Previously, the MMIO and MSR RAPL interfaces shared the same set of
RAPL defaults provided by common code. However, unlike the MSR
interface, the MMIO RAPL interface does not require CPU-specific
variations in its default handling. Keeping the RAPL defaults in
the RAPL common driver therefore provides no additional benefit.
Move the MMIO defaults into the MMIO interface driver. This change
includes the following updates:
* Introduce a MMIO-local rapl_defaults instance with the appropriate
default callbacks.
* Assign the MMIO-specific rapl_defaults to priv->defaults during
MMIO driver initialization.
No functional changes are expected.
Co-developed-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-11-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
TPMI-specific RAPL defaults differ from those used by MSR and MMIO
interfaces. Keeping them in RAPL common driver introduces unnecessary
complexity.
Move the TPMI defaults into the TPMI interface driver. This change
includes the following updates:
1. Add a TPMI-local struct rapl_defaults instance and assign it to
priv->defaults during TPMI probe.
2. Move rapl_check_unit_tpmi() and related unit-field definitions from
the common driver into the TPMI driver.
3. In rapl_check_unit_tpmi(), replace the generic get_rid() usage with
direct access to the TPMI package ID, since the function is now
interface-specific.
No functional changes are intended.
Co-developed-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-10-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
RAPL default settings vary across different RAPL interfaces (MSR, TPMI,
MMIO). Currently, these defaults are stored in the common RAPL driver,
which requires interface-specific handling logic and makes the common
layer unnecessarily complex. There is no strong reason for the common
code to own these defaults, since they are inherently
interface-specific.
To prepare for moving default configuration into the individual
interface drivers,
1. Move struct rapl_defaults into a shared header so that interface
drivers can directly populate their own default settings.
2. Change the @defaults field in struct rapl_if_priv from void * to
const struct rapl_defaults * to improve type safety and readability
and update the common driver to use the typed defaults structure.
3. Update all internal getter functions and local pointers to use
const struct rapl_defaults * to maintain const-correctness.
4. Rename and export the common helper functions (check_unit,
set_floor_freq, compute_time_window) so interface drivers may
reuse or override them as appropriate.
No functional changes. This is a preparatory refactoring to allow
interface drivers to supply their own RAPL default settings.
Co-developed-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-9-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Replace hardcoded numeric constants with standard unit conversion
macros from linux/units.h for better code clarity and
self-documentation.
Add MICROJOULE_PER_JOULE and NANOJOULE_PER_JOULE to units.h to
support energy unit conversions, following the existing pattern
for power units.
No functional changes.
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-8-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Replace hardcoded bitmasks and bit shift operations with standard
GENMASK(), GENMASK_ULL(), BIT(), and BIT_ULL() macros for better
readability and to follow kernel coding conventions.
No functional changes.
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-7-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Replace division by (1 << value) with shift operations for clarity and
consistency. Add ULL suffix to avoid undefined behavior from shifting
signed integers.
No functional changes intended.
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-6-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Restructure to use early return for to_raw case, eliminating
redundant assignments and clarifying conversion paths.
No functional changes.
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-5-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Remove TIME_WINDOW_MIN_MSEC and TIME_WINDOW_MAX_MSEC as they
are not used anywhere in the code.
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-4-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cleanup of the intel_rapl common driver requires introducing additional
exported helper and lifecycle functions. Before adding new exports,
create a dedicated symbol namespace for intel_rapl and update the
relevant interface drivers to explicitly import it.
This makes the intended usage of these symbols explicit, avoids
polluting the global namespace, and prepares the codebase for the
ongoing RAPL refactoring.
No functional changes are intended.
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260212233044.329790-2-sathyanarayanan.kuppuswamy@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Ankit Garg says:
====================
gve: optimize and enable HW GRO for DQO
The DQO device has always performed HW GRO, not LRO. This series updates
the feature bit and modifies the RX path to enhance support. It sets
gso_segs correctly so the software stack can continue coalescing, and
pulls network headers into the skb linear space to avoid multiple small
memory copies when header-split is disabled.
We also enable HW GRO by default on supported devices.
====================
Link: https://patch.msgid.link/20260303195549.2679070-1-joshwash@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Change the driver's default behavior to enable hw-gro whenever supported
for device.
Performance observations:
- We observed ~10% improvement in RX single stream throughput across
various MTU sizes.
- No change in TCP_RR/TCP_CRR latencies
Signed-off-by: Ankit Garg <nktgrg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Link: https://patch.msgid.link/20260303195549.2679070-5-joshwash@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Currently, in DQO mode with hw-gro enabled, entire received packet is
placed into skb fragments when header-split is disabled. This leaves
the skb linear part empty, forcing the networking stack to do multiple
small memory copies to access eth, IP and TCP headers.
This patch adds a single memcpy to put all headers into linear portion
before packet reaches the SW GRO stack; thus eliminating multiple
smaller memcpy calls.
Additionally, the criteria for calling napi_gro_frags() was updated.
Since skb->head is now populated, we instead check if the SKB is the
cached NAPI scratchpad to ensure we continue using the zero-allocation
path.
Signed-off-by: Ankit Garg <nktgrg@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Link: https://patch.msgid.link/20260303195549.2679070-4-joshwash@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Leaving gso_segs unpopulated on hardware GRO packet prevents further
coalescing by software stack because the kernel's GRO logic marks the
SKB for flush because the expected length of all segments doesn't match
actual payload length.
Setting gso_segs correctly results in significantly more segments being
coalesced as measured by the result of dev_gro_receive().
gso_segs are derived from payload length. When header-split is enabled,
payload is in the non-linear portion of skb. And when header-split is
disabled, we have to parse the headers to determine payload length.
Signed-off-by: Ankit Garg <nktgrg@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jordan Rhee <jordanrhee@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Link: https://patch.msgid.link/20260303195549.2679070-3-joshwash@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The device behind DQO format has always coalesced packets per stricter
hardware GRO spec even though it was being advertised as LRO.
Update advertised capability to match device behavior.
Signed-off-by: Ankit Garg <nktgrg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Link: https://patch.msgid.link/20260303195549.2679070-2-joshwash@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Include policy->cur in the debug message to explicitly show the frequency
transition (from current to target).
Signed-off-by: Pengjie Zhang <zhangpengjie2@huawei.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://patch.msgid.link/20260129121813.3874516-1-zhangpengjie2@huawei.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reset eBPF program pointer to old_prog and do not decrease its ref-count
if mtk_open routine in mtk_xdp_setup() fails.
Fixes: 7c26c20da5 ("net: ethernet: mtk_eth_soc: add basic XDP support")
Suggested-by: Paolo Valerio <pvalerio@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260303-mtk-xdp-prog-ptr-fix-v2-1-97b6dbbe240f@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add support for reading DDR data rate from PCI config offset.
The register details are:
CFG Offset : 0xE0
Bits : 11:2
DDR Data rate is in 33.33 MTPS units.
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
[ rjw: Rearrange code to avoid using goto and make declarations consistent ]
Link: https://patch.msgid.link/20260223190420.874853-1-srinivas.pandruvada@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
This change is based on the observation that it is not in fact necessary
to select a deep idle state every time the scheduler tick has been
stopped before the idle state selection takes place. Namely, if the
time till the closest timer (that is not the tick) is short enough,
a shallow idle state can be selected because the timer will kick the
CPU out of that state, so the damage from a possible overly optimistic
selection will be limited.
Update the teo governor in accordance with the above in analogy with
the previous analogous menu governor update.
Among other things, this will cause the teo governor to call
tick_nohz_get_sleep_length() every time when the tick has been
stopped already and only change the original idle state selection
if the time till the closest timer is beyond SAFE_TIMER_RANGE_NS
which is way more straightforward than the current code flow.
Of course, this effectively throws away some of the recent teo governor
changes made recently, but the resulting simplification is worth it in
my view.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Link: https://patch.msgid.link/1865078.VLH7GnMWUR@rafael.j.wysocki
This change is based on the observation that it is not in fact necessary
to select a deep idle state every time the scheduler tick has been
stopped before the idle state selection takes place. Namely, if the
time till the closest timer (that is not the tick) is short enough,
a shallow idle state can be selected because the timer will kick the
CPU out of that state, so the damage from a possible overly optimistic
selection will be limited.
Update the menu governor in accordance with the above and use twice
the tick period length as the "safe timer range" for allowing the
original predicted_ns value to be used even if the tick has been
stopped.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Link: https://patch.msgid.link/3341782.5fSG56mABF@rafael.j.wysocki
This reverts commit 2e3649e237.
The problem occurs when userspace is compiled against new headers
with new members, but don't correctly initialise those new members.
This is not a kernel problem, and should be fixed in userspace by
correctly zero'ing all members.
Cc: Rob Clark <robdclark@chromium.org>
Cc: Julian Orth <ju.orth@gmail.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Michel Dänzer <michel.daenzer@mailbox.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Julian Orth <ju.orth@gmail.com>
Link: https://patch.msgid.link/20260305113734.1309238-1-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
Driver core holds a reference to the USB interface and its parent USB
device while the interface is bound to a driver and there is no need to
take additional references unless the structures are needed after
disconnect.
Similarly, USB core holds a reference to all interfaces in the active
configuration so there is no need for a driver to take a reference to a
sibling interface only to release it at disconnect either.
Drop the redundant references to reduce cargo culting, make it easier to
spot drivers where extra references are needed, and reduce the risk of
memory leaks when drivers fail to release them.
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260305111810.18688-1-johan@kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The Dojo device has a M.2 M-key slot for an included NVMe on some
models.
Add a proper device tree description based on the new M.2 M-key binding.
Power for the slot is controlled by the embedded controller. As far as
the main SoC is concerned, it is always on.
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Signed-off-by: Chen-Yu Tsai <wenst@chromium.org>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
The MT8195 Cherry design features an M.2 E-key slot wired up with PCIe
and USB for a WiFi+BT adapter. Previously the power was just enabled
all the time with a default pinctrl setting that set the GPIO pin high.
With the PCIe slot description DT binding in place, the power supplies
can at least be added and tied to the PCIe and USB hosts. Once the
M.2 E-key binding is merged, this description can be further converted
to an M.2 E-key.
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Signed-off-by: Chen-Yu Tsai <wenst@chromium.org>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
This patch adds support for chip RTL8125cp. Its XID is 0x708. We apply
different configuration and firmware for RTL8125cp.
Signed-off-by: Javen Xu <javen_xu@realsil.com.cn>
Link: https://patch.msgid.link/20260303094611.450-1-javen_xu@realsil.com.cn
[pabeni@redhat.com: changelog cleanup]
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Currently, ppp->xmit_pending is used in ppp_send_frame() to pass a skb
to ppp_push(), and holds the skb when a PPP channel cannot immediately
transmit it. This state is redundant because the transmit queue
(ppp->file.xq) can already handle the backlog. Furthermore, during
normal operation, an skb is queued in file.xq only to be immediately
dequeued, causing unnecessary overhead.
Refactor the transmit path to avoid stashing the skb when possible:
- Remove ppp->xmit_pending.
- Rename ppp_send_frame() to ppp_prepare_tx_skb(), and don't call
ppp_push() in it. It returns 1 if the skb is consumed
(dropped/handled) or 0 if it can be passed to ppp_push().
- Update ppp_push() to accept the skb. It returns 1 if the skb is
consumed, or 0 if the channel is busy.
- Optimize __ppp_xmit_process():
- Fastpath: If the queue is empty, attempt to send the skb directly
via ppp_push(). If busy, queue it.
- Slowpath: If the queue is not empty, process the backlog in
file.xq. Split dequeuing loop into a separate function
ppp_xmit_flush() so ppp_channel_push() uses that directly instead of
passing a NULL skb to __ppp_xmit_process().
This simplifies the states and reduces locking in the fastpath.
Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Link: https://patch.msgid.link/20260303093219.234403-1-dqfext@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Yiming Qian reports Use-after-free in the pipapo set type:
Under a large number of expired elements, commit-time GC can run for a very
long time in a non-preemptible context, triggering soft lockup warnings and
RCU stall reports (local denial of service).
We must split GC in an unlink and a reclaim phase.
We cannot queue elements for freeing until pointers have been swapped.
Expired elements are still exposed to both the packet path and userspace
dumpers via the live copy of the data structure.
call_rcu() does not protect us: dump operations or element lookups starting
after call_rcu has fired can still observe the free'd element, unless the
commit phase has made enough progress to swap the clone and live pointers
before any new reader has picked up the old version.
This a similar approach as done recently for the rbtree backend in commit
35f83a7552 ("netfilter: nft_set_rbtree: don't gc elements on insert").
Fixes: 3c4287f620 ("nf_tables: Add set type for arbitrary concatenation of ranges")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Syzbot with fault injection triggered a failing memory allocation with
GFP_KERNEL which results in a WARN splat:
iter.err
WARNING: net/netfilter/nf_tables_api.c:845 at nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845, CPU#0: syz.0.17/5992
Modules linked in:
CPU: 0 UID: 0 PID: 5992 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026
RIP: 0010:nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845
Code: 8b 05 86 5a 4e 09 48 3b 84 24 a0 00 00 00 75 62 48 8d 65 d8 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc cc e8 63 6d fa f7 90 <0f> 0b 90 43
+80 7c 35 00 00 0f 85 23 fe ff ff e9 26 fe ff ff 89 d9
RSP: 0018:ffffc900045af780 EFLAGS: 00010293
RAX: ffffffff89ca45bd RBX: 00000000fffffff4 RCX: ffff888028111e40
RDX: 0000000000000000 RSI: 00000000fffffff4 RDI: 0000000000000000
RBP: ffffc900045af870 R08: 0000000000400dc0 R09: 00000000ffffffff
R10: dffffc0000000000 R11: fffffbfff1d141db R12: ffffc900045af7e0
R13: 1ffff920008b5f24 R14: dffffc0000000000 R15: ffffc900045af920
FS: 000055557a6a5500(0000) GS:ffff888125496000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fb5ea271fc0 CR3: 000000003269e000 CR4: 00000000003526f0
Call Trace:
<TASK>
__nft_release_table+0xceb/0x11f0 net/netfilter/nf_tables_api.c:12115
nft_rcv_nl_event+0xc25/0xdb0 net/netfilter/nf_tables_api.c:12187
notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85
blocking_notifier_call_chain+0x6a/0x90 kernel/notifier.c:380
netlink_release+0x123b/0x1ad0 net/netlink/af_netlink.c:761
__sock_release net/socket.c:662 [inline]
sock_close+0xc3/0x240 net/socket.c:1455
Restrict set clone to the flush set command in the preparation phase.
Add NFT_ITER_UPDATE_CLONE and use it for this purpose, update the rbtree
and pipapo backends to only clone the set when this iteration type is
used.
As for the existing NFT_ITER_UPDATE type, update the pipapo backend to
use the existing set clone if available, otherwise use the existing set
representation. After this update, there is no need to clone a set that
is being deleted, this includes bound anonymous set.
An alternative approach to NFT_ITER_UPDATE_CLONE is to add a .clone
interface and call it from the flush set path.
Reported-by: syzbot+4924a0edc148e8b4b342@syzkaller.appspotmail.com
Fixes: 3f1d886cc7 ("netfilter: nft_set_pipapo: move cloning of match info to insert/removal path")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
In case that the set is full, a new element gets published then removed
without waiting for the RCU grace period, while RCU reader can be
walking over it already.
To address this issue, add the element transaction even if set is full,
but toggle the set_full flag to report -ENFILE so the abort path safely
unwinds the set to its previous state.
As for element updates, decrement set->nelems to restore it.
A simpler fix is to call synchronize_rcu() in the error path.
However, with a large batch adding elements to already maxed-out set,
this could cause noticeable slowdown of such batches.
Fixes: 35d0ac9070 ("netfilter: nf_tables: fix set->nelems counting with no NLM_F_EXCL")
Reported-by: Inseo An <y0un9sa@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Fix three error handling issues in FAT table operations:
1. Fix exfat_update_bh() to properly return errors from sync_dirty_buffer
2. Fix exfat_end_bh() to properly return errors from exfat_update_bh()
and exfat_mirror_bh()
3. Fix ignored return values from exfat_chain_cont_cluster() in inode.c
and namei.c
These fixes ensure that FAT table write errors are properly propagated
to the caller instead of being silently ignored.
Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
When converting files from NO_FAT_CHAIN to FAT_CHAIN format, profiling
reveals significant time spent in mark_buffer_dirty() and exfat_mirror_bh()
operations. This overhead occurs because each FAT entry modification
triggers a full block dirty marking and mirroring operation.
For consecutive clusters that reside in the same block, optimize by caching
the buffer head and performing dirty marking only once at the end of the
block's modifications.
Performance improvements for converting a 30GB file:
| Cluster Size | Before Patch | After Patch | Speedup |
|--------------|--------------|-------------|---------|
| 512 bytes | 4.243s | 1.866s | 2.27x |
| 4KB | 0.863s | 0.236s | 3.66x |
| 32KB | 0.069s | 0.034s | 2.03x |
| 256KB | 0.012s | 0.006s | 2.00x |
Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
The sector offset can be obtained from bh->b_blocknr, so drop the
redundant sec parameter from exfat_mirror_bh(). Also clean up the
function to use exfat_update_bh() helper.
No functional changes.
Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Replace the custom exfat_dir_readahead() function with the unified
exfat_blk_readahead() helper in exfat_get_dentry(). This removes
the duplicate readahead implementation and uses the common interface,
also reducing code complexity.
Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Use the newly added exfat_blk_readahead() helper in exfat_allocate_bitmap()
to simplify the code. This eliminates the duplicate inline readahead logic
and uses the unified readahead interface.
Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
When a file cannot allocate contiguous clusters, exfat converts the file
from NO_FAT_CHAIN to FAT_CHAIN format. For large files, this conversion
process can take a significant amount of time.
Add simple readahead to read all the FAT blocks in advance, as these
blocks are consecutive, significantly improving the conversion performance.
Test in an empty exfat filesystem:
dd if=/dev/zero of=/mnt/file bs=1M count=30k
dd if=/dev/zero of=/mnt/file2 bs=1M count=1
time cat /mnt/file2 >> /mnt/file
| cluster size | before patch | after patch |
| ------------ | ------------ | ----------- |
| 512 | 47.667s | 4.316s |
| 4k | 6.436s | 0.541s |
| 32k | 0.758s | 0.071s |
| 256k | 0.117s | 0.011s |
Signed-off-by: Chi Zhiling <chizhiling@kylinos.cn>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Make code printing pointer error value a bit simpler and fix coccinelle
suggestion:
tegra/mc.c:975:4-11: WARNING: Consider using %pe to print PTR_ERR()
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://patch.msgid.link/20260226-memory-simplify-v1-4-ccb94f378628@oss.qualcomm.com
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Use dev_err_probe() to simplify the code and fix Coccinelle warning:
tegra/mc.c:513:52-59: WARNING: Consider using %pe to print PTR_ERR()
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://patch.msgid.link/20260226-memory-simplify-v1-3-ccb94f378628@oss.qualcomm.com
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
tegra_mc_setup_latency_allowance() only succeeds, thus its return value
can be dropped making code a bit simpler.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://patch.msgid.link/20260226-memory-simplify-v1-2-ccb94f378628@oss.qualcomm.com
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Use dev_err_probe() to simplify the code and fix Coccinelle warning:
renesas-rpc-if.c:1010:3-10: WARNING: Consider using %pe to print PTR_ERR()
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260226-memory-simplify-v1-1-ccb94f378628@oss.qualcomm.com
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Add MAC address to vPort configuration success message and update error
message to be more specific about HWC message errors in
mana_send_request.
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260302174204.234837-1-ernis@linux.microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
After acquiring netdev_queue::_xmit_lock the number of the CPU owning
the lock is recorded in netdev_queue::xmit_lock_owner. This works as
long as the BH context is not preemptible.
On PREEMPT_RT the softirq context is preemptible and without the
softirq-lock it is possible to have multiple user in __dev_queue_xmit()
submitting a skb on the same CPU. This is fine in general but this means
also that the current CPU is recorded as netdev_queue::xmit_lock_owner.
This in turn leads to the recursion alert and the skb is dropped.
Instead checking the for CPU number, that owns the lock, PREEMPT_RT can
check if the lockowner matches the current task.
Add netif_tx_owned() which returns true if the current context owns the
lock by comparing the provided CPU number with the recorded number. This
resembles the current check by negating the condition (the current check
returns true if the lock is not owned).
On PREEMPT_RT use rt_mutex_owner() to return the lock owner and compare
the current task against it.
Use the new helper in __dev_queue_xmit() and netif_local_xmit_active()
which provides a similar check.
Update comments regarding pairing READ_ONCE().
Reported-by: Bert Karwatzki <spasswolf@web.de>
Closes: https://lore.kernel.org/all/20260216134333.412332-1-spasswolf@web.de
Fixes: 3253cb49cb ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reported-by: Bert Karwatzki <spasswolf@web.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20260302162631.uGUyIqDT@linutronix.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Use trylock instead of blocking lock acquisition for update_nr_hwq_lock
in queue_requests_store() and elv_iosched_store() to avoid circular lock
dependency with kernfs active reference during concurrent disk deletion:
update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del)
kn->active -> update_nr_hwq_lock (via sysfs write path)
Return -EBUSY when the lock is not immediately available.
Reported-and-tested-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-block/CAHj4cs-em-4acsHabMdT=jJhXkCzjnprD-aQH1OgrZo4nTnmMw@mail.gmail.com/
Fixes: 626ff4f8eb ("blk-mq: convert to serialize updating nr_requests with update_nr_hwq_lock")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Extend the VAR allocation UAPI to accept an optional flags attribute,
allowing userspace to request TLP VAR allocation via the
MLX5_IB_UAPI_VAR_ALLOC_FLAG_TLP flag.
When the TLP flag "MLX5_IB_UAPI_VAR_ALLOC_FLAG_TLP" is specified,
the driver selects the TLP VAR region for allocation instead of the
regular VirtIO VAR region.
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Add support for TLP (Transaction Layer Packet) VAR regions used by
software-defined device emulation. TLP VAR provides dedicated response
gateways for sending TLP responses back to the host in TLP emulation
scenarios.
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Extract mlx5_var_region struct from mlx5_var_table to enable
supporting multiple VAR regions in VAR table, which will be used in
the upcoming patches (Virtio emulation VAR and TLP emulation VAR).
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
This series adds support for Transaction Layer Packet (TLP) emulation
response gateway regions, enabling userspace device emulation software
to write TLP responses directly to lower layers without kernel driver
involvement.
Currently, the mlx5 driver exposes VirtIO emulation access regions via
the MLX5_IB_METHOD_VAR_OBJ_ALLOC ioctl. This series extends that
ioctl to also support allocating TLP response gateway channels for
PCI device emulation use cases.
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Allow netlink users, through the usage of driver-details netlink
attribute, to get information about internal FRMR pools that use the
kernel_vendor_key FRMR key member.
Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20260226-frmr_pools-v4-11-95360b54f15e@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Allow users to set through netlink, for a specific FRMR pool, the amount
of handles that are not aged, and fill the pool to this amount.
This allows users to warm-up the FRMR pools to an expected amount of
handles with specific attributes that fits their expected usage.
Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://patch.msgid.link/20260226-frmr_pools-v4-10-95360b54f15e@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
