Add flow control mechanism between paired netdevsim devices to stop the
TX queue during high traffic scenarios. When a receive queue becomes
congested (approaching NSIM_RING_SIZE limit), the corresponding transmit
queue on the peer device is stopped using netif_subqueue_try_stop().
Once the receive queue has sufficient capacity again, the peer's
transmit queue is resumed with netif_tx_wake_queue().
Key changes:
* Add nsim_stop_peer_tx_queue() to pause peer TX when RX queue is full
* Add nsim_start_peer_tx_queue() to resume peer TX when RX queue drains
* Implement queue mapping validation to ensure TX/RX queue count match
* Wake all queues during device unlinking to prevent stuck queues
* Use RCU protection when accessing peer device references
* wake the queues when changing the queue numbers
* Remove IFF_NO_QUEUE given it will enqueue packets now
The flow control only activates when devices have matching TX/RX queue
counts to ensure proper queue mapping.
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250711-netdev_flow_control-v3-1-aa1d5a155762@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Added a test for variable PMTU in broadcast routes.
This test uses iputils' ping and attempts to send a ping between
two peers, which should result in a regular echo reply.
This test will fail when the receiving peer does not receive the echo
request due to a lack of packet fragmentation.
Signed-off-by: Oscar Maes <oscmaes92@gmail.com>
Link: https://patch.msgid.link/20250710142714.12986-2-oscmaes92@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, __mkroute_output overrules the MTU value configured for
broadcast routes.
This buggy behaviour can be reproduced with:
ip link set dev eth1 mtu 9000
ip route del broadcast 192.168.0.255 dev eth1 proto kernel scope link src 192.168.0.2
ip route add broadcast 192.168.0.255 dev eth1 proto kernel scope link src 192.168.0.2 mtu 1500
The maximum packet size should be 1500, but it is actually 8000:
ping -b 192.168.0.255 -s 8000
Fix __mkroute_output to allow MTU values to be configured for
for broadcast routes (to support a mixed-MTU local-area-network).
Signed-off-by: Oscar Maes <oscmaes92@gmail.com>
Link: https://patch.msgid.link/20250710142714.12986-1-oscmaes92@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----
iQFHBAABCgAxFiEEn/sM2K9nqF/8FWzzDHRl3/mQkZwFAmhw48wTHG1rbEBwZW5n
dXRyb25peC5kZQAKCRAMdGXf+ZCRnMWyCACNCHDSMr0BVzC2461MjsEmfi5P4Ri7
+9qL7oV5YWL3WDO8ltId0F8Up+WX8TeDIjzzx1z5tTZ1wgCSgoN74dIfkHRjaLzT
5u+D5880GrgtUUBsZCl6eY+uqazsMnZQHSDi69/KTaii8jW4YH+/mH5hgxoVUBAX
QHuMxcHQSn4lo8w31ChUVNVCFtUllZZRfdRzZX/JctFHLfUK17R04xyjzsWJDZm9
GxQwmu0Me7NFPipb1YzlDNu747XpTTnqBFNFjYJdzgkBgR7Ypy+yVng2h5j3PEy4
XGECdyfU9zmhP1ddn5k4J7H3OaWSsba5IwKwGU0zw5FHXFpfaxd7wcrb
=ELzu
-----END PGP SIGNATURE-----
Merge tag 'linux-can-next-for-6.17-20250711' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next
Marc Kleine-Budde says:
====================
pull-request: can-next 2025-07-11
The first patch is by Geert Uytterhoeven and converts the rcar_can
driver to DEFINE_SIMPLE_DEV_PM_OPS.
The last patch is by Biju Das and removes unused macros from the
rcar_canfd driver.
* tag 'linux-can-next-for-6.17-20250711' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next:
can: rcar_canfd: Drop unused macros
can: rcar_can: Convert to DEFINE_SIMPLE_DEV_PM_OPS()
====================
Link: https://patch.msgid.link/20250711101706.2822687-1-mkl@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
x25_terminate_link() has been unused since the last use was removed
in 2020 by:
commit 7eed751b3b ("net/x25: handle additional netdev events")
Remove it.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Acked-by: Martin Schiller <ms@dev.tdt.de>
Link: https://patch.msgid.link/20250712205759.278777-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As described in a previous commit [1], Lion's patch [2] revealed an ancient
bug in the qdisc API. Whenever a user tries to add a qdisc to an
invalid parent (not a class, root, or ingress qdisc), the qdisc API will
detect this after qdisc_create is called. Some qdiscs (like fq_codel, pie,
and sfq) call functions (on their init callback) which assume the parent is
valid, so qdisc_create itself may have caused a NULL pointer dereference in
such cases.
This commit creates 3 TDC tests that attempt to add fq_codel, pie and sfq
qdiscs to invalid parents
- Attempts to add an fq_codel qdisc to an hhf qdisc parent
- Attempts to add a pie qdisc to a drr qdisc parent
- Attempts to add an sfq qdisc to an inexistent hfsc classid (which would
belong to a valid hfsc qdisc)
[1] https://lore.kernel.org/all/20250707210801.372995-1-victor@mojatatu.com/
[2] https://lore.kernel.org/netdev/d912cbd7-193b-4269-9857-525bee8bbb6a@gmail.com/
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20250712145035.705156-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
I missed adding rss_api.py to the Makefile. The NIPA Makefile
checking script was scanning for shell scripts only, so it
didn't flag it either.
Fixes: 4d13c6c449 ("selftests: drv-net: test RSS Netlink notifications")
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250712012005.4010263-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The buffer bgx_sel used in snprintf() was too small to safely hold
the formatted string "BGX%d" for all valid bgx_id values. This caused
a -Wformat-truncation warning with `Werror` enabled during build.
Increase the buffer size from 5 to 7 and use `sizeof(bgx_sel)` in
snprintf() to ensure safety and suppress the warning.
Build warning:
CC drivers/net/ethernet/cavium/thunder/thunder_bgx.o
drivers/net/ethernet/cavium/thunder/thunder_bgx.c: In function
‘bgx_acpi_match_id’:
drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1434:27: error: ‘%d’
directive output may be truncated writing between 1 and 3 bytes into a
region of size 2 [-Werror=format-truncation=]
snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);
^~
drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1434:23: note:
directive argument in the range [0, 255]
snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);
^~~~~~~
drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1434:2: note:
‘snprintf’ output between 5 and 7 bytes into a destination of size 5
snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);
compiler warning due to insufficient snprintf buffer size.
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250711140532.2463602-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In the current driver, the MAC address is set in both fec_restart() and
fec_set_mac_address(), so a generic helper function fec_set_hw_mac_addr()
is added to set the hardware MAC address to make the code more compact.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250711091639.1374411-4-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
There are also some RCR bits that are not defined but are used by the
driver, so add macro definitions for these bits to improve readability
and maintainability.
In addition, although FEC_RCR_HALFDPX has been defined, it is not used
in the driver. According to the description of FEC_RCR[1] in RM, it is
used to disable receive on transmit. Therefore, it is more appropriate
to redefine FEC_RCR[1] as FEC_RCR_DRT.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250711091639.1374411-3-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Use the generic helper function phy_interface_mode_is_rgmii() to check
RGMII mode.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250711091639.1374411-2-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This is a follow-up for commit eb1ac9ff6c ("ipv6: anycast: Don't
hold RTNL for IPV6_JOIN_ANYCAST.").
We should not add a new device lookup API without netdevice_tracker.
Let's pass netdevice_tracker to dev_get_by_flags_rcu() and rename it
with netdev_ prefix to match other newer APIs.
Note that we always use GFP_ATOMIC for netdev_hold() as it's expected
to be called under RCU.
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/netdev/20250708184053.102109f6@kernel.org/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250711051120.2866855-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The Renesas RZ/G3E SMARC EVK uses KSZ9131RNXC phy. On deep power state,
PHY loses the power and on wakeup the rgmii delays are not reconfigured
causing it to fail.
Replace the callback kszphy_resume()->ksz9131_resume() for reconfiguring
the rgmii_delay when it exits from PM suspend state.
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250711054029.48536-1-biju.das.jz@bp.renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
kernel test robot reports that xtensa complains about different
signedness for a min_not_zero() comparison. Cast the int part to size_t
to avoid this issue.
Fixes: e227c8cdb4 ("io_uring/net: use passed in 'len' in io_recv_buf_select()")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202507150504.zO5FsCPm-lkp@intel.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Reject the KVM_SET_TSC_KHZ VM ioctl when vCPUs have been created and
update the documentation to reflect it.
The VM scope KVM_SET_TSC_KHZ ioctl is used to set up the default TSC
frequency that all subsequently created vCPUs can use. It is only
intended to be called before any vCPU is created. Allowing it to be
called after that only results in confusion but nothing good.
Note this is an ABI change. But currently in Qemu (the de facto
userspace VMM) only TDX uses this VM ioctl, and it is only called once
before creating any vCPU, therefore the risk of breaking userspace is
pretty low.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
Reviewed-by: Nikunj A Dadhania <nikunj@amd.com>
Link: https://lore.kernel.org/r/135a35223ce8d01cea06b6cef30bfe494ec85827.1752444335.git.kai.huang@intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Enable internal clock gating for Qualcomm UFS host controller by setting
the following attributes to 1 during host controller initialization:
- DL_VS_CLK_CFG
- PA_VS_CLK_CFG_REG
- DME_VS_CORE_CLK_CTRL.DME_HW_CGC_EN
This change is necessary to support the internal clock gating mechanism
in Qualcomm UFS host controller. This is power saving feature and hence
driver can continue to function correctly despite any error in enabling
these feature.
Signed-off-by: Nitin Rawat <quic_nitirawa@quicinc.com>
Link: https://lore.kernel.org/r/20250714075336.2133-4-quic_nitirawa@quicinc.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Introduce ufshcd_dme_rmw() API to read, modify, and write DME attributes
in UFS host controllers using a mask and value.
Signed-off-by: Nitin Rawat <quic_nitirawa@quicinc.com>
Link: https://lore.kernel.org/r/20250714075336.2133-3-quic_nitirawa@quicinc.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
The MCQ feature and ESI are supported by all Qualcomm UFS controller
versions 6 and above.
Therefore, update the ESI vector mask in the UFS_MEM_CFG3 register for
platforms with major version number of 6 or higher.
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Signed-off-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Nitin Rawat <quic_nitirawa@quicinc.com>
Link: https://lore.kernel.org/r/20250714075336.2133-2-quic_nitirawa@quicinc.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
At the end of the isect translation, disc_addr represents the physical
disk offset. Thus, end calculated from disk_addr is also a physical disk
offset. Therefore, range checking should be done using map->disk_offset,
not map->start.
Signed-off-by: Sergey Bashirov <sergeybashirov@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250702133226.212537-1-sergeybashirov@gmail.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
When there are too many block extents for a layoutcommit, they may not
all fit into the maximum-sized RPC. This patch allows the generic pnfs
code to properly handle -ENOSPC returned by the block/scsi layout driver
and trigger additional layoutcommits if necessary.
Co-developed-by: Konstantin Evtushenko <koevtushenko@yandex.com>
Signed-off-by: Konstantin Evtushenko <koevtushenko@yandex.com>
Signed-off-by: Sergey Bashirov <sergeybashirov@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250630183537.196479-5-sergeybashirov@gmail.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
The ext_tree_encode_commit() function may be called multiple times for
the same file, layout, and last written byte if the provided buffer is
not large enough to encode all extents in it.
The first problem is that the last written byte field must be zeroed
only on a successful call, otherwise we will lose its actual value and
get an integer overflow on the next encoding attempt.
The second problem is that we can't count and encode in one pass. The
extent state changes during encoding, so if we return -ENOSPC but have
already encoded some extents into a small buffer, they will not be
re-encoded into a new larger buffer on the next try. As a result, the
client never commits these extents to the server.
Co-developed-by: Konstantin Evtushenko <koevtushenko@yandex.com>
Signed-off-by: Konstantin Evtushenko <koevtushenko@yandex.com>
Signed-off-by: Sergey Bashirov <sergeybashirov@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250630183537.196479-3-sergeybashirov@gmail.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
The error occurs on the third attempt to encode extents. When function
ext_tree_prepare_commit() reallocates a larger buffer to retry encoding
extents, the "layoutupdate_pages" page array is initialized only after the
retry loop. But ext_tree_free_commitdata() is called on every iteration
and tries to put pages in the array, thus dereferencing uninitialized
pointers.
An additional problem is that there is no limit on the maximum possible
buffer_size. When there are too many extents, the client may create a
layoutcommit that is larger than the maximum possible RPC size accepted
by the server.
During testing, we observed two typical scenarios. First, one memory page
for extents is enough when we work with small files, append data to the
end of the file, or preallocate extents before writing. But when we fill
a new large file without preallocating, the number of extents can be huge,
and counting the number of written extents in ext_tree_encode_commit()
does not help much. Since this number increases even more between
unlocking and locking of ext_tree, the reallocated buffer may not be
large enough again and again.
Co-developed-by: Konstantin Evtushenko <koevtushenko@yandex.com>
Signed-off-by: Konstantin Evtushenko <koevtushenko@yandex.com>
Signed-off-by: Sergey Bashirov <sergeybashirov@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250630183537.196479-2-sergeybashirov@gmail.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
nfs_umount() has been unused since 2013's
commit 4580a92d44 ("NFS: Use server-recommended security flavor by
default (NFSv3)")
Remove it.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20250218215250.263709-1-linux@treblig.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Remove a bunch of unused xdr_*decode* functions:
The last use of xdr_decode_netobj() was removed in 2021 by:
commit 7cf96b6d01 ("lockd: Update the NLMv4 SHARE arguments decoder to
use struct xdr_stream")
The last use of xdr_decode_string_inplace() was removed in 2021 by:
commit 3049e974a7 ("lockd: Update the NLMv4 FREE_ALL arguments decoder
to use struct xdr_stream")
The last use of xdr_stream_decode_opaque() was removed in 2024 by:
commit fed8a17c61 ("xdrgen: typedefs should use the built-in string and
opaque functions")
The functions xdr_stream_decode_string() and
xdr_stream_decode_opaque_dup() were both added in 2018 by the
commit 0e779aa703 ("SUNRPC: Add helpers for decoding opaque and string
types")
but never used.
Remove them.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20250712233006.403226-1-linux@treblig.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Create a kernel .nfs keyring similar to the nvme .nvme one. Unlike for
a userspace-created keyrind, tlshd is a possesor of the keys with this
and thus the keys don't need user read permissions.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Link: https://lore.kernel.org/r/20250515115107.33052-3-hch@lst.de
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Allow tlshd to use a per-mount key from the kernel keyring similar
to NVMe over TCP.
Note that tlshd expects keys and certificates stored in the kernel
keyring to be in DER format, not the PEM format used for file based keys
and certificates, so they need to be converted before they are added
to the keyring, which is a bit unexpected.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Link: https://lore.kernel.org/r/20250515115107.33052-2-hch@lst.de
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
When the mode is MIGRATE_SYNC, we are allowed to call nfs_wb_folio()
under the folio lock.
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Add new tracepoints in the NFSv4 match_stateid minorversion op that show
the info in both stateids.
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20250618-nfs-tracepoints-v2-4-540c9fb48da2@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Add a tracepoint in the function that decides whether to return a
delegation to the server.
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20250618-nfs-tracepoints-v2-3-540c9fb48da2@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
We have tracepoints for setting a delegation and reclaiming them. Add a
tracepoint for when the delegation is being detached from the inode.
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20250618-nfs-tracepoints-v2-2-540c9fb48da2@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Managing the cache_validity flags is the deep voodoo of NFS cache
coherency. Let's have a little extra visibility into that value via the
nfs_inode_event tracepoints.
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20250618-nfs-tracepoints-v2-1-540c9fb48da2@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
The last code that was using this was removed via commit 20d655d619
("pnfs/blocklayout: use the device id cache") which was merged in
v3.18-rc1, so it can be removed completely.
Signed-off-by: Anthony Iliopoulos <ailiop@suse.com>
Link: https://lore.kernel.org/r/20250613094439.82338-4-ailiop@suse.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
The last code that was using this was removed via commit ca0daa277a
("NFS: Cache aggressively when file is open for writing") which was
merged in v4.8-rc1, so it can be removed completely.
Signed-off-by: Anthony Iliopoulos <ailiop@suse.com>
Link: https://lore.kernel.org/r/20250613094439.82338-3-ailiop@suse.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
The wpages field is not serving any purpose since commit c63c7b0513
("NFS: Fix a race when doing NFS write coalescing") which was merged in
v2.6.22-rc1. Remove it completely.
Signed-off-by: Anthony Iliopoulos <ailiop@suse.com>
Link: https://lore.kernel.org/r/20250613094439.82338-2-ailiop@suse.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Rather than open-coding this function call it to make intention clear
and to use "correct" nesting levels (parent and child are for
directories).
This is purely cosmetic with no expected change in behaviour.
Signed-off-by: NeilBrown <neil@brown.name>
Link: https://lore.kernel.org/r/174942091741.608730.3327223511347232829@noble.neil.brown.name
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Add tracking of the create time (a.k.a. btime) along with corresponding
bitfields, request, and decode xdr routines.
Signed-off-by: Anne Marie Merritt <annemarie.merritt@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/1e3677b0655fa2bbaba0817b41d111d94a06e5ee.1748515333.git.bcodding@redhat.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
We need to be able to track more than 32 attributes per inode.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/1e3405fca54efd0be7c91c1da77917b94f5dfcc4.1748515333.git.bcodding@redhat.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
On AMD CPUs without ensuring cache consistency, each memory page
reclamation in an SEV guest triggers a call to do WBNOINVD/WBINVD on all
CPUs, thereby affecting the performance of other programs on the host.
Typically, an AMD server may have 128 cores or more, while the SEV guest
might only utilize 8 of these cores. Meanwhile, host can use qemu-affinity
to bind these 8 vCPUs to specific physical CPUs.
Therefore, keeping a record of the physical core numbers each time a vCPU
runs can help avoid flushing the cache for all CPUs every time.
Take care to allocate the cpumask used to track which CPUs have run a
vCPU when copying or moving an "encryption context", as nothing guarantees
memory in a mirror VM is a strict subset of the ASID owner, and the
destination VM for intrahost migration needs to maintain it's own set of
CPUs. E.g. for intrahost migration, if a CPU was used for the source VM
but not the destination VM, then it can only have cached memory that was
accessible to the source VM. And a CPU that was run in the source is also
used by the destination is no different than a CPU that was run in the
destination only.
Note, KVM is guaranteed to do flush caches prior to sev_vm_destroy(),
thanks to kvm_arch_guest_memory_reclaimed for SEV and SEV-ES, and
kvm_arch_gmem_invalidate() for SEV-SNP. I.e. it's safe to free the
cpumask prior to unregistering encrypted regions and freeing the ASID.
Opportunistically clean up sev_vm_destroy()'s comment regarding what is
(implicitly, what isn't) skipped for mirror VMs.
Cc: Srikanth Aithal <sraithal@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Zheyun Shen <szy0127@sjtu.edu.cn>
Link: https://lore.kernel.org/r/20250522233733.3176144-9-seanjc@google.com
Link: https://lore.kernel.org/all/935a82e3-f7ad-47d7-aaaf-f3d2b62ed768@amd.com
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Jordan Rife says:
====================
bpf: tcp: Exactly-once socket iteration
TCP socket iterators use iter->offset to track progress through a
bucket, which is a measure of the number of matching sockets from the
current bucket that have been seen or processed by the iterator. On
subsequent iterations, if the current bucket has unprocessed items, we
skip at least iter->offset matching items in the bucket before adding
any remaining items to the next batch. However, iter->offset isn't
always an accurate measure of "things already seen" when the underlying
bucket changes between reads, which can lead to repeated or skipped
sockets. Instead, this series remembers the cookies of the sockets we
haven't seen yet in the current bucket and resumes from the first cookie
in that list that we can find on the next iteration.
This is a continuation of the work started in [1]. This series largely
replicates the patterns applied to UDP socket iterators, applying them
instead to TCP socket iterators.
CHANGES
=======
v5 -> v6:
* In patch ten ("selftests/bpf: Create established sockets in socket
iterator tests"), use poll() to choose a socket that has a connection
ready to be accept()ed. Before, connect_to_server would set the
O_NONBLOCK flag on all listening sockets so that accept_from_one could
loop through them all and find the one that connect_to_addr_str
connected to. However, this is subtly buggy and could potentially lead
to test flakes, since the 3 way handshake isn't necessarily done when
connect returns, so it's possible none of the accept() calls succeed.
Use poll() instead to guarantee that the socket we accept() from is
ready and eliminate the need for the O_NONBLOCK flag (Martin).
v4 -> v5:
* Move WARN_ON_ONCE before the `done` label in patch two ("bpf: tcp:
Make sure iter->batch always contains a full bucket snapshot"")
(Martin).
* Remove unnecessary kfunc declaration in patch eleven ("selftests/bpf:
Create iter_tcp_destroy test program") (Martin).
* Make sure to close the socket fd at the end of `destroy` in patch
twelve ("selftests/bpf: Add tests for bucket resume logic in
established sockets") (Martin).
v3 -> v4:
* Drop braces around sk_nulls_for_each_from in patch five ("bpf: tcp:
Avoid socket skips and repeats during iteration") (Stanislav).
* Add a break after the TCP_SEQ_STATE_ESTABLISHED case in patch five
(Stanislav).
* Add an `if (sock_type == SOCK_STREAM)` check before assigning
TCP_LISTEN to skel->rodata->ss in patch eight ("selftests/bpf: Allow
for iteration over multiple states") to more clearly express the
intent that the option is only consumed for SOCK_STREAM tests
(Stanislav).
* Move the `i = 0` assignment into the for loop in patch ten
("selftests/bpf: Create established sockets in socket iterator
tests") (Stanislav).
v2 -> v3:
* Unroll the loop inside bpf_iter_tcp_batch to make the logic easier to
follow in patch two ("bpf: tcp: Make sure iter->batch always contains
a full bucket snapshot"). This gets rid of the `resizes` variable from
v2 and eliminates the extra conditional that checks how many batch
resize attempts have occurred so far (Stanislav).
Note: This changes the behavior slightly. Before, in the case that
the second call to tcp_seek_last_pos (and later bpf_iter_tcp_resume)
advances to a new bucket, which may happen if the current bucket is
emptied after releasing its lock, the `resizes` "budget" would be
reset, the net effect being that we would try a batch resize with
GFP_USER at most once per bucket. Now, we try to resize the batch
with GFP_USER at most once per call, so it makes it slightly more
likely that we hit the GFP_NOWAIT scenario. However, this edge case
should be rare in practice anyway, and the new behavior is more or
less consistent with the original retry logic, so avoid the loop and
prefer code clarity.
* Move the call to bpf_iter_tcp_put_batch out of
bpf_iter_tcp_realloc_batch and call it directly before invoking
bpf_iter_tcp_realloc_batch with GFP_USER inside bpf_iter_tcp_batch.
/Don't/ call it before invoking bpf_iter_tcp_realloc_batch the second
time while we hold the lock with GFP_NOWAIT. This avoids a conditional
inside bpf_iter_tcp_realloc_batch from v2 that only calls
bpf_iter_tcp_put_batch if flags != GFP_NOWAIT and is a bit more
explicit (Stanislav).
* Adjust patch five ("bpf: tcp: Avoid socket skips and repeats during
iteration") to fit with the new logic in patch two.
v1 -> v2:
* In patch five ("bpf: tcp: Avoid socket skips and repeats during
iteration"), remove unnecessary bucket bounds checks in
bpf_iter_tcp_resume. In either case, if st->bucket is outside the
current table's range then bpf_iter_tcp_resume_* calls *_get_first
which immediately returns NULL anyway and the logic will fall through.
(Martin)
* Add a check at the top of bpf_iter_tcp_resume_listening and
bpf_iter_tcp_resume_established to see if we're done with the current
bucket and advance it immediately instead of wasting time finding the
first matching socket in that bucket with
(listening|established)_get_first. In v1, we originally discussed
adding logic to advance the bucket in bpf_iter_tcp_seq_next and
bpf_iter_tcp_seq_stop, but after trying this the logic seemed harder
to track. Overall, keeping everything inside bpf_iter_tcp_resume_*
seemed a bit clearer. (Martin)
* Instead of using a timeout in the last patch ("selftests/bpf: Add
tests for bucket resume logic in established sockets") to wait for
sockets to leave the ehash table after calling close(), use
bpf_sock_destroy to deterministically destroy and remove them. This
introduces one more patch ("selftests/bpf: Create iter_tcp_destroy
test program") to create the iterator program that destroys a selected
socket. Drive this through a destroy() function in the last patch
which, just like close(), accepts a socket file descriptor. (Martin)
* Introduce one more patch ("selftests/bpf: Allow for iteration over
multiple states") to fix a latent bug in iter_tcp_soreuse where the
sk->sk_state != TCP_LISTEN check was ignored. Add the "ss" variable to
allow test code to configure which socket states to allow.
[1]: https://lore.kernel.org/bpf/20250502161528.264630-1-jordan@jrife.io/
====================
Link: https://patch.msgid.link/20250714180919.127192-1-jordan@jrife.io
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Replicate the set of test cases used for UDP socket iterators to test
similar scenarios for TCP established sockets.
Signed-off-by: Jordan Rife <jordan@jrife.io>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Prepare for bucket resume tests for established TCP sockets by creating
a program to immediately destroy and remove sockets from the TCP ehash
table, since close() is not deterministic.
Signed-off-by: Jordan Rife <jordan@jrife.io>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Prepare for bucket resume tests for established TCP sockets by creating
established sockets. Collect socket fds from connect() and accept()
sides and pass them to test cases.
Signed-off-by: Jordan Rife <jordan@jrife.io>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Prepare for bucket resume tests for established TCP sockets by making
the number of ehash buckets configurable. Subsequent patches force all
established sockets into the same bucket by setting ehash_buckets to
one.
Signed-off-by: Jordan Rife <jordan@jrife.io>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
