OSDN Git Service
Wu XiangCheng [Sun, 4 Apr 2021 14:23:15 +0000 (22:23 +0800)]
tipc: Fix a kernel-doc warning in name_table.c
Fix kernel-doc warning:
Documentation/networking/tipc:66: /home/sfr/next/next/net/tipc/name_table.c
:558: WARNING: Unexpected indentation.
Documentation/networking/tipc:66: /home/sfr/next/next/net/tipc/name_table.c
:559: WARNING: Block quote ends without a blank line; unexpected unindent.
Due to blank line missing.
Fixes:
908148bc5046 ("tipc: refactor tipc_sendmsg() and tipc_lookup_anycast()")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: https://lore.kernel.org/netdev/20210318172255.63185609@canb.auug.org.au/
Signed-off-by: Wu XiangCheng <bobwxc@email.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
Taehee Yoo [Sun, 4 Apr 2021 13:38:23 +0000 (13:38 +0000)]
mld: change lockdep annotation for ip6_sf_socklist and ipv6_mc_socklist
struct ip6_sf_socklist and ipv6_mc_socklist are per-socket MLD data.
These data are protected by rtnl lock, socket lock, and RCU.
So, when these are used, it verifies whether rtnl lock is acquired or not.
ip6_mc_msfget() is called by do_ipv6_getsockopt().
But caller doesn't acquire rtnl lock.
So, when these data are used in the ip6_mc_msfget() lockdep warns about it.
But accessing these is actually safe because socket lock was acquired by
do_ipv6_getsockopt().
So, it changes lockdep annotation from rtnl lock to socket lock.
(rtnl_dereference -> sock_dereference)
Locking graph for mld data is like below:
When writing mld data:
do_ipv6_setsockopt()
rtnl_lock
lock_sock
(mld functions)
idev->mc_lock(if per-interface mld data is modified)
When reading mld data:
do_ipv6_getsockopt()
lock_sock
ip6_mc_msfget()
Splat looks like:
=============================
WARNING: suspicious RCU usage
5.12.0-rc4+ #503 Not tainted
-----------------------------
net/ipv6/mcast.c:610 suspicious rcu_dereference_protected() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by mcast-listener-/923:
#0:
ffff888007958a70 (sk_lock-AF_INET6){+.+.}-{0:0}, at:
ipv6_get_msfilter+0xaf/0x190
stack backtrace:
CPU: 1 PID: 923 Comm: mcast-listener- Not tainted 5.12.0-rc4+ #503
Call Trace:
dump_stack+0xa4/0xe5
ip6_mc_msfget+0x553/0x6c0
? ipv6_sock_mc_join_ssm+0x10/0x10
? lockdep_hardirqs_on_prepare+0x3e0/0x3e0
? mark_held_locks+0xb7/0x120
? lockdep_hardirqs_on_prepare+0x27c/0x3e0
? __local_bh_enable_ip+0xa5/0xf0
? lock_sock_nested+0x82/0xf0
ipv6_get_msfilter+0xc3/0x190
? compat_ipv6_get_msfilter+0x300/0x300
? lock_downgrade+0x690/0x690
do_ipv6_getsockopt.isra.6.constprop.13+0x1809/0x29e0
? do_ipv6_mcast_group_source+0x150/0x150
? register_lock_class+0x1750/0x1750
? kvm_sched_clock_read+0x14/0x30
? sched_clock+0x5/0x10
? sched_clock_cpu+0x18/0x170
? find_held_lock+0x3a/0x1c0
? lock_downgrade+0x690/0x690
? ipv6_getsockopt+0xdb/0x1b0
ipv6_getsockopt+0xdb/0x1b0
[ ... ]
Fixes:
88e2ca308094 ("mld: convert ifmcaddr6 to RCU")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Christophe JAILLET [Sun, 4 Apr 2021 12:42:57 +0000 (14:42 +0200)]
qede: Use 'skb_add_rx_frag()' instead of hand coding it
Some lines of code can be merged into an equivalent 'skb_add_rx_frag()'
call which is less verbose.
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Christophe JAILLET [Sun, 4 Apr 2021 12:42:44 +0000 (14:42 +0200)]
qede: Remove a erroneous ++ in 'qede_rx_build_jumbo()'
This ++ is confusing. It looks duplicated with the one already performed in
'skb_fill_page_desc()'.
In fact, it is harmless. 'nr_frags' is written twice with the same value.
Once, because of the nr_frags++, and once because of the 'nr_frags = i + 1'
in 'skb_fill_page_desc()'.
So axe this post-increment to avoid confusion.
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Christophe JAILLET [Sun, 4 Apr 2021 09:45:11 +0000 (11:45 +0200)]
sfc: Use 'skb_add_rx_frag()' instead of hand coding it
Some lines of code can be merged into an equivalent 'skb_add_rx_frag()'
call which is less verbose.
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Christophe JAILLET [Sun, 4 Apr 2021 08:54:37 +0000 (10:54 +0200)]
ibmvnic: Use 'skb_frag_address()' instead of hand coding it
'page_address(skb_frag_page()) + skb_frag_off()' can be replaced by an
equivalent 'skb_frag_address()' which is less verbose.
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Christophe JAILLET [Sun, 4 Apr 2021 06:33:44 +0000 (08:33 +0200)]
net: ag71xx: Slightly simplify 'ag71xx_rx_packets()'
There is no need to use 'list_for_each_entry_safe' here, as nothing is
removed from the list in the 'for' loop.
Use 'list_for_each_entry' instead, it is slightly less verbose.
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Xie He [Fri, 2 Apr 2021 09:30:00 +0000 (02:30 -0700)]
net: x25: Queue received packets in the drivers instead of per-CPU queues
X.25 Layer 3 (the Packet Layer) expects layer 2 to provide a reliable
datalink service such that no packets are reordered or dropped. And
X.25 Layer 2 (the LAPB layer) is indeed designed to provide such service.
However, this reliability is not preserved when a driver calls "netif_rx"
to deliver the received packets to layer 3, because "netif_rx" will put
the packets into per-CPU queues before they are delivered to layer 3.
If there are multiple CPUs, the order of the packets may not be preserved.
The per-CPU queues may also drop packets if there are too many.
Therefore, we should not call "netif_rx" to let it queue the packets.
Instead, we should use our own queue that won't reorder or drop packets.
This patch changes all X.25 drivers to use their own queues instead of
calling "netif_rx". The patch also documents this requirement in the
"x25-iface" documentation.
Cc: Martin Schiller <ms@dev.tdt.de>
Signed-off-by: Xie He <xie.he.0141@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Christophe JAILLET [Sun, 4 Apr 2021 07:11:03 +0000 (09:11 +0200)]
net: openvswitch: Use 'skb_push_rcsum()' instead of hand coding it
'skb_push()'/'skb_postpush_rcsum()' can be replaced by an equivalent
'skb_push_rcsum()' which is less verbose.
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Sun, 4 Apr 2021 08:41:08 +0000 (01:41 -0700)]
Merge tag 'mlx5-updates-2021-04-02' of git://git./linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2021-04-02
This series provides trivial updates and cleanup to mlx5 driver
1) Support for matching on ct_state inv and rel flag in connection tracking
2) Reject TC rules that redirect from a VF to itself
3) Parav provided some E-Switch cleanups that could be summarized to:
3.1) Packing and Reduce structure sizes
3.2) Dynamic allocation of rate limit tables and structures
4) Vu Makes the netdev arfs and vlan tables allocation dynamic.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Sat, 3 Apr 2021 21:13:40 +0000 (14:13 -0700)]
Merge branch 'stmmac-xdp'
Ong Boon Leong says:
====================
stmmac: Add XDP support
This is the v4 patch series for adding XDP native support to stmmac.
Changes in v4:
5/6: Move TX clean timer setup to the end of NAPI RX process and
group it under stmmac_finalize_xdp_rx().
Also, fixed stmmac_xdp_xmit_back() returns STMMAC_XDP_CONSUMED
if XDP buffer conversion to XDP frame fails.
6/6: Move xdp_do_flush(0 into stmmac_finalize_xdp_rx() and combine
the XDP verdict of XDP TX and XDP REDIRECT together.
I retested the patch series on the 'xdp2' and 'xdp_redirect' related to
changes above and found the result to be satisfactory.
History of previous patch series:
v3: https://patchwork.kernel.org/project/netdevbpf/cover/
20210331154135.8507-1-boon.leong.ong@intel.com/
v2: https://patchwork.kernel.org/project/netdevbpf/list/?series=457757
v1: https://patchwork.kernel.org/project/netdevbpf/list/?series=457139
It will be great if community can help to test or review the v4 series
and provide me any input if any.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Ong Boon Leong [Thu, 1 Apr 2021 02:11:17 +0000 (10:11 +0800)]
net: stmmac: Add support for XDP_REDIRECT action
This patch adds the support of XDP_REDIRECT to another remote cpu for
further action. It also implements ndo_xdp_xmit ops, enabling the driver
to transmit packets forwarded to it by XDP program running on another
interface.
This patch has been tested using "xdp_redirect_cpu" for XDP_REDIRECT
+ drop testing. It also been tested with "xdp_redirect" sample app
which can be used to exercise ndo_xdp_xmit ops. The burst traffics are
generated using pktgen_sample03_burst_single_flow.sh in samples/pktgen
directory.
v4: Move xdp_do_flush() processing into stmmac_finalize_xdp_rx() and
combined the XDP verdict of XDP TX and REDIRECT together.
v3: Added 'nq->trans_start = jiffies' to avoid TX time-out as we are
sharing TX queue between slow path and XDP. Thanks to Jakub Kicinski
for point out.
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ong Boon Leong [Thu, 1 Apr 2021 02:11:16 +0000 (10:11 +0800)]
net: stmmac: Add support for XDP_TX action
This patch adds support for XDP_TX action which enables XDP program to
transmit back received frames.
This patch has been tested with the "xdp2" app located in samples/bpf
dir. The DUT receives burst traffic packet generated using pktgen script
'pktgen_sample03_burst_single_flow.sh'.
v4: Moved stmmac_tx_timer_arm() to be done once at the end of NAPI RX.
Fixed stmmac_xdp_xmit_back() to return STMMAC_XDP_CONSUMED if
XDP buffer to frame conversion fails. Thanks to Jakub's input.
v3: Added 'nq->trans_start = jiffies' to avoid TX time-out as we are
sharing TX queue between slow path and XDP. Thanks to Jakub Kicinski
for pointing out.
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ong Boon Leong [Thu, 1 Apr 2021 02:11:15 +0000 (10:11 +0800)]
net: stmmac: Add initial XDP support
This patch adds the initial XDP support to stmmac driver. It supports
XDP_PASS, XDP_DROP and XDP_ABORTED actions. Upcoming patches will add
support for XDP_TX and XDP_REDIRECT.
To support XDP headroom, this patch adds page_offset into RX buffer and
change the dma_sync_single_for_device|cpu(). The DMA address used for
RX operation are changed to take into page_offset too. As page_pool
can handle dma_sync_single_for_device() on behalf of driver with
PP_FLAG_DMA_SYNC_DEV flag, we skip doing that in stmmac driver.
Current stmmac driver supports split header support (SPH) in RX but
the flexibility of splitting header and payload at different position
makes it very complex to be supported for XDP processing. In addition,
jumbo frame is not supported in XDP to keep the initial codes simple.
This patch has been tested with the sample app "xdp1" located in
samples/bpf directory for both SKB and Native (XDP) mode. The burst
traffic generated using pktgen_sample03_burst_single_flow.sh in
samples/pktgen directory.
Changes in v3:
- factor in xdp header and tail adjustment done by XDP program.
Thanks to Jakub Kicinski for pointing out the gap in v2.
Changes in v2:
- fix for "warning: variable 'len' set but not used" reported by lkp.
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ong Boon Leong [Thu, 1 Apr 2021 02:11:14 +0000 (10:11 +0800)]
net: stmmac: arrange Tx tail pointer update to stmmac_flush_tx_descriptors
This patch organizes TX tail pointer update into a new function called
stmmac_flush_tx_descriptors() so that we can reuse it in stmmac_xmit(),
stmmac_tso_xmit() and up-coming XDP implementation.
Changes to v2:
- Fix for warning: unused variable ‘desc_size’
https://patchwork.hopto.org/static/nipa/457321/
12170149/build_32bit/stderr
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ong Boon Leong [Thu, 1 Apr 2021 02:11:13 +0000 (10:11 +0800)]
net: stmmac: make SPH enable/disable to be configurable
SPH functionality splits header and payload according to split mode and
offsef fields (SPLM and SPLOFST). It is beneficials for Linux network
stack RX processing however it adds a lot of complexity in XDP
processing.
So, this patch makes the split-header (SPH) capability of the controller
is stored in "priv->sph_cap" and the enabling/disabling of SPH is decided
by "priv->sph".
This is to prepare initial XDP enabling for stmmac to disable the use of
SPH whenever XDP is enabled.
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ong Boon Leong [Thu, 1 Apr 2021 02:11:12 +0000 (10:11 +0800)]
net: stmmac: set IRQ affinity hint for multi MSI vectors
Certain platform likes Intel mGBE has independent hardware IRQ resources
for TX and RX DMA operation. In preparation to support XDP TX, we add IRQ
affinity hint to group both RX and TX queue of the same queue ID to the
same CPU.
Changes in v2:
- IRQ affinity hint need to set to null before IRQ is released.
Thanks to issue reported by Song, Yoong Siang.
Reported-by: Song, Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vu Pham [Sat, 27 Feb 2021 05:17:12 +0000 (21:17 -0800)]
net/mlx5e: Dynamic alloc vlan table for netdev when needed
Dynamic allocate vlan table in mlx5e_priv for EN netdev
when needed. Don't allocate it for representor netdev.
Signed-off-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Vu Pham [Fri, 26 Feb 2021 23:51:12 +0000 (15:51 -0800)]
net/mlx5e: Dynamic alloc arfs table for netdev when needed
Dynamic allocate arfs table in mlx5e_priv for EN netdev
when needed. Don't allocate it for representor netdev.
Signed-off-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Ariel Levkovich [Thu, 11 Mar 2021 18:37:21 +0000 (20:37 +0200)]
net/mlx5e: Reject tc rules which redirect from a VF to itself
Since there are self loopback prevention mechanisms at the
VF level, offloading such rules which redirect from a VF
to itself in the eswitch will break the datapath since the
packets will be dropped once they go back to the vport they
came from.
Therefore, offloading such rules will be rejected and left to
be handled by SW.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Roi Dayan [Mon, 15 Mar 2021 11:31:40 +0000 (13:31 +0200)]
net/mlx5: Use ida_alloc_range() instead of ida_simple_alloc()
ida_simple_alloc() and remove functions are deprecated.
Related change:
commit
3264ceec8f17 ("lib/idr.c: document that ida_simple_{get,remove}() are deprecated")
Signed-off-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Wed, 3 Feb 2021 13:32:50 +0000 (15:32 +0200)]
net/mlx5: E-Switch, move QoS specific fields to existing qos struct
Function QoS related fields are already defined in qos related struct.
min and max rate are left out to mlx5_vport_info struct.
Move them to existing qos struct.
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Wed, 3 Feb 2021 04:59:32 +0000 (06:59 +0200)]
net/mlx5: E-Switch, cut down mlx5_vport_info structure size by 8 bytes
Structure mlx5_vport_info consumes 40 bytes of space due to a hole
in it. After packing it reduces to 32 bytes.
Currently:
pahole -C mlx5_vport_info drivers/net/ethernet/mellanox/mlx5/core/eswitch.o
struct mlx5_vport_info {
u8 mac[6]; /* 0 6 */
u16 vlan; /* 6 2 */
u8 qos; /* 8 1 */
/* XXX 7 bytes hole, try to pack */
u64 node_guid; /* 16 8 */
int link_state; /* 24 4 */
u32 min_rate; /* 28 4 */
u32 max_rate; /* 32 4 */
bool spoofchk; /* 36 1 */
bool trusted; /* 37 1 */
/* size: 40, cachelines: 1, members: 9 */
/* sum members: 31, holes: 1, sum holes: 7 */
/* padding: 2 */
/* last cacheline: 40 bytes */
};
After packing:
$ pahole -C mlx5_vport_info drivers/net/ethernet/mellanox/mlx5/core/eswitch.o
struct mlx5_vport_info {
u8 mac[6]; /* 0 6 */
u16 vlan; /* 6 2 */
u64 node_guid; /* 8 8 */
int link_state; /* 16 4 */
u32 min_rate; /* 20 4 */
u32 max_rate; /* 24 4 */
u8 qos; /* 28 1 */
u8 spoofchk:1; /* 29: 0 1 */
u8 trusted:1; /* 29: 1 1 */
/* size: 32, cachelines: 1, members: 9 */
/* padding: 2 */
/* bit_padding: 6 bits */
/* last cacheline: 32 bytes */
};
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Fri, 19 Feb 2021 07:36:54 +0000 (09:36 +0200)]
net/mlx5: Pair mutex_destory with mutex_init for rate limit table
Add missing mutex_destroy() to pair with mutex_init().
This should be done only when table is initialized, hence perform
mutex_init() only when table is initialized.
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Fri, 19 Feb 2021 10:06:54 +0000 (12:06 +0200)]
net/mlx5: Allocate rate limit table when rate is configured
A device supports 128 rate limiters. A static table allocation consumes
8KB of memory even when rate is not configured.
Instead, allocate the table when at least one rate is configured.
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Thu, 25 Feb 2021 11:38:07 +0000 (13:38 +0200)]
net/mlx5: Use helper to increment, decrement rate entry refcount
Rate limit entry refcount can be incremented uniformly when it is newly
allocated or reused.
So simplify the code to increment refcount at one place.
Use decrement refcount helper in two routines.
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Fri, 19 Feb 2021 07:29:56 +0000 (09:29 +0200)]
net/mlx5: Use helpers to allocate and free rl table entries
User helper routines to allocate and free rate limit table entries.
Subsequent patch extends use of these helpers to do allocation
during rate entry allocation callback.
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Wed, 24 Feb 2021 09:04:19 +0000 (11:04 +0200)]
net/mlx5: Do not hold mutex while reading table constants
Table max_size, min and max rate are constants initialized while table
is created. Reading it doesn't need to hold a table mutex. Hence, read
them without holding table mutex.
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Fri, 19 Feb 2021 06:18:12 +0000 (08:18 +0200)]
net/mlx5: Pack mlx5_rl_entry structure
mlx5_rl_entry structure is not properly packed as shown below. Due to this
an array of size 9144 bytes allocated which is aligned to 16Kbytes.
Hence, pack the structure and avoid the wastage.
This offers 8Kbytes of saving per mlx5_core_dev struct.
pahole -C mlx5_rl_entry drivers/net/ethernet/mellanox/mlx5/core/en_main.o
Existing layout:
struct mlx5_rl_entry {
u8 rl_raw[48]; /* 0 48 */
u16 index; /* 48 2 */
/* XXX 6 bytes hole, try to pack */
u64 refcount; /* 56 8 */
/* --- cacheline 1 boundary (64 bytes) --- */
u16 uid; /* 64 2 */
u8 dedicated:1; /* 66: 0 1 */
/* size: 72, cachelines: 2, members: 5 */
/* sum members: 60, holes: 1, sum holes: 6 */
/* sum bitfield members: 1 bits (0 bytes) */
/* padding: 5 */
/* bit_padding: 7 bits */
/* last cacheline: 8 bytes */
};
After alignment:
struct mlx5_rl_entry {
u8 rl_raw[48]; /* 0 48 */
u64 refcount; /* 48 8 */
u16 index; /* 56 2 */
u16 uid; /* 58 2 */
u8 dedicated:1; /* 60: 0 1 */
/* size: 64, cachelines: 1, members: 5 */
/* padding: 3 */
/* bit_padding: 7 bits */
};
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Tue, 9 Feb 2021 07:44:27 +0000 (09:44 +0200)]
net/mlx5: Use unsigned int for free_count
Fix the warning due to missing int.
WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
+ unsigned free_count;
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Wed, 3 Feb 2021 13:32:50 +0000 (15:32 +0200)]
net/mlx5: E-Switch, move QoS specific fields to existing qos struct
Function QoS related fields are already defined in qos related struct.
min and max rate are left out to mlx5_vport_info struct.
Move them to existing qos struct.
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Parav Pandit [Wed, 3 Feb 2021 04:59:32 +0000 (06:59 +0200)]
net/mlx5: E-Switch, cut down mlx5_vport_info structure size by 8 bytes
Structure mlx5_vport_info consumes 40 bytes of space due to a hole
in it. After packing it reduces to 32 bytes.
Currently:
pahole -C mlx5_vport_info drivers/net/ethernet/mellanox/mlx5/core/eswitch.o
struct mlx5_vport_info {
u8 mac[6]; /* 0 6 */
u16 vlan; /* 6 2 */
u8 qos; /* 8 1 */
/* XXX 7 bytes hole, try to pack */
u64 node_guid; /* 16 8 */
int link_state; /* 24 4 */
u32 min_rate; /* 28 4 */
u32 max_rate; /* 32 4 */
bool spoofchk; /* 36 1 */
bool trusted; /* 37 1 */
/* size: 40, cachelines: 1, members: 9 */
/* sum members: 31, holes: 1, sum holes: 7 */
/* padding: 2 */
/* last cacheline: 40 bytes */
};
After packing:
$ pahole -C mlx5_vport_info drivers/net/ethernet/mellanox/mlx5/core/eswitch.o
struct mlx5_vport_info {
u8 mac[6]; /* 0 6 */
u16 vlan; /* 6 2 */
u64 node_guid; /* 8 8 */
int link_state; /* 16 4 */
u32 min_rate; /* 20 4 */
u32 max_rate; /* 24 4 */
u8 qos; /* 28 1 */
u8 spoofchk:1; /* 29: 0 1 */
u8 trusted:1; /* 29: 1 1 */
/* size: 32, cachelines: 1, members: 9 */
/* padding: 2 */
/* bit_padding: 6 bits */
/* last cacheline: 32 bytes */
};
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Ariel Levkovich [Mon, 15 Mar 2021 17:59:52 +0000 (19:59 +0200)]
net/mlx5: CT: Add support for matching on ct_state inv and rel flags
Add support for matching on ct_state inv and rel flags.
Currently the support is only for match on -inv and -rel.
Matching on +inv and +rel will be rejected.
Example:
$ tc filter add dev ens1f0_0 ingress prio 1 chain 1 proto ip flower \
ct_state -est-rel+trk \
action mirred egress redirect dev ens1f0_1
$ tc filter add dev ens1f0_1 ingress prio 1 chain 1 proto ip flower \
ct_state +trk+est-inv \
action mirred egress redirect dev ens1f0_0
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Eric Dumazet [Fri, 2 Apr 2021 18:10:37 +0000 (11:10 -0700)]
tcp: reorder tcp_congestion_ops for better cache locality
Group all the often used fields in the first cache line,
to reduce cache line misses.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Fri, 2 Apr 2021 18:07:46 +0000 (11:07 -0700)]
net: reorganize fields in netns_mib
Order fields to increase locality for most used protocols.
udplite and icmp are moved at the end.
Same for proc_net_devsnmp6 which is not used in fast path.
This potentially saves one cache line miss for typical TCP/UDP over IPv4/IPv6.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dan Carpenter [Fri, 2 Apr 2021 11:44:42 +0000 (14:44 +0300)]
nfc: pn533: prevent potential memory corruption
If the "type_a->nfcid_len" is too large then it would lead to memory
corruption in pn533_target_found_type_a() when we do:
memcpy(nfc_tgt->nfcid1, tgt_type_a->nfcid_data, nfc_tgt->nfcid1_len);
Fixes:
c3b1e1e8a76f ("NFC: Export NFCID1 from pn533")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 2 Apr 2021 21:25:47 +0000 (14:25 -0700)]
Merge branch 'dpaa2-rx-copybreak'
Ioana Ciornei says:
====================
dpaa2-eth: add rx copybreak support
DMA unmapping, allocating a new buffer and DMA mapping it back on the
refill path is really not that efficient. Proper buffer recycling (page
pool, flipping the page and using the other half) cannot be done for
DPAA2 since it's not a ring based controller but it rather deals with
multiple queues which all get their buffers from the same buffer pool on
Rx.
To circumvent these limitations, add support for Rx copybreak in
dpaa2-eth.
Below you can find a summary of the tests that were run to end up
with the default rx copybreak value of 512.
A bit about the setup - a LS2088A SoC, 8 x Cortex A72 @ 1.8GHz, IPfwd
zero loss test @ 20Gbit/s throughput. I tested multiple frame sizes to
get an idea where is the break even point.
Here are 2 sets of results, (1) is the baseline and (2) is just
allocating a new skb for all frames sizes received (as if the copybreak
was even to the MTU). All numbers are in Mpps.
64 128 256 512 640 768 896
(1) 3.23 3.23 3.24 3.21 3.1 2.76 2.71
(2) 3.95 3.88 3.79 3.62 3.3 3.02 2.65
It seems that even for 512 bytes frame sizes it's comfortably better when
allocating a new skb. After that, we see diminishing rewards or even worse.
Changes in v2:
- properly marked dpaa2_eth_copybreak as static
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Ioana Ciornei [Fri, 2 Apr 2021 09:55:32 +0000 (12:55 +0300)]
dpaa2-eth: export the rx copybreak value as an ethtool tunable
It's useful, especially for debugging purposes, to have the Rx copybreak
value changeable at runtime. Export it as an ethtool tunable.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ioana Ciornei [Fri, 2 Apr 2021 09:55:31 +0000 (12:55 +0300)]
dpaa2-eth: add rx copybreak support
DMA unmapping, allocating a new buffer and DMA mapping it back on the
refill path is really not that efficient. Proper buffer recycling (page
pool, flipping the page and using the other half) cannot be done for
DPAA2 since it's not a ring based controller but it rather deals with
multiple queues which all get their buffers from the same buffer pool on
Rx.
To circumvent these limitations, add support for Rx copybreak. For small
sized packets instead of creating a skb around the buffer in which the
frame was received, allocate a new sk buffer altogether, copy the
contents of the frame and release the initial page back into the buffer
pool.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ioana Ciornei [Fri, 2 Apr 2021 09:55:30 +0000 (12:55 +0300)]
dpaa2-eth: rename dpaa2_eth_xdp_release_buf into dpaa2_eth_recycle_buf
Rename the dpaa2_eth_xdp_release_buf function into dpaa2_eth_recycle_buf
since in the next patches we'll be using the same recycle mechanism for
the normal stack path beside for XDP_DROP.
Also, rename the array which holds the buffers to be recycled so that it
does not have any reference to XDP.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 2 Apr 2021 21:21:51 +0000 (14:21 -0700)]
Merge branch 'mptcp-misc'
Mat Martineau says:
====================
MPTCP: Miscellaneous changes
Here is a collection of patches from the MPTCP tree:
Patches 1 and 2 add some helpful MIB counters for connection
information.
Patch 3 cleans up some unnecessary checks.
Patch 4 is a new feature, support for the MP_TCPRST option. This option
is used when resetting one subflow within a MPTCP connection, and
provides a reason code that the recipient can use when deciding how to
adapt to the lost subflow.
Patches 5-7 update the existing MPTCP selftests to improve timeout
handling and to share better information when tests fail.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Matthieu Baerts [Thu, 1 Apr 2021 23:19:47 +0000 (16:19 -0700)]
selftests: mptcp: dump more info on mpjoin errors
Very occasionally, MPTCP selftests fail. Yeah, I saw that at least once!
Here we provide more details in case of errors with mptcp_join.sh script
like it was done with mptcp_connect.sh, see
commit
767389c8dd55 ("selftests: mptcp: dump more info on errors")
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Matthieu Baerts [Thu, 1 Apr 2021 23:19:46 +0000 (16:19 -0700)]
selftests: mptcp: init nstat history
Not to be impacted by packets sent between sub-tests.
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Matthieu Baerts [Thu, 1 Apr 2021 23:19:45 +0000 (16:19 -0700)]
selftests: mptcp: launch mptcp_connect with timeout
'mptcp_connect' already has a timeout for poll() but in some cases, it
is not enough.
With "timeout" tool, we will force the command to fail if it doesn't
finish on time. Thanks to that, the script will continue and display
details about the current state before marking the test as failed.
Displaying this state is very important to be able to understand the
issue. Best to have our CI reporting the issue than just "the test
hanged".
Note that in mptcp_connect.sh, we were using a long timeout to validate
the fact we cannot create a socket if a sysctl is set. We don't need
this timeout.
In diag.sh, we want to send signals to mptcp_connect instances that have
been started in the netns. But we cannot send this signal to 'timeout'
otherwise that will stop the timeout and messages telling us SIGUSR1 has
been received will be printed. Instead of trying to find the right PID
and storing them in an array, we can simply use the output of
'ip netns pids' which is all the PIDs we want to send signal to.
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/160
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Florian Westphal [Thu, 1 Apr 2021 23:19:44 +0000 (16:19 -0700)]
mptcp: add mptcp reset option support
The MPTCP reset option allows to carry a mptcp-specific error code that
provides more information on the nature of a connection reset.
Reset option data received gets stored in the subflow context so it can
be sent to userspace via the 'subflow closed' netlink event.
When a subflow is closed, the desired error code that should be sent to
the peer is also placed in the subflow context structure.
If a reset is sent before subflow establishment could complete, e.g. on
HMAC failure during an MP_JOIN operation, the mptcp skb extension is
used to store the reset information.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Paolo Abeni [Thu, 1 Apr 2021 23:19:43 +0000 (16:19 -0700)]
mptcp: remove unneeded check on first subflow
Currently we explicitly check for the first subflow being
NULL in a couple of places, even if we don't need any
special actions in such scenario.
Just drop the unneeded checks, to avoid confusion.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Paolo Abeni [Thu, 1 Apr 2021 23:19:42 +0000 (16:19 -0700)]
mptcp: add active MPC mibs
We are not currently tracking the active MPTCP connection
attempts. Let's add the related counters.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Paolo Abeni [Thu, 1 Apr 2021 23:19:41 +0000 (16:19 -0700)]
mptcp: add mib for token creation fallback
If the MPTCP protocol is unable to create a new token,
the socket fallback to plain TCP, let's keep track
of such events via a specific MIB.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 2 Apr 2021 21:18:33 +0000 (14:18 -0700)]
Merge branch 'ionic-ptp'
Shannon Nelson says:
====================
ionic: add PTP and hw clock support
This patchset adds support for accessing the DSC hardware clock and
for offloading PTP timestamping.
Tx packet timestamping happens through a separate Tx queue set up with
expanded completion descriptors that can report the timestamp.
Rx timestamping can happen either on all queues, or on a separate
timestamping queue when specific filtering is requested. Again, the
timestamps are reported with the expanded completion descriptors.
The timestamping offload ability is advertised but not enabled until an
OS service asks for it. At that time the driver's queues are reconfigured
to use the different completion descriptors and the private processing
queues as needed.
Reading the raw clock value comes through a new pair of values in the
device info registers in BAR0. These high and low values are interpreted
with help from new clock mask, mult, and shift values in the device
identity information.
First we add the ability to detect new queue features, then the handling
of the new descriptor sizes. After adding the new interface structures,
we start adding the support code, saving the advertising to the stack
for last.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:10 +0000 (10:56 -0700)]
ionic: advertise support for hardware timestamps
Let the network stack know we've got support for timestamping
the packets.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:09 +0000 (10:56 -0700)]
ionic: ethtool ptp stats
Add the new hwstamp stats to our ethtool stats output.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:08 +0000 (10:56 -0700)]
ionic: add ethtool support for PTP
Add the get_ts_info() callback for ethtool support of
timestamping information.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:07 +0000 (10:56 -0700)]
ionic: add and enable tx and rx timestamp handling
The Tx and Rx timestamped packets are handled through separate
queues. Here we set them up, service them, and tear them down
along with the normal Tx and Rx queues.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:06 +0000 (10:56 -0700)]
ionic: set up hw timestamp queues
We do hardware timestamping through a separate Tx queue,
and optionally through a separate Rx queue. These queues
are allocated, freed, and tracked separately from the basic
queue arrays.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:05 +0000 (10:56 -0700)]
ionic: add rx filtering for hw timestamp steering
Add handling of the new Rx packet classification filter type.
This simple bit of classification allows for steering packets
to a separate Rx queue for processing.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:04 +0000 (10:56 -0700)]
ionic: link in the new hw timestamp code
These are changes to compile and link the new code, but no
new feature support is available or advertised yet.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:03 +0000 (10:56 -0700)]
ionic: add hw timestamp support files
This adds the file of code for supporting Tx and Rx hardware
timestamps and the raw clock interface, but does not yet link
it in for compiling or use.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:02 +0000 (10:56 -0700)]
ionic: split adminq post and wait calls
Split the wait part out of adminq_post_wait() into a separate
function so that a caller can have finer grain control over
the sequencing of operations and locking.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:01 +0000 (10:56 -0700)]
ionic: add hw timestamp structs to interface
The interface for hardware timestamping includes a new FW
request, device identity fields, Tx and Rx queue feature bits, a
new Rx filter type, the beginnings of Rx packet classifications,
and hardware timestamp registers.
If the IONIC_ETH_HW_TIMESTAMP bit is shown in the
ionic_lif_config features bit string, then we have support
for the hw clock registers. If the IONIC_RXQ_F_HWSTAMP and
IONIC_TXQ_F_HWSTAMP features are shown in the ionic_q_identity
features, then the queues can support HW timestamps on packets.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:56:00 +0000 (10:56 -0700)]
ionic: add handling of larger descriptors
In preparating for hardware timestamping, we need to support
large Tx and Rx completion descriptors. Here we add the new
queue feature ids and handling for the completion descriptor
sizes.
We only are adding support for the Rx 2x sized completion
descriptors in the general Rx queues for now as we will be
using it for PTP Rx support, and we don't have an immediate
use for the large descriptors in the general Tx queues yet;
it will be used in a special Tx queues added in one of the
next few patches.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Thu, 1 Apr 2021 17:55:59 +0000 (10:55 -0700)]
ionic: add new queue features to interface
Add queue feature extensions to prepare for features that
can be queue specific, in addition to the general queue
features already defined. While we're here, change the
existing feature ids from #defines to enum.
Signed-off-by: Allen Hubbe <allenbh@pensando.io>
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 2 Apr 2021 18:03:07 +0000 (11:03 -0700)]
Merge git://git./linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2021-04-01
The following pull-request contains BPF updates for your *net-next* tree.
We've added 68 non-merge commits during the last 7 day(s) which contain
a total of 70 files changed, 2944 insertions(+), 1139 deletions(-).
The main changes are:
1) UDP support for sockmap, from Cong.
2) Verifier merge conflict resolution fix, from Daniel.
3) xsk selftests enhancements, from Maciej.
4) Unstable helpers aka kernel func calling, from Martin.
5) Batches ops for LPM map, from Pedro.
6) Fix race in bpf_get_local_storage, from Yonghong.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Phillip Potter [Thu, 1 Apr 2021 22:36:07 +0000 (23:36 +0100)]
net: usb: ax88179_178a: initialize local variables before use
Use memset to initialize local array in drivers/net/usb/ax88179_178a.c, and
also set a local u16 and u32 variable to 0. Fixes a KMSAN found uninit-value bug
reported by syzbot at:
https://syzkaller.appspot.com/bug?id=
00371c73c72f72487c1d0bfe0cc9d00de339d5aa
Reported-by: syzbot+4993e4a0e237f1b53747@syzkaller.appspotmail.com
Signed-off-by: Phillip Potter <phil@philpotter.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Florian Fainelli [Thu, 1 Apr 2021 16:42:33 +0000 (09:42 -0700)]
net: phy: broadcom: Add statistics for all Gigabit PHYs
All Gigabit PHYs use the same register layout as far as fetching
statistics goes. Fast Ethernet PHYs do not all support statistics, and
the BCM54616S would require some switching between the coper and fiber
modes to fetch the appropriate statistics which is not supported yet.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Otto Hollmann [Thu, 1 Apr 2021 15:57:05 +0000 (17:57 +0200)]
net: document a side effect of ip_local_reserved_ports
If there is overlapp between ip_local_port_range and ip_local_reserved_ports with a huge reserved block, it will affect probability of selecting ephemeral ports, see file net/ipv4/inet_hashtables.c:723
int __inet_hash_connect(
...
for (i = 0; i < remaining; i += 2, port += 2) {
if (unlikely(port >= high))
port -= remaining;
if (inet_is_local_reserved_port(net, port))
continue;
E.g. if there is reserved block of 10000 ports, two ports right after this block will be 5000 more likely selected than others.
If this was intended, we can/should add note into documentation as proposed in this commit, otherwise we should think about different solution. One option could be mapping table of continuous port ranges. Second option could be letting user to modify step (port+=2) in above loop, e.g. using new sysctl parameter.
Signed-off-by: Otto Hollmann <otto.hollmann@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yang Yingliang [Thu, 1 Apr 2021 14:20:15 +0000 (22:20 +0800)]
lan743x: remove redundant semi-colon
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lu Wei [Thu, 1 Apr 2021 09:27:01 +0000 (17:27 +0800)]
net: hns: Fix some typos
Fix some typos.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Lu Wei <luwei32@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Wan Jiabing [Thu, 1 Apr 2021 08:40:29 +0000 (16:40 +0800)]
net: smc: Remove repeated struct declaration
struct smc_clc_msg_local is declared twice. One is declared at
301st line. The blew one is not needed. Remove the duplicate.
Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Acked-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Wan Jiabing [Thu, 1 Apr 2021 07:08:22 +0000 (15:08 +0800)]
include: net: Remove repeated struct declaration
struct ctl_table_header is declared twice. One is declared
at 46th line. The blew one is not needed. Remove the duplicate.
Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Wong Vee Khee [Thu, 1 Apr 2021 06:06:28 +0000 (14:06 +0800)]
net: stmmac: remove unnecessary pci_enable_msi() call
The commit
d2a029bde37b ("stmmac: pci: add MSI support for Intel Quark
X1000") introduced a pci_enable_msi() call in stmmac_pci.c.
With the commit
58da0cfa6cf1 ("net: stmmac: create dwmac-intel.c to
contain all Intel platform"), Intel Quark platform related codes
have been moved to the newly created driver.
Removing this unnecessary pci_enable_msi() call as there are no other
devices that uses stmmac-pci and need MSI to be enabled.
Signed-off-by: Wong Vee Khee <vee.khee.wong@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Wong Vee Khee [Thu, 1 Apr 2021 06:02:50 +0000 (14:02 +0800)]
stmmac: intel: use managed PCI function on probe and resume
Update dwmac-intel to use managed function, i.e. pcim_enable_device().
This will allow devres framework to call resource free function for us.
Signed-off-by: Wong Vee Khee <vee.khee.wong@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Xu Jia [Thu, 1 Apr 2021 03:22:23 +0000 (11:22 +0800)]
net: ipv6: Refactor in rt6_age_examine_exception
The logic in rt6_age_examine_exception is confusing. The commit is
to refactor the code.
Signed-off-by: Xu Jia <xujia39@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hoang Le [Thu, 1 Apr 2021 02:30:48 +0000 (09:30 +0700)]
tipc: fix unique bearer names sanity check
When enabling a bearer by name, we don't sanity check its name with
higher slot in bearer list. This may have the effect that the name
of an already enabled bearer bypasses the check.
To fix the above issue, we just perform an extra checking with all
existing bearers.
Fixes:
cb30a63384bc9 ("tipc: refactor function tipc_enable_bearer()")
Cc: stable@vger.kernel.org
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 1 Apr 2021 22:41:08 +0000 (15:41 -0700)]
Merge branch '100GbE' of git://git./linux/kernel/git/tnguy/next-queue
Tony Nguyen says:
====================
100GbE Intel Wired LAN Driver Updates 2021-03-31
This series contains updates to ice driver only.
Benita adds support for XPS.
Ani moves netdev registration to the end of probe to prevent use before
the interface is ready and moves up an error check to possibly avoid
an unneeded call. He also consolidates the VSI state and flag fields to
a single field.
Dan changes the segment where package information is pulled.
Paul S ensures correct ITR values are set when increasing ring size.
Paul G rewords a link misconfiguration message as this could be
expected.
Bruce removes setting an unnecessary AQ flag and corrects a memory
allocation call. Also fixes checkpatch issues for 'COMPLEX_MACRO'.
Qi aligns PTYPE bitmap naming by adding 'ptype' prefix to the bitmaps
missing it.
Brett removes limiting Rx queue mapping to RSS size as there is not a
dependency on this. He also refactors RSS configuration by introducing
individual functions for LUT and key configuration and by passing a
structure containing pertinent information instead of individual
arguments.
Tony corrects a comment block to follow netdev style.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexei Starovoitov [Thu, 1 Apr 2021 17:56:15 +0000 (10:56 -0700)]
Merge branch 'sockmap: introduce BPF_SK_SKB_VERDICT and support UDP'
Cong Wang says:
====================
From: Cong Wang <cong.wang@bytedance.com>
We have thousands of services connected to a daemon on every host
via AF_UNIX dgram sockets, after they are moved into VM, we have to
add a proxy to forward these communications from VM to host, because
rewriting thousands of them is not practical. This proxy uses an
AF_UNIX socket connected to services and a UDP socket to connect to
the host. It is inefficient because data is copied between kernel
space and user space twice, and we can not use splice() which only
supports TCP. Therefore, we want to use sockmap to do the splicing
without going to user-space at all (after the initial setup).
Currently sockmap only fully supports TCP, UDP is partially supported
as it is only allowed to add into sockmap. This patchset, as the second
part of the original large patchset, extends sockmap with:
1) cross-protocol support with BPF_SK_SKB_VERDICT; 2) full UDP support.
On the high level, ->read_sock() is required for each protocol to support
sockmap redirection, and in order to do sock proto update, a new ops
->psock_update_sk_prot() is introduced, which is also required. And the
BPF ->recvmsg() is also needed to replace the original ->recvmsg() to
retrieve skmsg. To make life easier, we have to get rid of lock_sock()
in sk_psock_handle_skb(), otherwise we would have to implement
->sendmsg_locked() on top of ->sendmsg(), which is ugly.
Please see each patch for more details.
To see the big picture, the original patchset is available here:
https://github.com/congwang/linux/tree/sockmap
this patchset is also available:
https://github.com/congwang/linux/tree/sockmap2
---
v8: get rid of 'offset' in udp_read_sock()
add checks for skb_verdict/stream_verdict conflict
add two cleanup patches for sock_map_link()
add a new test case
v7: use work_mutex to protect psock->work
return err in udp_read_sock()
add patch 6/13
clean up test case
v6: get rid of sk_psock_zap_ingress()
add rcu work patch
v5: use INDIRECT_CALL_2() for function pointers
use ingress_lock to fix a race condition found by Jacub
rename two helper functions
v4: get rid of lock_sock() in sk_psock_handle_skb()
get rid of udp_sendmsg_locked()
remove an empty line
update cover letter
v3: export tcp/udp_update_proto()
rename sk->sk_prot->psock_update_sk_prot()
improve changelogs
v2: separate from the original large patchset
rebase to the latest bpf-next
split UDP test case
move inet_csk_has_ulp() check to tcp_bpf.c
clean up udp_read_sock()
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cong Wang [Wed, 31 Mar 2021 02:32:37 +0000 (19:32 -0700)]
selftests/bpf: Add a test case for loading BPF_SK_SKB_VERDICT
This adds a test case to ensure BPF_SK_SKB_VERDICT and
BPF_SK_STREAM_VERDICT will never be attached at the same time.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-17-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:36 +0000 (19:32 -0700)]
selftests/bpf: Add a test case for udp sockmap
Add a test case to ensure redirection between two UDP sockets work.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-16-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:35 +0000 (19:32 -0700)]
sock_map: Update sock type checks for UDP
Now UDP supports sockmap and redirection, we can safely update
the sock type checks for it accordingly.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-15-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:34 +0000 (19:32 -0700)]
udp: Implement udp_bpf_recvmsg() for sockmap
We have to implement udp_bpf_recvmsg() to replace the ->recvmsg()
to retrieve skmsg from ingress_msg.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-14-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:33 +0000 (19:32 -0700)]
skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data()
Although these two functions are only used by TCP, they are not
specific to TCP at all, both operate on skmsg and ingress_msg,
so fit in net/core/skmsg.c very well.
And we will need them for non-TCP, so rename and move them to
skmsg.c and export them to modules.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:32 +0000 (19:32 -0700)]
udp: Implement ->read_sock() for sockmap
This is similar to tcp_read_sock(), except we do not need
to worry about connections, we just need to retrieve skb
from UDP receive queue.
Note, the return value of ->read_sock() is unused in
sk_psock_verdict_data_ready(), and UDP still does not
support splice() due to lack of ->splice_read(), so users
can not reach udp_read_sock() directly.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-12-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:31 +0000 (19:32 -0700)]
sock: Introduce sk->sk_prot->psock_update_sk_prot()
Currently sockmap calls into each protocol to update the struct
proto and replace it. This certainly won't work when the protocol
is implemented as a module, for example, AF_UNIX.
Introduce a new ops sk->sk_prot->psock_update_sk_prot(), so each
protocol can implement its own way to replace the struct proto.
This also helps get rid of symbol dependencies on CONFIG_INET.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-11-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:30 +0000 (19:32 -0700)]
sock_map: Introduce BPF_SK_SKB_VERDICT
Reusing BPF_SK_SKB_STREAM_VERDICT is possible but its name is
confusing and more importantly we still want to distinguish them
from user-space. So we can just reuse the stream verdict code but
introduce a new type of eBPF program, skb_verdict. Users are not
allowed to attach stream_verdict and skb_verdict programs to the
same map.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-10-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:29 +0000 (19:32 -0700)]
sock_map: Kill sock_map_link_no_progs()
Now we can fold sock_map_link_no_progs() into sock_map_link()
and get rid of sock_map_link_no_progs().
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210331023237.41094-9-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:28 +0000 (19:32 -0700)]
sock_map: Simplify sock_map_link() a bit
sock_map_link() passes down map progs, but it is confusing
to see both map progs and psock progs. Make the map progs
more obvious by retrieving it directly with sock_map_progs()
inside sock_map_link(). Now it is aligned with
sock_map_link_no_progs() too.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-8-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:27 +0000 (19:32 -0700)]
skmsg: Use GFP_KERNEL in sk_psock_create_ingress_msg()
This function is only called in process context.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-7-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:26 +0000 (19:32 -0700)]
skmsg: Use rcu work for destroying psock
The RCU callback sk_psock_destroy() only queues work psock->gc,
so we can just switch to rcu work to simplify the code.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-6-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:25 +0000 (19:32 -0700)]
skmsg: Avoid lock_sock() in sk_psock_backlog()
We do not have to lock the sock to avoid losing sk_socket,
instead we can purge all the ingress queues when we close
the socket. Sending or receiving packets after orphaning
socket makes no sense.
We do purge these queues when psock refcnt reaches zero but
here we want to purge them explicitly in sock_map_close().
There are also some nasty race conditions on testing bit
SK_PSOCK_TX_ENABLED and queuing/canceling the psock work,
we can expand psock->ingress_lock a bit to protect them too.
As noticed by John, we still have to lock the psock->work,
because the same work item could be running concurrently on
different CPU's.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-5-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:24 +0000 (19:32 -0700)]
net: Introduce skb_send_sock() for sock_map
We only have skb_send_sock_locked() which requires callers
to use lock_sock(). Introduce a variant skb_send_sock()
which locks on its own, callers do not need to lock it
any more. This will save us from adding a ->sendmsg_locked
for each protocol.
To reuse the code, pass function pointers to __skb_send_sock()
and build skb_send_sock() and skb_send_sock_locked() on top.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-4-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:23 +0000 (19:32 -0700)]
skmsg: Introduce a spinlock to protect ingress_msg
Currently we rely on lock_sock to protect ingress_msg,
it is too big for this, we can actually just use a spinlock
to protect this list like protecting other skb queues.
__tcp_bpf_recvmsg() is still special because of peeking,
it still has to use lock_sock.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-3-xiyou.wangcong@gmail.com
Cong Wang [Wed, 31 Mar 2021 02:32:22 +0000 (19:32 -0700)]
skmsg: Lock ingress_skb when purging
Currently we purge the ingress_skb queue only when psock
refcnt goes down to 0, so locking the queue is not necessary,
but in order to be called during ->close, we have to lock it
here.
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210331023237.41094-2-xiyou.wangcong@gmail.com
Carlos Llamas [Thu, 1 Apr 2021 00:40:20 +0000 (00:40 +0000)]
selftests/net: so_txtime multi-host support
SO_TXTIME hardware offload requires testing across devices, either
between machines or separate network namespaces.
Split up SO_TXTIME test into tx and rx modes, so traffic can be
sent from one process to another. Create a veth-pair on different
namespaces and bind each process to an end point via [-S]ource and
[-D]estination parameters. Optional start [-t]ime parameter can be
passed to synchronize the test across the hosts (with synchorinzed
clocks).
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Frank Wunderlich [Wed, 31 Mar 2021 13:34:37 +0000 (15:34 +0200)]
net: mediatek: add flow offload for mt7623
mt7623 uses offload version 2 too
tested on Bananapi-R2
Signed-off-by: Frank Wunderlich <frank-w@public-files.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Voon Weifeng [Wed, 31 Mar 2021 16:18:25 +0000 (00:18 +0800)]
net: stmmac: enable MTL ECC Error Address Status Over-ride by default
Turn on the MEEAO field of MTL_ECC_Control_Register by default.
As the MTL ECC Error Address Status Over-ride(MEEAO) is set by default,
the following error address fields will hold the last valid address
where the error is detected.
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: Tan Tee Min <tee.min.tan@intel.com>
Co-developed-by: Wong Vee Khee <vee.khee.wong@linux.intel.com>
Signed-off-by: Wong Vee Khee <vee.khee.wong@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 31 Mar 2021 21:57:44 +0000 (14:57 -0700)]
Merge branch 'nxp-enetc-xdp'
Vladimir Oltean says:
====================
XDP for NXP ENETC
This series adds support to the enetc driver for the basic XDP primitives.
The ENETC is a network controller found inside the NXP LS1028A SoC,
which is a dual-core Cortex A72 device for industrial networking,
with the CPUs clocked at up to 1.3 GHz. On this platform, there are 4
ENETC ports and a 6-port embedded DSA switch, in a topology that looks
like this:
+-------------------------------------------------------------------------+
| +--------+ 1 Gbps (typically disabled) |
| ENETC PCI | ENETC |--------------------------+ |
| Root Complex | port 3 |-----------------------+ | |
| Integrated +--------+ | | |
| Endpoint | | |
| +--------+ 2.5 Gbps | | |
| | ENETC |--------------+ | | |
| | port 2 |-----------+ | | | |
| +--------+ | | | | |
| | | | | |
| +------------------------------------------------+
| | | Felix | | Felix | |
| | Switch | port 4 | | port 5 | |
| | +--------+ +--------+ |
| | |
| +--------+ +--------+ | +--------+ +--------+ +--------+ +--------+ |
| | ENETC | | ENETC | | | Felix | | Felix | | Felix | | Felix | |
| | port 0 | | port 1 | | | port 0 | | port 1 | | port 2 | | port 3 | |
+-------------------------------------------------------------------------+
| | | | | |
v v v v v v
Up to Up to Up to 4x 2.5Gbps
2.5Gbps 1Gbps
The ENETC ports 2 and 3 can act as DSA masters for the embedded switch.
Because 4 out of the 6 externally-facing ports of the SoC are switch
ports, the most interesting use case for XDP on this device is in fact
XDP_TX on the 2.5Gbps DSA master.
Nonetheless, the results presented below are for IPv4 forwarding between
ENETC port 0 (eno0) and port 1 (eno1) both configured for 1Gbps.
There are two streams of IPv4/UDP datagrams with a frame length of 64
octets delivered at 100% port load to eno0 and to eno1. eno0 has a flow
steering rule to process the traffic on RX ring 0 (CPU 0), and eno1 has
a flow steering rule towards RX ring 1 (CPU 1).
For the IPFWD test, standard IP routing was enabled in the netns.
For the XDP_DROP test, the samples/bpf/xdp1 program was attached to both
eno0 and to eno1.
For the XDP_TX test, the samples/bpf/xdp2 program was attached to both
eno0 and to eno1.
For the XDP_REDIRECT test, the samples/bpf/xdp_redirect program was
attached once to the input of eno0/output of eno1, and twice to the
input of eno1/output of eno0.
Finally, the preliminary results are as follows:
| IPFWD | XDP_TX | XDP_REDIRECT | XDP_DROP
--------+-------+--------+-------------------------
fps | 761 | 2535 | 1735 | 2783
Gbps | 0.51 | 1.71 | 1.17 | n/a
There is a strange phenomenon in my testing sistem where it appears that
one CPU is processing more than the other. I have not investigated this
too much. Also, the code might not be very well optimized (for example
dma_sync_for_device is called with the full ENETC_RXB_DMA_SIZE_XDP).
Design wise, the ENETC is a PCI device with BD rings, so it uses the
MEM_TYPE_PAGE_SHARED memory model, as can typically be seen in Intel
devices. The strategy was to build upon the existing model that the
driver uses, and not change it too much. So you will see things like a
separate NAPI poll function for XDP.
I have only tested with PAGE_SIZE=4096, and since we split pages in
half, it means that MTU-sized frames are scatter/gather (the XDP
headroom + skb_shared_info only leaves us 1476 bytes of data per
buffer). This is sub-optimal, but I would rather keep it this way and
help speed up Lorenzo's series for S/G support through testing, rather
than change the enetc driver to use some other memory model like page_pool.
My code is already structured for S/G, and that works fine for XDP_DROP
and XDP_TX, just not for XDP_REDIRECT, even between two enetc ports.
So the S/G XDP_REDIRECT is stubbed out (the frames are dropped), but
obviously I would like to remove that limitation soon.
Please note that I am rather new to this kind of stuff, I am more of a
control path person, so I would appreciate feedback.
Enough talking, on to the patches.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Wed, 31 Mar 2021 20:08:57 +0000 (23:08 +0300)]
net: enetc: add support for XDP_REDIRECT
The driver implementation of the XDP_REDIRECT action reuses parts from
XDP_TX, most notably the enetc_xdp_tx function which transmits an array
of TX software BDs. Only this time, the buffers don't have DMA mappings,
we need to create them.
When a BPF program reaches the XDP_REDIRECT verdict for a frame, we can
employ the same buffer reuse strategy as for the normal processing path
and for XDP_PASS: we can flip to the other page half and seed that to
the RX ring.
Note that scatter/gather support is there, but disabled due to lack of
multi-buffer support in XDP (which is added by this series):
https://patchwork.kernel.org/project/netdevbpf/cover/cover.
1616179034.git.lorenzo@kernel.org/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Wed, 31 Mar 2021 20:08:56 +0000 (23:08 +0300)]
net: enetc: increase RX ring default size
As explained in the XDP_TX patch, when receiving a burst of frames with
the XDP_TX verdict, there is a momentary dip in the number of available
RX buffers. The system will eventually recover as TX completions will
start kicking in and refilling our RX BD ring again. But until that
happens, we need to survive with as few out-of-buffer discards as
possible.
This increases the memory footprint of the driver in order to avoid
discards at 2.5Gbps line rate 64B packet sizes, the maximum speed
available for testing on 1 port on NXP LS1028A.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Wed, 31 Mar 2021 20:08:55 +0000 (23:08 +0300)]
net: enetc: add support for XDP_TX
For reflecting packets back into the interface they came from, we create
an array of TX software BDs derived from the RX software BDs. Therefore,
we need to extend the TX software BD structure to contain most of the
stuff that's already present in the RX software BD structure, for
reasons that will become evident in a moment.
For a frame with the XDP_TX verdict, we don't reuse any buffer right
away as we do for XDP_DROP (the same page half) or XDP_PASS (the other
page half, same as the skb code path).
Because the buffer transfers ownership from the RX ring to the TX ring,
reusing any page half right away is very dangerous. So what we can do is
we can recycle the same page half as soon as TX is complete.
The code path is:
enetc_poll
-> enetc_clean_rx_ring_xdp
-> enetc_xdp_tx
-> enetc_refill_rx_ring
(time passes, another MSI interrupt is raised)
enetc_poll
-> enetc_clean_tx_ring
-> enetc_recycle_xdp_tx_buff
But that creates a problem, because there is a potentially large time
window between enetc_xdp_tx and enetc_recycle_xdp_tx_buff, period in
which we'll have less and less RX buffers.
Basically, when the ship starts sinking, the knee-jerk reaction is to
let enetc_refill_rx_ring do what it does for the standard skb code path
(refill every 16 consumed buffers), but that turns out to be very
inefficient. The problem is that we have no rx_swbd->page at our
disposal from the enetc_reuse_page path, so enetc_refill_rx_ring would
have to call enetc_new_page for every buffer that we refill (if we
choose to refill at this early stage). Very inefficient, it only makes
the problem worse, because page allocation is an expensive process, and
CPU time is exactly what we're lacking.
Additionally, there is an even bigger problem: if we let
enetc_refill_rx_ring top up the ring's buffers again from the RX path,
remember that the buffers sent to transmission haven't disappeared
anywhere. They will be eventually sent, and processed in
enetc_clean_tx_ring, and an attempt will be made to recycle them.
But surprise, the RX ring is already full of new buffers, because we
were premature in deciding that we should refill. So not only we took
the expensive decision of allocating new pages, but now we must throw
away perfectly good and reusable buffers.
So what we do is we implement an elastic refill mechanism, which keeps
track of the number of in-flight XDP_TX buffer descriptors. We top up
the RX ring only up to the total ring capacity minus the number of BDs
that are in flight (because we know that those BDs will return to us
eventually).
The enetc driver manages 1 RX ring per CPU, and the default TX ring
management is the same. So we do XDP_TX towards the TX ring of the same
index, because it is affined to the same CPU. This will probably not
produce great results when we have a tc-taprio/tc-mqprio qdisc on the
interface, because in that case, the number of TX rings might be
greater, but I didn't add any checks for that yet (mostly because I
didn't know what checks to add).
It should also be noted that we need to change the DMA mapping direction
for RX buffers, since they may now be reflected into the TX ring of the
same device. We choose to use DMA_BIDIRECTIONAL instead of unmapping and
remapping as DMA_TO_DEVICE, because performance is better this way.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Wed, 31 Mar 2021 20:08:54 +0000 (23:08 +0300)]
net: enetc: add support for XDP_DROP and XDP_PASS
For the RX ring, enetc uses an allocation scheme based on pages split
into two buffers, which is already very efficient in terms of preventing
reallocations / maximizing reuse, so I see no reason why I would change
that.
+--------+--------+--------+--------+--------+--------+--------+
| | | | | | | |
| half B | half B | half B | half B | half B | half B | half B |
| | | | | | | |
+--------+--------+--------+--------+--------+--------+--------+
| | | | | | | |
| half A | half A | half A | half A | half A | half A | half A | RX ring
| | | | | | | |
+--------+--------+--------+--------+--------+--------+--------+
^ ^
| |
next_to_clean next_to_alloc
next_to_use
+--------+--------+--------+--------+--------+
| | | | | |
| half B | half B | half B | half B | half B |
| | | | | |
+--------+--------+--------+--------+--------+--------+--------+
| | | | | | | |
| half B | half B | half A | half A | half A | half A | half A | RX ring
| | | | | | | |
+--------+--------+--------+--------+--------+--------+--------+
| | | ^ ^
| half A | half A | | |
| | | next_to_clean next_to_use
+--------+--------+
^
|
next_to_alloc
then when enetc_refill_rx_ring is called, whose purpose is to advance
next_to_use, it sees that it can take buffers up to next_to_alloc, and
it says "oh, hey, rx_swbd->page isn't NULL, I don't need to allocate
one!".
The only problem is that for default PAGE_SIZE values of 4096, buffer
sizes are 2048 bytes. While this is enough for normal skb allocations at
an MTU of 1500 bytes, for XDP it isn't, because the XDP headroom is 256
bytes, and including skb_shared_info and alignment, we end up being able
to make use of only 1472 bytes, which is insufficient for the default
MTU.
To solve that problem, we implement scatter/gather processing in the
driver, because we would really like to keep the existing allocation
scheme. A packet of 1500 bytes is received in a buffer of 1472 bytes and
another one of 28 bytes.
Because the headroom required by XDP is different (and much larger) than
the one required by the network stack, whenever a BPF program is added
or deleted on the port, we drain the existing RX buffers and seed new
ones with the required headroom. We also keep the required headroom in
rx_ring->buffer_offset.
The simplest way to implement XDP_PASS, where an skb must be created, is
to create an xdp_buff based on the next_to_clean RX BDs, but not clear
those BDs from the RX ring yet, just keep the original index at which
the BDs for this frame started. Then, if the verdict is XDP_PASS,
instead of converting the xdb_buff to an skb, we replay a call to
enetc_build_skb (just as in the normal enetc_clean_rx_ring case),
starting from the original BD index.
We would also like to be minimally invasive to the regular RX data path,
and not check whether there is a BPF program attached to the ring on
every packet. So we create a separate RX ring processing function for
XDP.
Because we only install/remove the BPF program while the interface is
down, we forgo the rcu_read_lock() in enetc_clean_rx_ring, since there
shouldn't be any circumstance in which we are processing packets and
there is a potentially freed BPF program attached to the RX ring.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Wed, 31 Mar 2021 20:08:53 +0000 (23:08 +0300)]
net: enetc: move up enetc_reuse_page and enetc_page_reusable
For XDP_TX, we need to call enetc_reuse_page from enetc_clean_tx_ring,
so we need to avoid a forward declaration.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>