- May 24, 2023
-
-
David Howells authored
Convert udp_sendpage() to use sendmsg() with MSG_SPLICE_PAGES rather than directly splicing in the pages itself. This allows ->sendpage() to be replaced by something that can handle multiple multipage folios in a single transaction. Signed-off-by:
David Howells <dhowells@redhat.com> cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
Make IP6/UDP6 sendmsg() support MSG_SPLICE_PAGES. This causes pages to be spliced from the source iterator if possible, copying the data if not. This allows ->sendpage() to be replaced by something that can handle multiple multipage folios in a single transaction. Signed-off-by:
David Howells <dhowells@redhat.com> cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
Make IP/UDP sendmsg() support MSG_SPLICE_PAGES. This causes pages to be spliced from the source iterator. This allows ->sendpage() to be replaced by something that can handle multiple multipage folios in a single transaction. Signed-off-by:
David Howells <dhowells@redhat.com> cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
Fold do_tcp_sendpages() into its last remaining caller, tcp_sendpage_locked(). Signed-off-by:
David Howells <dhowells@redhat.com> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
do_tcp_sendpages() is now just a small wrapper around tcp_sendmsg_locked(), so inline it, allowing do_tcp_sendpages() to be removed. This is part of replacing ->sendpage() with a call to sendmsg() with MSG_SPLICE_PAGES set. Signed-off-by:
David Howells <dhowells@redhat.com> Reviewed-by:
Bernard Metzler <bmt@zurich.ibm.com> Reviewed-by:
Tom Talpey <tom@talpey.com> cc: Jason Gunthorpe <jgg@ziepe.ca> cc: Leon Romanovsky <leon@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
do_tcp_sendpages() is now just a small wrapper around tcp_sendmsg_locked(), so inline it, allowing do_tcp_sendpages() to be removed. This is part of replacing ->sendpage() with a call to sendmsg() with MSG_SPLICE_PAGES set. Signed-off-by:
David Howells <dhowells@redhat.com> cc: Boris Pismenny <borisp@nvidia.com> cc: John Fastabend <john.fastabend@gmail.com> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
do_tcp_sendpages() is now just a small wrapper around tcp_sendmsg_locked(), so inline it, allowing do_tcp_sendpages() to be removed. This is part of replacing ->sendpage() with a call to sendmsg() with MSG_SPLICE_PAGES set. Signed-off-by:
David Howells <dhowells@redhat.com> cc: Steffen Klassert <steffen.klassert@secunet.com> cc: Herbert Xu <herbert@gondor.apana.org.au> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
do_tcp_sendpages() is now just a small wrapper around tcp_sendmsg_locked(), so inline it. This is part of replacing ->sendpage() with a call to sendmsg() with MSG_SPLICE_PAGES set. Signed-off-by:
David Howells <dhowells@redhat.com> cc: John Fastabend <john.fastabend@gmail.com> cc: Jakub Sitnicki <jakub@cloudflare.com> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
Convert do_tcp_sendpages() to use sendmsg() with MSG_SPLICE_PAGES rather than directly splicing in the pages itself. do_tcp_sendpages() can then be inlined in subsequent patches into its callers. This allows ->sendpage() to be replaced by something that can handle multiple multipage folios in a single transaction. Signed-off-by:
David Howells <dhowells@redhat.com> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
Make TCP's sendmsg() support MSG_SPLICE_PAGES. This causes pages to be spliced or copied (if it cannot be spliced) from the source iterator. This allows ->sendpage() to be replaced by something that can handle multiple multipage folios in a single transaction. Signed-off-by:
David Howells <dhowells@redhat.com> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
Add a function to handle MSG_SPLICE_PAGES being passed internally to sendmsg(). Pages are spliced into the given socket buffer if possible and copied in if not (e.g. they're slab pages or have a zero refcount). Signed-off-by:
David Howells <dhowells@redhat.com> cc: David Ahern <dsahern@kernel.org> cc: Al Viro <viro@zeniv.linux.org.uk> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
Pass the maximum number of fragments into skb_append_pagefrags() rather than using MAX_SKB_FRAGS so that it can be used from code that wants to specify sysctl_max_skb_frags. Signed-off-by:
David Howells <dhowells@redhat.com> cc: David Ahern <dsahern@kernel.org> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
David Howells authored
Declare MSG_SPLICE_PAGES, an internal sendmsg() flag, that hints to a network protocol that it should splice pages from the source iterator rather than copying the data if it can. This flag is added to a list that is cleared by sendmsg syscalls on entry. This is intended as a replacement for the ->sendpage() op, allowing a way to splice in several multipage folios in one go. Signed-off-by:
David Howells <dhowells@redhat.com> Reviewed-by:
Willem de Bruijn <willemb@google.com> cc: Jens Axboe <axboe@kernel.dk> cc: Matthew Wilcox <willy@infradead.org> Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Jaco Coetzee authored
Add layer 4 RSS hashing on UDP traffic to allow for the utilization of multiple queues for multiple connections on the same IP address. Previously, since the introduction of the driver, RSS hashing was only performed on the source and destination IP addresses of UDP packets thereby limiting UDP traffic to a single queue for multiple connections on the same IP address. The transport layer is now included in RSS hashing for UDP traffic, which was not previously the case. The reason behind the previous limitation is unclear - either a historic limitation of the NFP device, or an oversight. Signed-off-by:
Jaco Coetzee <jaco.coetzee@corigine.com> Acked-by:
Simon Horman <simon.horman@corigine.com> Signed-off-by:
Louis Peens <louis.peens@corigine.com> Link: https://lore.kernel.org/r/20230522141335.22536-1-louis.peens@corigine.com Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Josua Mayer authored
Walsun offers commercial ("C") and industrial ("I") variants of multi-rate copper SFP+ modules. Add quirk for HXSX-ATRI-1 using same parameters as the already supported commercial variant HXSX-ATRC-1. Signed-off-by:
Josua Mayer <josua@solid-run.com> Reviewed-by:
Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Link: https://lore.kernel.org/r/20230522145242.30192-2-josua@solid-run.com/ Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
- May 23, 2023
-
-
Ratheesh Kannoth authored
Page pool for each rx queue enhance rx side performance by reclaiming buffers back to each queue specific pool. DMA mapping is done only for first allocation of buffers. As subsequent buffers allocation avoid DMA mapping, it results in performance improvement. Image | Performance ------------ | ------------ Vannila | 3Mpps | with this | 42Mpps change | --------------------------- Signed-off-by:
Ratheesh Kannoth <rkannoth@marvell.com> Link: https://lore.kernel.org/r/20230522020404.152020-1-rkannoth@marvell.com Signed-off-by:
Paolo Abeni <pabeni@redhat.com>
-
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linuxJakub Kicinski authored
Saeed Mahameed says: ==================== mlx5-updates-2023-05-19 mlx5 misc changes and code clean up: The following series contains general changes for improving E-Switch driver behavior. 1) improving condition checking 2) Code clean up 3) Using metadata matching on send-to-vport rules. 4) Using RoCE v2 instead of v1 for loopback rules. * tag 'mlx5-updates-2023-05-19' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux: net/mlx5e: E-Switch, Initialize E-Switch for eswitch manager net/mlx5: devlink, Only show PF related devlink warning when needed net/mlx5: E-Switch, Use metadata matching for RoCE loopback rule net/mlx5: E-Switch, Use RoCE version 2 for loopback traffic net/mlx5e: E-Switch, Add a check that log_max_l2_table is valid net/mlx5e: E-Switch: move debug print of adding mac to correct place net/mlx5e: E-Switch, Check device is PF when stopping esw offloads net/mlx5: Remove redundant vport_group_manager cap check net/mlx5e: E-Switch, Use metadata for vport matching in send-to-vport rules net/mlx5e: E-Switch, Allow get vport api if esw exists net/mlx5e: E-Switch, Update when to set other vport context net/mlx5e: Remove redundant __func__ arg from fs_err() calls net/mlx5e: E-Switch, Remove flow_source check for metadata matching net/mlx5: E-Switch, Remove redundant check net/mlx5: Remove redundant esw multiport validate function ==================== Acked-by:
Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/r/20230519175557.15683-1-saeed@kernel.org Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Russell King (Oracle) authored
We have been requiring the supported_interfaces bitmap to be filled in by MAC drivers that have a mac_select_pcs() method. Now that all MAC drivers fill in the supported_interfaces bitmap, it is time to enforce this. We have already required supported_interfaces to be set in order for optical SFPs to be configured in commit f81fa96d ("net: phylink: use phy_interface_t bitmaps for optical modules"). Refuse phylink creation if supported_interfaces is empty, and remove code to deal with cases where this mask is empty. Signed-off-by:
Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Link: https://lore.kernel.org/r/E1q0K1u-006EIP-ET@rmk-PC.armlinux.org.uk Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Russell King (Oracle) authored
Add support for the Fiberstore SFP-10G-T and Walsun HXSX-ATRC-1 modules. Internally, the PCB silkscreen has what seems to be a part number of WT_502. Fiberstore use v2.2 whereas Walsun use v2.6. These modules contain a Marvell AQrate AQR113C PHY, accessible through I2C 0x51 using the "rollball" protocol. In both cases, the PHY is programmed to use 10GBASE-R with pause-mode rate adaption. Unlike the other rollball modules, these only need a four second delay before we can talk to the PHY. Signed-off-by:
Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Link: https://lore.kernel.org/r/E1q0JfS-006Dqc-8t@rmk-PC.armlinux.org.uk Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
- May 22, 2023
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queueDavid S. Miller authored
Tony Nguyen says: ==================== ice: allow matching on meta data Michal Swiatkowski says: This patchset is intended to improve the usability of the switchdev slow path. Without matching on a meta data values slow path works based on VF's MAC addresses. It causes a problem when the VF wants to use more than one MAC address (e.g. when it is in trusted mode). Parse all meta data in the same place where protocol type fields are parsed. Add description for the currently implemented meta data. It is important to note that depending on DDP not all described meta data can be available. Using not available meta data leads to error returned by function which is looking for correct words in profiles read from DDP. There is also one small improvement, remove of rx field in rule info structure (patch 2). It is redundant. ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Uwe Kleine-König authored
After commit b8a1a4cd ("i2c: Provide a temporary .probe_new() call-back type"), all drivers being converted to .probe_new() and then 03c835f4 ("i2c: Switch .probe() to not take an id parameter") convert back to (the new) .probe() to be able to eventually drop .probe_new() from struct i2c_driver. Signed-off-by:
Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Reviewed-by:
Luca Ceresoli <luca.ceresoli@bootlin.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Pavel Begunkov authored
Don't keep hand coded offset caluclations and replace it with container_of(). It should be type safer and a bit less confusing. It also makes it with a macro instead of inline function to preserve constness, which was previously casted out like in case of tcp_v6_send_synack(). Signed-off-by:
Pavel Begunkov <asml.silence@gmail.com> Reviewed-by:
Simon Horman <simon.horman@corigine.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Russell King authored
There are several places which open code comparing PHY IDs. Provide a couple of helpers to assist with this, using a slightly simpler test than the original: - phy_id_compare() compares two arbitary PHY IDs and a mask of the significant bits in the ID. - phydev_id_compare() compares the bound phydev with the specified PHY ID, using the bound driver's mask. Signed-off-by:
Russell King <rmk+kernel@armlinux.org.uk> Reviewed-by:
Simon Horman <simon.horman@corigine.com> Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Russell King (Oracle) authored
The mac_an_restart() method will only be called if the driver sets legacy_pre_march2020, which the altera tse driver does not do. Therefore, providing a stub is unnecessary. Fixes: fef29982 ("net: altera: tse: convert to phylink") Signed-off-by:
Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by:
Simon Horman <simon.horman@corigine.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Arnd Bergmann authored
The new variable is only used when IPCONFIG_BOOTP is defined and otherwise causes a warning: net/ipv4/ipconfig.c:177:12: error: 'ic_nameservers_fallback' defined but not used [-Werror=unused-variable] Move it next to the user. Fixes: 81ac2722 ("net: ipconfig: Allow DNS to be overwritten by DHCPACK") Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Reviewed-by:
Simon Horman <simon.horman@corigine.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Wei Fang authored
This patch is a cleanup for fec driver. The fec_enet_reset_skb() is used to free skb buffers for tx queues and is only invoked in fec_restart(). However, fec_enet_bd_init() also resets skb buffers and is invoked in fec_restart() too. So fec_enet_reset_skb() is redundant and useless. Signed-off-by:
Wei Fang <wei.fang@nxp.com> Reviewed-by:
Simon Horman <simon.horman@corigine.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Wei Fang authored
The XDP features are supported since the commit 66c0e13a ("drivers: net: turn on XDP features"). Currently, the fec driver supports NETDEV_XDP_ACT_BASIC, NETDEV_XDP_ACT_REDIRECT and NETDEV_XDP_ACT_NDO_XMIT. So turn on these XDP features for fec driver. Signed-off-by:
Wei Fang <wei.fang@nxp.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- May 20, 2023
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queueJakub Kicinski authored
Tony Nguyen says: ==================== Intel Wired LAN Driver Updates 2023-05-18 (igc, igb, e1000e) This series contains updates to igc, igb, and e1000e drivers. Kurt Kanzenbach adds calls to txq_trans_cond_update() for XDP transmit on igc. Tom Rix makes definition of igb_pm_ops conditional on CONFIG_PM for igb. Baozhu Ni adds a missing kdoc description on e1000e. * '1GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue: e1000e: Add @adapter description to kdoc igb: Define igb_pm_ops conditionally on CONFIG_PM igc: Avoid transmit queue timeout for XDP ==================== Link: https://lore.kernel.org/r/20230518170942.418109-1-anthony.l.nguyen@intel.com Signed-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Roi Dayan authored
Initialize eswitch instance for a function which is eswitch manager but not a vport group manager. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
Limit the PF related warning to show if device is actually a PF. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
Use metadata matching for RoCE loopback rule if device is configured to use metadata for source port matching. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
Could be port initializing eswitch doesn't support RoCE version 1 but all ports should support RoCE version 2. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Gottlieb <maorg@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
If log_max_l2_table is 0 there is no really room for one L2 address. and should be treated as not supported. Do the check in MPFS init and for vport context events which both used to update L2 address. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
Move the debug print inside the if clause that actually does the change. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
Checking sriov is done on the pci device so it can return true on other devices like SF but nothing should be done in this case. Add a check that the device is PF. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
It's enough to check for esw_manager cap for get the esw flow table caps. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
Like other rules use metadata matching if supported instead of source_port. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
We could have an esw manager device which is not a vport group manager. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
Other vport context should be set if vport number is not 0. In case of ECPF, vport 0 represents the host PF representor so also need to set other vport context. Signed-off-by:
Roi Dayan <roid@nvidia.com> Reviewed-by:
Maor Dickman <maord@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-
Roi Dayan authored
fs_err() already logs the function name. remote the arg so the function name will not be logged twice. Signed-off-by:
Roi Dayan <roid@nvidia.com> Signed-off-by:
Saeed Mahameed <saeedm@nvidia.com>
-