Since commit 88d26136a2 ("PM: Prevent runtime suspend during system
resume"), PM runtime will not let devices idle during system suspend.
This is because of the pm_runtime_get_noresume() call done in
device_prepare() that is not released until at device_complete() after
resume.
We must now disable the USB PHY in suspend if no USB cable is connected.
Cc: Andreas Kemnade <andreas@kemnade.info>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20210727104512.52968-1-tony@atomide.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The controller is designed to use use PLL integer mode, but
in fact used fractional mode for some ones on mt8195, this
causes signal degradation (e.g. eye diagram test fail), fix
it by switching PLL to 26Mhz from default 48Mhz to improve
signal quality.
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/1627028562-23584-3-git-send-email-chunfeng.yun@mediatek.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The PHYA arch is updated, and doesn't support slew rate calibrate
anymore on 7nm or advanced process, add a new version number to
support it.
Note: the FreqMeter bank is not used but reserved.
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/1627028562-23584-2-git-send-email-chunfeng.yun@mediatek.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The PHYA architecture is updated, and doesn't support slew rate
calibration anymore on 7nm or advanced process, add a new version
number to support it.
Due to the FreqMeter bank is not used but reserved, it's backward
with v2 until now.
For mt8195, no function changes when use generic v2 or v3 compatible,
but prefer to use v3's compatible, it will not waste the time to
calibrate the slew rate, and also correspond with hardware version.
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/1627028562-23584-1-git-send-email-chunfeng.yun@mediatek.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Introduce a new option to dirty_log_perf_test: -x number_of_slots. This
causes the test to attempt to split the region of memory into the given
number of slots. If the region cannot be evenly divided, the test will
fail.
This allows testing with more than one slot and therefore measure how
performance scales with the number of memslots.
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-8-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
gfn_to_rmap was removed in the previous patch so there is no need to
retain the double underscore on __gfn_to_rmap.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-7-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
rmap_add() and rmap_recycle() both run in the context of the vCPU and
thus we can use kvm_vcpu_gfn_to_memslot() to look up the memslot. This
enables rmap_add() and rmap_recycle() to take advantage of
vcpu->last_used_slot and avoid expensive memslot searching.
This change improves the performance of "Populate memory time" in
dirty_log_perf_test with tdp_mmu=N. In addition to improving the
performance, "Populate memory time" no longer scales with the number
of memslots in the VM.
Command | Before | After
------------------------------- | ---------------- | -------------
./dirty_log_perf_test -v64 -x1 | 15.18001570s | 14.99469366s
./dirty_log_perf_test -v64 -x64 | 18.71336392s | 14.98675076s
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-6-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The existing TDP MMU methods to handle dirty logging are vcpu-agnostic
since they can be driven by MMU notifiers and other non-vcpu-specific
events in addition to page faults. However this means that the TDP MMU
is not benefiting from the new vcpu->last_used_slot. Fix that by
introducing a tdp_mmu_map_set_spte_atomic() which is only called during
a TDP page fault and has access to the kvm_vcpu for fast slot lookups.
This improves "Populate memory time" in dirty_log_perf_test by 5%:
Command | Before | After
------------------------------- | ---------------- | -------------
./dirty_log_perf_test -v64 -x64 | 5.472321072s | 5.169832886s
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-5-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The memslot for a given gfn is looked up multiple times during page
fault handling. Avoid binary searching for it multiple times by caching
the most recently used slot. There is an existing VM-wide last_used_slot
but that does not work well for cases where vCPUs are accessing memory
in different slots (see performance data below).
Another benefit of caching the most recently use slot (versus looking
up the slot once and passing around a pointer) is speeding up memslot
lookups *across* faults and during spte prefetching.
To measure the performance of this change I ran dirty_log_perf_test with
64 vCPUs and 64 memslots and measured "Populate memory time" and
"Iteration 2 dirty memory time". Tests were ran with eptad=N to force
dirty logging to use fast_page_fault so its performance could be
measured.
Config | Metric | Before | After
---------- | ----------------------------- | ------ | ------
tdp_mmu=Y | Populate memory time | 6.76s | 5.47s
tdp_mmu=Y | Iteration 2 dirty memory time | 2.83s | 0.31s
tdp_mmu=N | Populate memory time | 20.4s | 18.7s
tdp_mmu=N | Iteration 2 dirty memory time | 2.65s | 0.30s
The "Iteration 2 dirty memory time" results are especially compelling
because they are equivalent to running the same test with a single
memslot. In other words, fast_page_fault performance no longer scales
with the number of memslots.
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Make search_memslots unconditionally search all memslots and move the
last_used_slot logic up one level to __gfn_to_memslot. This is in
preparation for introducing a per-vCPU last_used_slot.
As part of this change convert existing callers of search_memslots to
__gfn_to_memslot to avoid making any functional changes.
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
lru_slot is used to keep track of the index of the most-recently used
memslot. The correct acronym would be "mru" but that is not a common
acronym. So call it last_used_slot which is a bit more obvious.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20210804222844.1419481-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Fix errant use of "/**" to begin a comment although the comment
is not kernel-doc notation. Just use "/*" instead.
Fixes this kernel-doc warning:
drivers/phy/qualcomm/phy-qcom-usb-hs.c:3: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
* Copyright (C) 2016 Linaro Ltd
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Andy Gross <agross@kernel.org>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: linux-arm-msm@vger.kernel.org
Cc: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: linux-phy@lists.infradead.org
Link: https://lore.kernel.org/r/20210723022548.25695-1-rdunlap@infradead.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The "Arm True Random Number Generator Firmware Interface"[1] provides
an SMCCC based interface to a true hardware random number generator.
So far we are using that in arch_get_random_seed(), but it might be
useful to expose the entropy through the /dev/hwrng device as well. This
allows to assess the quality of the implementation, by using "rngtest"
from the rng-tools package, for example.
Add a simple platform driver implementing the hw_random interface.
The corresponding platform device is created by the SMCCC core code,
we just match it here by name and provide a module alias.
Since the firmware takes care about serialisation, this can happily
coexist with the arch_get_random_seed() bits.
[1] https://developer.arm.com/documentation/den0098/latest/
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
At the moment we probe for the Random Number Generator SMCCC service,
and use that in the core code (arch_get_random). However the hardware
entropy can also be useful to access from userland, and be it to assess
its quality.
Register a platform device when the SMCCC TRNG service is detected, to
allow a hw_random driver to hook onto this.
The function registering the device is deliberately made in a way which
allows expansion, so other services that could be exposed via a platform
device (or some other interface), can be added here easily.
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The commit 97f9ac3db6 ("crypto: ccp - Add support for SEV-ES to the
PSP driver") added support to allocate Trusted Memory Region (TMR)
used during the SEV-ES firmware initialization. The TMR gets locked
during the firmware initialization and unlocked during the shutdown.
While the TMR is locked, access to it is disallowed.
Currently, the CCP driver does not shutdown the firmware during the
kexec reboot, leaving the TMR memory locked.
Register a callback to shutdown the SEV firmware on the kexec boot.
Fixes: 97f9ac3db6 ("crypto: ccp - Add support for SEV-ES to the PSP driver")
Reported-by: Lucas Nussbaum <lucas.nussbaum@inria.fr>
Tested-by: Lucas Nussbaum <lucas.nussbaum@inria.fr>
Cc: <stable@kernel.org>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Acked-by: Tom Lendacky <thomas.lendacky@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Commit b0a3d8986a ("crypto: omap-sham - Use pm_runtime_irq_safe()") added
the use of pm_runtime_irq_safe() as pm_runtime_get_sync() was called
from a tasklet.
We now use the crypto engine queue instead of a custom queue since
commit 33c3d434d91 ("crypto: omap-sham - convert to use crypto engine").
We want to drop the use of pm_runtime_irq_safe() in general as it takes a
permanent usage count on the parent device causing issues for power
management.
Based on testing with CONFIG_DEBUG_ATOMIC_SLEEP=y, modprobe omap-sham,
followed by modprobe tcrypt sec=1 mode=423, I have not been able to
reproduce the scheduling while atomic issue seen earlier with current
kernels and we can just drop the call to pm_runtime_irq_safe().
Cc: Lokesh Vutla <lokeshvutla@ti.com>
Cc: Tero Kristo <kristo@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Let's get rid of the suspend and resume calls to runtime PM as these calls
do not idle the hardware. The runtime suspend has been disabled for
system suspend since commit 88d26136a2 ("PM: Prevent runtime suspend
during system resume").
Instead of runtime PM, the system suspend and resume functions should call
driver internal shared functions to idle the hardware as needed.
Cc: Lokesh Vutla <lokeshvutla@ti.com>
Cc: Tero Kristo <kristo@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
FLAGS_INIT is now unused and we can just use standard runtime PM
functions instead.
Cc: Lokesh Vutla <lokeshvutla@ti.com>
Cc: Tero Kristo <kristo@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
We should pair the usage of pm_runtime_use_autosuspend() with
pm_runtime_dont_use_autosuspend().
Cc: Lokesh Vutla <lokeshvutla@ti.com>
Cc: Tero Kristo <kristo@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Let's only initialize dd->req after omap_sham_hw_init() in case of
errors.
Looks like leaving dd->req initialized on omap_sham_hw_init() errors is
is not causing issues though as we return on errors. So this patch can be
applied as clean-up.
Cc: Lokesh Vutla <lokeshvutla@ti.com>
Cc: Tero Kristo <kristo@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
We should not clear FLAGS_DMA_ACTIVE before omap_sham_update_dma_stop() is
done calling dma_unmap_sg(). We already clear FLAGS_DMA_ACTIVE at the
end of omap_sham_update_dma_stop().
The early clearing of FLAGS_DMA_ACTIVE is not causing issues as we do not
need to defer anything based on FLAGS_DMA_ACTIVE currently. So this can be
applied as clean-up.
Cc: Lokesh Vutla <lokeshvutla@ti.com>
Cc: Tero Kristo <kristo@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Convert to jason schema.
Cc: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Li Jun <jun.li@nxp.com>
Cc: linux-phy@lists.infradead.org
Signed-off-by: Dong Aisheng <aisheng.dong@nxp.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20210715082536.1882077-5-aisheng.dong@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
For_each_available_child_of_node should have of_node_put()
before break around line 1184. The other jumps out of the
loop do contain the put.
Generated by: scripts/coccinelle/iterators/for_each_child.cocci
CC: Sumera Priyadarsini <sylphrenadin@gmail.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: kernel test robot <lkp@intel.com>
Signed-off-by: Julia Lawall <julia.lawall@inria.fr>
Link: https://lore.kernel.org/r/alpine.DEB.2.22.394.2106231617540.99238@hadrien
Signed-off-by: Vinod Koul <vkoul@kernel.org>
On s390, the following build warning occurs:
drivers/net/ethernet/marvell/mvpp2/mvpp2.h:844:2: warning: overflow in
conversion from 'long unsigned int' to 'int' changes value from
'18446744073709551584' to '-32' [-Woverflow]
844 | ((total_size) - MVPP2_SKB_HEADROOM - MVPP2_SKB_SHINFO_SIZE)
This happens because MVPP2_SKB_SHINFO_SIZE, which is 320 bytes (which is
already 64-byte aligned) on some architectures, actually gets ALIGN'd up
to 512 bytes in the s390 case.
So then, when this is invoked:
MVPP2_RX_MAX_PKT_SIZE(MVPP2_BM_SHORT_FRAME_SIZE)
...that turns into:
704 - 224 - 512 == -32
...which is not a good frame size to end up with! The warning above is a
bit lucky: it notices a signed/unsigned bad behavior here, which leads
to the real problem of a frame that is too short for its contents.
Increase MVPP2_BM_SHORT_FRAME_SIZE by 32 (from 704 to 736), which is
just exactly big enough. (The other values can't readily be changed
without causing a lot of other problems.)
Fixes: 07dd0a7aae ("mvpp2: add basic XDP support")
Cc: Sven Auhagen <sven.auhagen@voleatech.de>
Cc: Matteo Croce <mcroce@microsoft.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the missing RxUnicast counter.
Fixes: b8f126a8d5 ("net-next: dsa: add dsa support for Mediatek MT7530 switch")
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver currently still accepts untagged frames on VLAN-aware ports
without PVID. Use PVC.ACC_FRM to drop untagged frames in that case.
Signed-off-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tag for toerh trees/branches to pull from in order to have a stable base
to build off of for the "Allow deferred execution of
iomem_get_mapping()" set of sysfs changes
Link: https://lore.kernel.org/r/20210729233235.1508920-1-kw@linux.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
iG0EABECAC0WIQT0tgzFv3jCIUoxPcsxR9QN2y37KQUCYQ0XAw8cZ3JlZ0Brcm9h
aC5jb20ACgkQMUfUDdst+ymPsQCeLzeQco/wi96/nf2fhKqpAPsBtH4AoLqE8R7F
PDJCjDCLsbwL+7ZC2udo
=Fbxh
-----END PGP SIGNATURE-----
Merge tag 'sysfs_defferred_iomem_get_mapping-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core driver-core-next
sysfs: Allow deferred execution of iomem_get_mapping()
Tag for toerh trees/branches to pull from in order to have a stable base
to build off of for the "Allow deferred execution of
iomem_get_mapping()" set of sysfs changes
Link: https://lore.kernel.org/r/20210729233235.1508920-1-kw@linux.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
* tag 'sysfs_defferred_iomem_get_mapping-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
sysfs: Rename struct bin_attribute member to f_mapping
sysfs: Invoke iomem_get_mapping() from the sysfs open callback
IVO panel require less input video clock variation than video clock
variation in DP CTS spec.
This patch decreases the K value of ANX7625 which will shrink eDP Tx
video clock variation to meet IVO panel's requirement.
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Xin Ji <xji@analogixsemi.com>
Signed-off-by: Robert Foss <robert.foss@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20210806104407.2208538-1-xji@analogixsemi.com
The board features a 128MiB NAND chip and recently linux gained support
for the NAND controller on the Zynq SoC. Thus add the corresponding
devicetree nodes.
Signed-off-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20210616155437.27378-4-michael@walle.cc
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Recently, a driver for the ARM Primecell PL35x static memory controller
(including NAND controller) was added in linux. Add the corresponding
device tree node.
Signed-off-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20210616155437.27378-3-michael@walle.cc
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
After years, linux finally got a driver for the PL35x NAND controller
found on the Xilinx Zynq-7000 SoC for example. Enable support for this
driver.
Signed-off-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20210616155437.27378-2-michael@walle.cc
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
When converting arm64 to modern assembler annotations __bad_stack was left
as a raw local label without annotations. While this will have little if
any practical impact at present it may cause issues in the future if we
start using the annotations for things like reliable stack trace. Add
SYM_CODE annotations to fix this.
Signed-off-by: Mark Brown <broonie@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210804181710.19059-1-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Vladimir Oltean says:
====================
Always flood multicast to the DSA CPU port
Discussing with Qingfang, it became obvious that DSA is not prepared to
disable multicast flooding towards the CPU port under any circumstance
right now, and this in fact breaks traffic quite blatantly.
This series is a revert done in reverse chronological order. These
should be propagated to stable trees up to commit a8b659e7ff ("net:
dsa: act as passthrough for bridge port flags") which is in v5.12.
For older kernels, that commit blocks further backporting, so I need to
send a modified version of patch 3 separately to Greg after these go
into "net".
v1->v2: delete unused b53_set_mrouter function prototype
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 08cc83cc7f ("net: dsa: add support for BRIDGE_MROUTER
attribute") added an option for users to turn off multicast flooding
towards the CPU if they turn off the IGMP querier on a bridge which
already has enslaved ports (echo 0 > /sys/class/net/br0/bridge/multicast_router).
And commit a8b659e7ff ("net: dsa: act as passthrough for bridge port flags")
simply papered over that issue, because it moved the decision to flood
the CPU with multicast (or not) from the DSA core down to individual drivers,
instead of taking a more radical position then.
The truth is that disabling multicast flooding to the CPU is simply
something we are not prepared to do now, if at all. Some reasons:
- ICMP6 neighbor solicitation messages are unregistered multicast
packets as far as the bridge is concerned. So if we stop flooding
multicast, the outside world cannot ping the bridge device's IPv6
link-local address.
- There might be foreign interfaces bridged with our DSA switch ports
(sending a packet towards the host does not necessarily equal
termination, but maybe software forwarding). So if there is no one
interested in that multicast traffic in the local network stack, that
doesn't mean nobody is.
- PTP over L4 (IPv4, IPv6) is multicast, but is unregistered as far as
the bridge is concerned. This should reach the CPU port.
- The switch driver might not do FDB partitioning. And since we don't
even bother to do more fine-grained flood disabling (such as "disable
flooding _from_port_N_ towards the CPU port" as opposed to "disable
flooding _from_any_port_ towards the CPU port"), this breaks standalone
ports, or even multiple bridges where one has an IGMP querier and one
doesn't.
Reverting the logic makes all of the above work.
Fixes: a8b659e7ff ("net: dsa: act as passthrough for bridge port flags")
Fixes: 08cc83cc7f ("net: dsa: add support for BRIDGE_MROUTER attribute")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
DSA's idea of optimizing out multicast flooding to the CPU port leaves
quite a few holes open, so it should be reverted.
The mt7530 driver is the only new driver which added a .port_set_mrouter
implementation after the reorg from commit a8b659e7ff ("net: dsa: act
as passthrough for bridge port flags"), so it needs to be reverted
separately so that the other revert commit can go a bit further down the
git history.
Fixes: 5a30833b9a ("net: dsa: mt7530: support MDB and bridge flag operations")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Qingfang points out that when a bridge with the default settings is
created and a port joins it:
ip link add br0 type bridge
ip link set swp0 master br0
DSA calls br_multicast_router() on the bridge to see if the br0 device
is a multicast router port, and if it is, it enables multicast flooding
to the CPU port, otherwise it disables it.
If we look through the multicast_router_show() sysfs or at the
IFLA_BR_MCAST_ROUTER netlink attribute, we see that the default mrouter
attribute for the bridge device is "1" (MDB_RTR_TYPE_TEMP_QUERY).
However, br_multicast_router() will return "0" (MDB_RTR_TYPE_DISABLED),
because an mrouter port in the MDB_RTR_TYPE_TEMP_QUERY state may not be
actually _active_ until it receives an actual IGMP query. So, the
br_multicast_router() function should really have been called
br_multicast_router_active() perhaps.
When/if an IGMP query is received, the bridge device will transition via
br_multicast_mark_router() into the active state until the
ip4_mc_router_timer expires after an multicast_querier_interval.
Of course, this does not happen if the bridge is created with an
mcast_router attribute of "2" (MDB_RTR_TYPE_PERM).
The point is that in lack of any IGMP query messages, and in the default
bridge configuration, unregistered multicast packets will not be able to
reach the CPU port through flooding, and this breaks many use cases
(most obviously, IPv6 ND, with its ICMP6 neighbor solicitation multicast
messages).
Leave the multicast flooding setting towards the CPU port down to a driver
level decision.
Fixes: 010e269f91 ("net: dsa: sync up switchdev objects and port attributes when joining the bridge")
Reported-by: DENG Qingfang <dqfext@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch enables support for hard irqs deferral feature from Eric Dumazet
[1] for TI K3 CPSW driver by using napi_complete_done() in TX completion
path.
Depending on gro_flush_timeout and napi_defer_hard_irqs at gives up to 30%
CPU utilization reduction:
gro_flush_timeout=50000
napi_defer_hard_irqs=2
netperf -l 10 -H 192.168.1.1 -t UDP_STREAM -c -C -- -m 1470
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.1.1 () port 0 AF_INET
Socket Message Elapsed Messages CPU Service
Size Size Time Okay Errors Throughput Util Demand
bytes bytes secs # # 10^6bits/sec % SS us/KB
before:
212992 1470 10.00 809632 0 952.0 42.98 14.792
212992 10.00 809630 952.0 50.66 8.719
after:
212992 1470 10.00 813686 0 956.8 32.14 11.009
212992 10.00 813686 956.8 50.05 8.570
[1] https://lore.kernel.org/netdev/20200422161329.56026-1-edumazet@google.com/
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On TI K3 am64x platform the issue with RX IRQ is observed - it's become
disabled forever after .ndo_stop(). The K3 CPSW driver manipulates RX IRQ
by using standard Linux enable_irq()/disable_irq_nosync() API as there is
no IRQ enable/disable options in CPSW HW itself, as result during
.ndo_stop() following sequence happens
phy_stop()
teardown TX/RX channels
wait for TX tdown complete
napi_disable(TX)
clean up TX channels
(a)
napi_disable(RX)
At point (a) it's not possible to predict if RX IRQ was triggered or not.
if RX IRQ was triggered then it also not possible to definitely say if RX
NAPI was run or only scheduled and immediately canceled by
napi_disable(RX). Actually the last case causes RX IRQ to be permanently
disabled.
Another observed issue is that RX IRQ enable counter become unbalanced if
(gro_flush_timeout =! 0) while (napi_defer_hard_irqs == 0):
Unbalanced enable for IRQ 44
WARNING: CPU: 0 PID: 10 at ../kernel/irq/manage.c:776 __enable_irq+0x38/0x80
__enable_irq+0x38/0x80
enable_irq+0x54/0xb0
am65_cpsw_nuss_rx_poll+0x2f4/0x368
__napi_poll+0x34/0x1b8
net_rx_action+0xe4/0x220
_stext+0x11c/0x284
run_ksoftirqd+0x4c/0x60
To avoid above issues introduce flag indicating if RX was actually disabled
before enabling it in am65_cpsw_nuss_rx_poll() and restore RX IRQ state in
.ndo_open()
Fixes: 4f7cce2724 ("net: ethernet: ti: am65-cpsw: add support for am64x cpsw3g")
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jonathan Lemon says:
====================
ptp: ocp: assorted fixes.
Assorted fixes for the ocp timecard.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
After writing an image blob to the flash memory, a reboot is required
to reload the FPGA. There is no versioning prsent in the FPGA image
file, so only a running version is available. The 'stored version'
was set to 'pending' in order to indicate a reboot was needed.
This isn't reliable, as the module could be unloaded/loaded, losing
the "reboot needed" indicator. Also, the devlink 'stored version'
information is designed to refer to the actual image version.
Unfortunately, there is no method to determine the flash image version
other than booting it, so remove the devlink stored version setting.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The TimeCard has two FPGA images in the flash: the actual firmware,
and a manufacturing fallback version which is intended to act as a
loader in case the flash update failed.
Name these "fw" and "loader", which are reflected in devlink:
[root@timecard drv]# devlink dev info
pci/0000:04:00.0:
driver ptp_ocp
serial_number fc:c2:3d:2e:d7:c0
versions:
running:
fw 5
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
GPS is not the only available positioning system. Use the generic
naming of "GNSS" instead.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
"devlink health" was used as a way to monitor the GNSS signal
status. This isn't really the intended use, and the same
functionality can be achived by monitoring the status file.
Remove the devlink heath support entirely, and also remove the
currently unused devlink parameters.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are two PPS blocks: one handles the external PPS signal output,
with the other handling the PPS signal input to the internal clock.
Add controls for the external PPS block.
Rename the fields so they match their function.
Add cable_delay to the register definitions.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the put_device() call to the error handling path, so the
device is released after the .release callback, avoiding a
use-after-free.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Julian reported that after d43c65b05b Coverity complains about a
missing check whether dev is NULL in ethnl_ops_complete().
There doesn't seem to be any valid case where dev could be NULL when
calling ethnl_ops_begin(), therefore return an error if dev is NULL.
Fixes: d43c65b05b ("ethtool: runtime-resume netdev parent in ethnl_ops_begin")
Reported-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Don't progress with adding and deleting ports as long as devlink
reload is running.
Fixes: 23809a726c ("netdevsim: Forbid devlink reload when adding or deleting ports")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Grygorii Strashko says:
====================
net: ethernet: ti: cpsw/emac: switch to use skb_put_padto()
Now frame padding in TI TI CPSW/EMAC is implemented in a bit of entangled way as
frame SKB padded in drivers (without skb->len) while frame length fixed in CPDMA.
Things became even more confusing hence CPSW switcdev driver need to perform min
TX frame length correction in switch mode [1].
To avoid further confusion, make xmit path more clear and linear, and avoid
updating CPDMA configuration interface for min TX frame length correction
(which is not CPDMA job in general) this series switches TI CPSW/EMAC
drivers to skb_put_padto() instead of skb_padto() in their xmit path, so
skb->len also got updated properly and then removes TX frame length
fixup from CPDMA code.
[1] https://patchwork.kernel.org/project/netdevbpf/patch/20210611132732.10690-1-grygorii.strashko@ti.com/
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Hence all users of davinci_cpdma switched to skb_put_padto() the frame
padding can be removed from it.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use skb_put_padto() instead of skb_padto() so skb->len also got updated, as
preparation for further removing frame padding from cpdma.
It also makes xmit path more clear and linear.
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>