| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Huazhong Tan says:
====================
net: hns3: updates for -next
There are several updates relating to the interrupt coalesce for
the HNS3 ethernet driver.
based on the frame quantity).
a fixed value in code.
based on the gap time).
its new usage.
change log:
V4 - remove #5~#10 from this series, which needs more discussion.
V3 - fix a typo error in #1 reported by Jakub Kicinski.
rewrite #9 commit log.
remove #11 from this series.
V2 - reorder #2 & #3 to fix compiler error.
fix some checkpatch warnings in #10 & #11.
previous version:
V3: https://patchwork.ozlabs.org/project/netdev/cover/1605151998-12633-1-git-send-email-tanhuazhong@huawei.com/
V2: https://patchwork.ozlabs.org/project/netdev/cover/1604892159-19990-1-git-send-email-tanhuazhong@huawei.com/
V1: https://patchwork.ozlabs.org/project/netdev/cover/1604730681-32559-1-git-send-email-tanhuazhong@huawei.com/
====================
Link: https://lore.kernel.org/r/1605514854-11205-1-git-send-email-tanhuazhong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Besides GL(Gap Limiting), QL(Quantity Limiting) can be modified
dynamically when DIM is supported. So rename gl_adapt_enable as
adapt_enable in struct hns3_enet_coalesce.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
For device whose version is above V3(include V3), the GL
configuration can set as 1us unit, so adds support for
configuring this field.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
For maintainability and compatibility, add support for querying
the maximum value of GL.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
QL(quantity limiting) means that hardware supports the interrupt
coalesce based on the frame quantity. QL can be configured when
int_ql_max in device's specification is non-zero, so add support
to configure it. Also, rename two coalesce init function to fit
their purpose.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Ioana Ciornei says:
====================
net: phy: add support for shared interrupts (part 2)
This patch set aims to actually add support for shared interrupts in
phylib and not only for multi-PHY devices. While we are at it,
streamline the interrupt handling in phylib.
For a bit of context, at the moment, there are multiple phy_driver ops
that deal with this subject:
- .config_intr() - Enable/disable the interrupt line.
- .ack_interrupt() - Should quiesce any interrupts that may have been
fired. It's also used by phylib in conjunction with .config_intr() to
clear any pending interrupts after the line was disabled, and before
it is going to be enabled.
- .did_interrupt() - Intended for multi-PHY devices with a shared IRQ
line and used by phylib to discern which PHY from the package was the
one that actually fired the interrupt.
- .handle_interrupt() - Completely overrides the default interrupt
handling logic from phylib. The PHY driver is responsible for checking
if any interrupt was fired by the respective PHY and choose
accordingly if it's the one that should trigger the link state machine.
From my point of view, the interrupt handling in phylib has become
somewhat confusing with all these callbacks that actually read the same
PHY register - the interrupt status. A more streamlined approach would
be to just move the responsibility to write an interrupt handler to the
driver (as any other device driver does) and make .handle_interrupt()
the only way to deal with interrupts.
Another advantage with this approach would be that phylib would gain
support for shared IRQs between different PHY (not just multi-PHY
devices), something which at the moment would require extending every
PHY driver anyway in order to implement their .did_interrupt() callback
and duplicate the same logic as in .ack_interrupt(). The disadvantage
of making .did_interrupt() mandatory would be that we are slightly
changing the semantics of the phylib API and that would increase
confusion instead of reducing it.
What I am proposing is the following:
- As a first step, make the .ack_interrupt() callback optional so that
we do not break any PHY driver amid the transition.
- Every PHY driver gains a .handle_interrupt() implementation that, for
the most part, would look like below:
irq_status = phy_read(phydev, INTR_STATUS);
if (irq_status < 0) {
phy_error(phydev);
return IRQ_NONE;
}
if (!(irq_status & irq_mask))
return IRQ_NONE;
phy_trigger_machine(phydev);
return IRQ_HANDLED;
- Remove each PHY driver's implementation of the .ack_interrupt() by
actually taking care of quiescing any pending interrupts before
enabling/after disabling the interrupt line.
- Finally, after all drivers have been ported, remove the
.ack_interrupt() and .did_interrupt() callbacks from phy_driver.
This patch set is part 2 of the entire change set and it addresses the
changes needed in 9 PHY drivers. The rest can be found on my Github
branch here:
https://github.com/IoanaCiornei/linux/commits/phylib-shared-irq
====================
Link: https://lore.kernel.org/r/20201113165226.561153-1-ciorneiioana@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Acked-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Acked-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Cc: Andre Edich <andre.edich@microchip.com>
Cc: Marco Felsch <m.felsch@pengutronix.de>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Cc: Andre Edich <andre.edich@microchip.com>
Cc: Marco Felsch <m.felsch@pengutronix.de>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Cc: Marek Vasut <marex@denx.de>
Cc: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Cc: Marek Vasut <marex@denx.de>
Cc: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Cc: Maxim Kochetkov <fido_max@inbox.ru>
Cc: Baruch Siach <baruch@tkos.co.il>
Cc: Robert Hancock <robert.hancock@calian.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Tested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Cc: Maxim Kochetkov <fido_max@inbox.ru>
Cc: Baruch Siach <baruch@tkos.co.il>
Cc: Robert Hancock <robert.hancock@calian.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Cc: Nisar Sayed <Nisar.Sayed@microchip.com>
Cc: Yuiko Oshino <yuiko.oshino@microchip.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Cc: Nisar Sayed <Nisar.Sayed@microchip.com>
Cc: Yuiko Oshino <yuiko.oshino@microchip.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In preparation of removing the .ack_interrupt() callback, we must replace
its occurrences (aka phy_clear_interrupt), from the 2 places where it is
called from (phy_enable_interrupts and phy_disable_interrupts), with
equivalent functionality.
This means that clearing interrupts now becomes something that the PHY
driver is responsible of doing, before enabling interrupts and after
clearing them. Make this driver follow the new contract.
Cc: Kavya Sree Kotagiri <kavyasree.kotagiri@microchip.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
In an attempt to actually support shared IRQs in phylib, we now move the
responsibility of triggering the phylib state machine or just returning
IRQ_NONE, based on the IRQ status register, to the PHY driver. Having
3 different IRQ handling callbacks (.handle_interrupt(),
.did_interrupt() and .ack_interrupt() ) is confusing so let the PHY
driver implement directly an IRQ handler like any other device driver.
Make this driver follow the new convention.
Cc: Kavya Sree Kotagiri <kavyasree.kotagiri@microchip.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The previous Kconfig patch led to some other build errors as
reported by the 0day bot and my own overnight build testing.
These are all in <linux/skbuff.h> when KCOV is enabled but
SKB_EXTENSIONS is not enabled, so fix those by combining those conditions
in the header file.
Fixes: 6370cc3bbd8a ("net: add kcov handle to skb extensions")
Fixes: 85ce50d337d1 ("net: kcov: don't select SKB_EXTENSIONS when there is no NET")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Aleksandr Nogikh <nogikh@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Florian Westphal <fw@strlen.de>
Link: https://lore.kernel.org/r/20201116212108.32465-1-rdunlap@infradead.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The code in this driver which parses the devicetree to determine
the phy/fixed link setup, can be replaced by a single library
function: of_phy_get_and_connect().
Behaviour is identical, except that the library function will
complain when 'phy-connection-type' is omitted, instead of
blindly using PHY_INTERFACE_MODE_NA, which would result in an
invalid phy configuration.
The library function no longer brings out the exact phy_mode,
but the driver doesn't need this, because phy_interface_is_rgmii()
queries the phydev directly. Remove 'phy_mode' from the private
adapter struct.
While we're here, log info about the attached phy on connect,
this is useful because the phy type and connection method is now
fully configurable via the devicetree.
Tested on a lan7430 chip with built-in phy. Verified that adding
fixed-link/phy-connection-type in the devicetree results in a
fixed-link setup. Used ethtool to verify that the devicetree
settings are used.
Tested-by: Sven Van Asbroeck <thesven73@gmail.com> # lan7430
Signed-off-by: Sven Van Asbroeck <thesven73@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20201116170155.26967-1-TheSven73@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Currently we print the driver name twice in phy_attached_print():
- phy_dev_info() prints it as part of the device info
- and we print it as part of the info string
This is a little bit ugly, it makes the info harder to read,
especially if the driver name is a little bit longer.
Therefore omit the driver name (if set) in the info string.
Example from r8169 that uses phylib:
old: Generic FE-GE Realtek PHY r8169-300:00: attached PHY driver \
[Generic FE-GE Realtek PHY] (mii_bus:phy_addr=r8169-300:00, irq=IGNORE)
new: Generic FE-GE Realtek PHY r8169-300:00: attached PHY driver \
(mii_bus:phy_addr=r8169-300:00, irq=IGNORE)
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/8ab72586-f079-41d8-84ee-9f6a5bd97b2a@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The only time when nr_frags isn't SKB_MAX_FRAGS is when entering
rtl8169_start_xmit(). However we can use SKB_MAX_FRAGS also here
because when queue isn't stopped there should always be room for
MAX_SKB_FRAGS + 1 descriptors.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/3d1f2ad7-31d5-2cac-4f4a-394f8a3cab63@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Condition !A || A && B is equivalent to !A || B.
Generated by: scripts/coccinelle/misc/excluded_middle.cocci
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>
Reviewed-by: Antoine Tenart <atenart@kernel.org>
Link: https://lore.kernel.org/r/alpine.DEB.2.22.394.2011161633240.2682@hadrien
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Tobias Waldekranz says:
====================
net: dsa: tag_dsa: Unify regular and ethertype DSA taggers
The first patch ports tag_edsa.c's handling of IGMP/MLD traps to
tag_dsa.c. That way, we start from two logically equivalent taggers
that are then merged. The second commit does the heavy lifting of
actually fusing tag_dsa.c and tag_edsa.c. The final one just follows
up with some clean up of existing comments.
v2 -> v3:
- Add the first patch described above as suggested by Andrew.
- Better documentation of TO_SNIFFER and FORWARD tags.
- Spelling.
v1 -> v2:
- Fixed some grammar and whitespace errors.
- Removed unnecessary default value in Kconfig.
- Removed unnecessary #ifdef.
- Split out comment fixes from functional changes.
- Fully document enum dsa_code.
====================
Link: https://lore.kernel.org/r/20201114234558.31203-1-tobias@waldekranz.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Use a consistent style of one-line/multi-line comments throughout the
file.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Ethertype DSA encodes exactly the same information in the DSA tag as
the non-ethertype variety. So refactor out the common parts and reuse
them for both protocols.
This is ensures tag parsing and generation is always consistent across
all mv88e6xxx chips.
While we are at it, explicitly deal with all possible CPU codes on
receive, making sure to set offload_fwd_mark as appropriate.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
When receiving an IGMP/MLD frame with a TO_CPU tag, the switch has not
performed any forwarding of it. This means that we should not set the
offload_fwd_mark on the skb, in case a software bridge wants it
forwarded.
This is a port of:
1ed9ec9b08ad ("dsa: Allow forwarding of redirected IGMP traffic")
Which corrected the issue for chips using EDSA tags, but not for those
using regular DSA tags.
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Paolo Abeni says:
====================
mptcp: improve multiple xmit streams support
This series improves MPTCP handling of multiple concurrent
xmit streams.
The to-be-transmitted data is enqueued to a subflow only when
the send window is open, keeping the subflows xmit queue shorter
and allowing for faster switch-over.
The above requires a more accurate msk socket state tracking
and some additional infrastructure to allow pushing the data
pending in the msk xmit queue as soon as the MPTCP's send window
opens (patches 6-10).
As a side effect, the MPTCP socket could enqueue data to subflows
after close() time - to completely spooling the data sitting in the
msk xmit queue. Dealing with the requires some infrastructure and
core TCP changes (patches 1-5)
Finally, patches 11-12 introduce a more accurate tracking of the other
end's receive window.
Overall this refactor the MPTCP xmit path, without introducing
new features - the new code is covered by the existing self-tests.
v2 -> v3:
- rebased,
- fixed checkpatch issue in patch 1/13
- fixed some state tracking issues in patch 8/13
v1 -> v2:
- this is just a repost, to cope with patchwork issues, no changes
at all
====================
Link: https://lore.kernel.org/r/cover.1605458224.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
When the worker moves some bytes from the OoO queue into
the receive queue, the msk->ask_seq is updated, the MPTCP-level
ack carrying that value needs to wait the next ingress packet,
possibly slowing down or hanging the peer
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Before sending 'x' new bytes also check that the new snd_una would
be within the permitted receive window.
For every ACK that also contains a DSS ack, check whether its tcp-level
receive window would advance the current mptcp window right edge and
update it if so.
Signed-off-by: Florian Westphal <fw@strlen.de>
Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
MPTCP maintains a status bit, MPTCP_SEND_SPACE, that is set when at
least one subflow and the mptcp socket itself are writeable.
mptcp_poll returns EPOLLOUT if the bit is set.
mptcp_sendmsg makes sure MPTCP_SEND_SPACE gets cleared when last write
has used up all subflows or the mptcp socket wmem.
This reworks nospace handling as follows:
MPTCP_SEND_SPACE is replaced with MPTCP_NOSPACE, i.e. inverted meaning.
This bit is set when the mptcp socket is not writeable.
The mptcp-level ack path schedule will then schedule the mptcp worker
to allow it to free already-acked data (and reduce wmem usage).
This will then wake userspace processes that wait for a POLLOUT event.
sendmsg will set MPTCP_NOSPACE only when it has to wait for more
wmem (blocking I/O case).
poll path will set MPTCP_NOSPACE in case the mptcp socket is
not writeable.
Normal tcp-level notification (SOCK_NOSPACE) is only enabled
in case the subflow socket has no available wmem.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
After the previous patch we may end-up with unsent data
in the write buffer. If such buffer is full, the writer
will block for unlimited time.
We need to trigger the MPTCP xmit path even for the
subflow rx path, on MPTCP snd_una updates.
Keep things simple and just schedule the work queue if
needed.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
mptcp_sendmsg() is refactored so that first it copies
the data provided from user space into the send queue,
and then tries to spool the send queue via sendmsg_frag.
There a subtle change in the mptcp level collapsing on
consecutive data fragment: we now allow that only on unsent
data.
The latter don't need to deal with msghdr data anymore
and can be simplified in a relevant way.
snd_nxt and write_seq are now tracked independently.
Overall this allows some relevant cleanup and will
allow sending pending mptcp data on msk una update in
later patch.
Co-developed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
We must not close the subflows before all the MPTCP level
data, comprising the DATA_FIN has been acked at the MPTCP
level, otherwise we could be unable to retransmit as needed.
__mptcp_wr_shutdown() shutdown is responsible to check for the
correct status and close all subflows. Is called by the output
path after spooling any data and at shutdown/close time.
In a similar way, __mptcp_destroy_sock() is responsible to clean-up
the MPTCP level status, and is called when the msk transition
to TCP_CLOSE.
The protocol level close() does not force anymore the TCP_CLOSE
status, but orphan the msk socket and all the subflows.
Orphaned msk sockets are forciby closed after a timeout or
when all MPTCP-level data is acked.
There is a caveat about keeping the orphaned subflows around:
the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via
tcp_close(). To prevent accessing freed memory on later MPTCP
level operations, the msk acquires a reference to each subflow
socket and prevent subflow_ulp_release() from releasing the
subflow context before __mptcp_destroy_sock().
The additional subflow references are released by __mptcp_done()
and the async ULP release is detected checking ULP ops. If such
field has been already cleared by the ULP release path, the
dangling context is freed directly by __mptcp_done().
Co-developed-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Track the next MPTCP sequence number used on xmit,
currently always equal to write_next.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Preparation patch to track the data pending in the msk
write queue. No functional change introduced here
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The current argument list is pretty long and quite unreadable,
move many of them into a specific struct. Later patches
will add more stuff to such struct.
Additionally drop the 'timeo' argument, now unused.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
remove some of code duplications an allow preventing
rescheduling on close.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
unlocked version of protocol level close, will be used by
MPTCP to allow decouple orphaning and subflow level close.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
mptcp_push_pending() is called even on orphaned
msk (and orphaned subflows), if there is outstanding
data at close() time.
To cope with the above MPTCP needs to handle explicitly
the allocation failure on xmit. The newly introduced
do_tcp_sendfrag() allows that, just plug it.
We can additionally drop a couple of sanity checks,
duplicate in the TCP code.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Will be needed by the next patch, as MPTCP needs to handle
directly the error/memory-allocation-needed path.
No functional changes intended.
Additionally let MPTCP code access the tcp_remove_empty_skb()
helper.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Francis Laniel says:
====================
Fix inefficiences and rename nla_strlcpy
This patch set answers to first three issues listed in:
https://github.com/KSPP/linux/issues/110
To sum up, the patch contributions are the following:
1. the first patch fixes an inefficiency where some bytes in dst were written
twice, one with 0 the other with src content.
2. The second one modifies nla_strlcpy to return the same value as strscpy,
i.e. number of bytes written or -E2BIG if src was truncated.
It also modifies code that calls nla_strlcpy and checks for its return value.
3. The third renames nla_strlcpy to nla_strscpy.
Unfortunately, I did not find how to create struct nlattr objects so I tested
my modifications on simple char* and with GDB using tc to get to
tcf_proto_check_kind.
====================
Link: https://lore.kernel.org/r/20201115170806.3578-1-laniel_francis@privacyrequired.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Calls to nla_strlcpy are now replaced by calls to nla_strscpy which is the new
name of this function.
Signed-off-by: Francis Laniel <laniel_francis@privacyrequired.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
nla_strlcpy now returns -E2BIG if src was truncated when written to dst.
It also returns this error value if dstsize is 0 or higher than INT_MAX.
For example, if src is "foo\0" and dst is 3 bytes long, the result will be:
1. "foG" after memcpy (G means garbage).
2. "fo\0" after memset.
3. -E2BIG is returned because src was not completely written into dst.
The callers of nla_strlcpy were modified to take into account this modification.
Signed-off-by: Francis Laniel <laniel_francis@privacyrequired.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
