
from kobject_create_and_add(), uses local buffer for range names to
avoid dynamic allocation, and implements a cleanup path that removes
previously created sysfs groups and kobjects on failure.
This prevents resource leaks when kobject creation or sysfs group
creation fails during boot memory range initialization.
Signed-off-by: Kaushlendra Kumar <kaushlendra.kumar@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://patch.msgid.link/20251030023228.3956296-1-kaushlendra.kumar@intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Replace kfree() with ACPI_FREE() in pch_fivr_read() to follow ACPICA
memory management conventions.
While functionally equivalent in Linux (ACPI_FREE() is implemented
as kfree()), using ACPI_FREE() maintains consistency with ACPICA
coding standards for deallocating ACPI buffer objects.
Signed-off-by: Kaushlendra Kumar <kaushlendra.kumar@intel.com>
[ rjw: Subject and changelog edits ]
Link: https://patch.msgid.link/20251028051554.2862049-1-kaushlendra.kumar@intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
These TCR_El1 helpers don't have any other callers. Drop these redundant
indirections completely thus making this code more compact and readable.
No functional change.
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
The zt-test output is awkward to read, as the 'Expected' value isn't
dumped on its own line and isn't aligned with the 'Got' value beneath.
For example:
Mismatch: PID=5281, iteration=3270249 Expected [00a1146901a1146902a1146903a1146904a1146905a1146906a1146907a1146908a1146909a114690aa114690ba114690ca114690da114690ea114690fa11469]
Got [00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000]
SVCR: 2
Add a newline, matching the other FPSIMD/SVE/SME tests, so that we get
output that can be read more easily:
Mismatch: PID=5281, iteration=3270249
Expected [00a1146901a1146902a1146903a1146904a1146905a1146906a1146907a1146908a1146909a114690aa114690ba114690ca114690da114690ea114690fa11469]
Got [00000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000]
SVCR: 2
Admittedly this isn't all that important when the 'Got' value is all
zeroes, but otherwise this would be a major help for identifying which
portion of the 'Got' value is not as expected.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kselftest@vger.kernel.org
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This is only relevant to the FLATMEM memory model, which isn't an option
since commit 782276b4d0 ("arm64: Force SPARSEMEM_VMEMMAP as the only
memory management model").
Signed-off-by: Omar Sandoval <osandov@fb.com>
Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
For those architectures with HAVE_SOFTIRQ_ON_OWN_STACK use
their dedicated softirq stack when !PREEMPT_RT. This condition
is ensured by SOFTIRQ_ON_OWN_STACK.
Let arm64 use SOFTIRQ_ON_OWN_STACK as well to select its
usage of the stack.
Signed-off-by: Ryo Takakura <ryotkkr98@gmail.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
CONFIG_VMAP_STACK is selected by arm64 arch unconditionly since commit
ef6861b8e6 ("arm64: Mandate VMAP_STACK").
Remove the redundant assertion and headers.
Signed-off-by: Dawei Li <dawei.li@linux.dev>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Using the IS_ENABLED() macro in the int340x_thermal_handler_attach()
forces the kernel to be recompiled when thermal drivers are enabled
or disabled, which is a significant limitation of its modularity.
The IS_ENABLED() macro is particularly problematic for the Android
Generic Kernel Image (GKI) project which uses unified core kernel
while SoC/board support is moved to loadable vendor modules.
The Intel Dynamic Platform and Thermal Framework (DPTF) requires
thermal drivers to be loaded at runtime, thus ACPI bus scan handler
is not needed and acpi_default_enumeration() may create all platform
devices, regardless of the actual setting of CONFIG_INT340X_THERMAL.
Signed-off-by: Slawomir Rosek <srosek@google.com>
Link: https://patch.msgid.link/20251103162516.2606158-3-srosek@google.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The IRQ used by the Intel SoC DTS thermal device for critical
overheating notification is listed in _CRS of device INT3401 which
therefore needs to be enumerated for Intel SoC DTS thermal to work.
The enumeration happens by binding the int3401_thermal driver to the
INT3401 platform device. Thus CONFIG_INT340X_THERMAL is in fact
necessary for enumerating it, so checking CONFIG_INTEL_SOC_DTS_THERMAL
in int340x_thermal_handler_attach() is pointless and INT340X_THERMAL
may as well be selected by INTEL_SOC_DTS_THERMAL.
Signed-off-by: Slawomir Rosek <srosek@google.com>
[ rjw: New subject ]
Link: https://patch.msgid.link/20251103162516.2606158-2-srosek@google.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The current code assumes that only DDR errors have split messages. Ensure
proper logging of non-standard event errors that may be split across multiple
messages too.
[ bp: Massage, move comment too, fix it up. ]
Fixes: d5fe2fec6c ("EDAC: Add a driver for the AMD Versal NET DDR controller")
Signed-off-by: Shubhrajyoti Datta <shubhrajyoti.datta@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://patch.msgid.link/20251023113108.3467132-1-shubhrajyoti.datta@amd.com
Remove the code to disable IRQs when unregistering KVM's user-return
notifier now that KVM doesn't invoke kvm_on_user_return() when disabling
virtualization via IPI function call, i.e. now that there's no need to
guard against re-entrancy via IPI callback.
Note, disabling IRQs has largely been unnecessary since commit
a377ac1cd9 ("x86/entry: Move user return notifier out of loop") moved
fire_user_return_notifiers() into the section with IRQs disabled. In doing
so, the commit somewhat inadvertently fixed the underlying issue that
was papered over by commit 1650b4ebc9 ("KVM: Disable irq while
unregistering user notifier"). I.e. in practice, the code and comment
has been stale since commit a377ac1cd9.
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
[sean: rewrite changelog after rebasing, drop lockdep assert]
Reviewed-by: Kai Huang <kai.huang@intel.com>
Link: https://patch.msgid.link/20251030191528.3380553-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Leave KVM's user-return notifier registered in the unlikely case that the
notifier is registered when disabling virtualization via IPI callback in
response to reboot/shutdown. On reboot/shutdown, keeping the notifier
registered is ok as far as MSR state is concerned (arguably better then
restoring MSRs at an unknown point in time), as the callback will run
cleanly and restore host MSRs if the CPU manages to return to userspace
before the system goes down.
The only wrinkle is that if kvm.ko module unload manages to race with
reboot/shutdown, then leaving the notifier registered could lead to
use-after-free due to calling into unloaded kvm.ko module code. But such
a race is only possible on --forced reboot/shutdown, because otherwise
userspace tasks would be frozen before kvm_shutdown() is called, i.e. on a
"normal" reboot/shutdown, it should be impossible for the CPU to return to
userspace after kvm_shutdown().
Furthermore, on a --forced reboot/shutdown, unregistering the user-return
hook from IRQ context doesn't fully guard against use-after-free, because
KVM could immediately re-register the hook, e.g. if the IRQ arrives before
kvm_user_return_register_notifier() is called.
Rather than trying to guard against the IPI in the "normal" user-return
code, which is difficult and noisy, simply leave the user-return notifier
registered on a reboot, and bump the kvm.ko module refcount to defend
against a use-after-free due to kvm.ko unload racing against reboot.
Alternatively, KVM could allow kvm.ko and try to drop the notifiers during
kvm_x86_exit(), but that's also a can of worms as registration is per-CPU,
and so KVM would need to blast an IPI, and doing so while a reboot/shutdown
is in-progress is far risky than preventing userspace from unloading KVM.
Link: https://patch.msgid.link/20251030191528.3380553-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
When freeing the per-CPU user-return MSRs structures, WARN if any CPU has
a registered notifier to help detect and/or debug potential use-after-free
issues. The lifecycle of the notifiers is rather convoluted, and has
several non-obvious paths where notifiers are unregistered, i.e. isn't
exactly the most robust code possible.
The notifiers they are registered on-demand in KVM, on the first WRMSR to
a tracked register. _Usually_ the notifier is unregistered whenever the
CPU returns to userspace. But because any given CPU isn't guaranteed to
return to userspace, e.g. the CPU could be offlined before doing so, KVM
also "drops", a.k.a. unregisters, the notifiers when virtualization is
disabled on the CPU.
Further complicating the unregister path is the fact that the calls to
disable virtualization come from common KVM, and the per-CPU calls are
guarded by a per-CPU flag (to harden _that_ code against bugs, e.g. due to
mishandling reboot). Reboot/shutdown in particular is problematic, as KVM
disables virtualization via IPI function call, i.e. from IRQ context,
instead of using the cpuhp framework, which runs in task context. I.e. on
reboot/shutdown, drop_user_return_notifiers() is called asynchronously.
Forced reboot/shutdown is the most problematic scenario, as userspace tasks
are not frozen before kvm_shutdown() is invoked, i.e. KVM could be actively
manipulating the user-return MSR lists and/or notifiers when the IPI
arrives. To a certain extent, all bets are off when userspace forces a
reboot/shutdown, but KVM should at least avoid a use-after-free, e.g. to
avoid crashing the kernel when trying to reboot.
Link: https://patch.msgid.link/20251030191528.3380553-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
