Taehee Yoo [Mon, 9 Apr 2018 14:40:34 +0000 (16:40 +0200)]
netfilter: xt_NFLOG: use nf_log_packet instead of nfulnl_log_packet.
The nfulnl_log_packet() is added to make sure that the NFLOG target
works as only user-space logger. but now, nf_log_packet() can find proper
log function using NF_LOG_TYPE_ULOG and NF_LOG_TYPE_LOG.
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Eric Dumazet [Wed, 18 Apr 2018 01:11:44 +0000 (18:11 -0700)]
ipv6: frags: fix a lockdep false positive
lockdep does not know that the locks used by IPv4 defrag
and IPv6 reassembly units are of different classes.
It complains because of following chains :
1) sch_direct_xmit() (lock txq->_xmit_lock)
dev_hard_start_xmit()
xmit_one()
dev_queue_xmit_nit()
packet_rcv_fanout()
ip_check_defrag()
ip_defrag()
spin_lock() (lock frag queue spinlock)
2) ip6_input_finish()
ipv6_frag_rcv() (lock frag queue spinlock)
ip6_frag_queue()
icmpv6_param_prob() (lock txq->_xmit_lock at some point)
We could add lockdep annotations, but we also can make sure IPv6
calls icmpv6_param_prob() only after the release of the frag queue spinlock,
since this naturally makes frag queue spinlock a leaf in lock hierarchy.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Haiyang Zhang [Tue, 17 Apr 2018 22:31:47 +0000 (15:31 -0700)]
hv_netvsc: Add NetVSP v6 and v6.1 into version negotiation
This patch adds the NetVSP v6 and 6.1 message structures, and includes
these versions into NetVSC/NetVSP version negotiation process.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stephen Hemminger [Tue, 17 Apr 2018 21:25:30 +0000 (14:25 -0700)]
hv_netvsc: propogate Hyper-V friendly name into interface alias
This patch implement the 'Device Naming' feature of the Hyper-V
network device API. In Hyper-V on the host through the GUI or PowerShell
it is possible to enable the device naming feature which causes
the host to make available to the guest the name of the device.
This shows up in the RNDIS protocol as the friendly name.
The name has no particular meaning and is limited to 256 characters.
The value can only be set via PowerShell on the host, but could
be scripted for mass deployments. The default value is the
string 'Network Adapter' and since that is the same for all devices
and useless, the driver ignores it.
In Windows, the value goes into a registry key for use in SNMP
ifAlias. For Linux, this patch puts the value in the network
device alias property; where it is visible in ip tools and SNMP.
The host provided ifAlias is just a suggestion, and can be
overridden by later ip commands.
Also requires exporting dev_set_alias in netdev core.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 19 Apr 2018 01:12:00 +0000 (21:12 -0400)]
Merge branch 'r8169-series-with-further-smaller-improvements'
Heiner Kallweit says:
====================
r8169: series with further smaller improvements
This series includes further smaller improvements.
Then I think the basic cleanup has been done and next step would be
preparing the switch to phylib.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:36:12 +0000 (23:36 +0200)]
r8169: remove jumbo_tx_csum from chip config struct
According to the chip configuration entries only RTL8169 (ver <= 06)
supports tx checksumming for jumbo packets.
By the way: constant JUMBO_1K is a little misleading because it refers
to the standard packet size and not to a jumbo packet size.
By implementing this rule we can get rid of configuring tx checksumming
support per chip type.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:34:22 +0000 (23:34 +0200)]
r8169: improve pci region handling
The region to be used is always the first of type IORESOURCE_MEM.
We can implement this rule directly w/o having to specify which
region is the first one per configuration entry.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:33:03 +0000 (23:33 +0200)]
r8169: drop member txd_version from struct rtl8169_private
txd_version is used in rtl_init_one() only, so we can drop member
txd_version from struct rtl8169_private.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:32:15 +0000 (23:32 +0200)]
r8169: improve rtl8169_get_mac_version
Certain entries in array mac_info[] are redundant, so remove them:
0x7cf, 0x2c200000 (VER 33): matched by entry 0x7c8, 0x2c000000
0x7cf, 0x28300000 (VER 26): matched by entry 0x7c8, 0x28000000
0x7cf, 0x3cb00000 (VER 24): matched by entry 0x7c8, 0x3c800000
0x7cf, 0x3c400000 (VER 22): matched by entry 0x7c8, 0x3c000000
0x7cf, 0x38500000 (VER 17): matched by entry 0x7c8, 0x38000000
0x7cf, 0x44900000 (VER 39): matched by entry 0x7c8, 0x44800000
0x7cf, 0x40b00000 (VER 30): matched by entry 0x7c8, 0x40800000
0x7cf, 0x40a00000 (VER 30): matched by entry 0x7c8, 0x40800000
0x7cf, 0x34a00000 (VER 09): matched by entry 0x7c8, 0x34800000
0x7cf, 0x24a00000 (VER 09): matched by entry 0x7c8, 0x24800000
In addition don't mask out bits 30 and 29 when printing the XID.
Most likely this is a relict from the times when the driver covered
RTL8169 chip version only.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:31:21 +0000 (23:31 +0200)]
r8169: don't display tp->mmio_addr address
For security reasons since commit
ad67b74d2469 "printk: hash addresses
printed with %p" %p doesn't display the full address any longer.
We could switch to %px, but I think the pointer address doesn't
provide a real benefit, so remove printing the hashed address.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:30:29 +0000 (23:30 +0200)]
r8169: drop member opts1_mask from struct rtl8169_private
We can get rid of member opts1_mask and in addition save a few cpu
cycles in the hot path of rtl_rx().
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:29:20 +0000 (23:29 +0200)]
r8169: change interrupt handler argument type
Code can be a little simplified by switching the interrupt handler
argument type to struct rtl8169_private *.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:28:28 +0000 (23:28 +0200)]
r8169: change argument type of counters handling functions
The counter handling functions don't deal with the net_device, so code
can be simplified by changing the argument type to
struct rtl8169_private *.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:27:38 +0000 (23:27 +0200)]
r8169: change hw_start argument type
Code can be simplified by changing the argument type of hw_start
callbacks from struct net_device * to struct rtl8169_private *.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:26:41 +0000 (23:26 +0200)]
r8169: remove rtl8169_map_to_asic
This function is very simple and used only once, so we can inline
the two statements.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:25:46 +0000 (23:25 +0200)]
r8169: replace rx_buf_sz with a constant
rx_buf_sz is constant, so we don't have to pass it as parameter and
in general can replace it with a constant.
When working on this I noticed that also before in
rtl_set_rx_max_size() a value of 0x4000 is set, what is not in line
with the chip spec. According to the spec only bits 0..13 are used
and we set an effective value of zero therefore.
However, the driver still seems to work and due to potential side
effects I'm reluctant to make a change.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:24:43 +0000 (23:24 +0200)]
r8169: remove unneeded check in rtl8169_rx_fill
rtl8169_rx_fill() is called only once and directly before the call
array tp->Rx_databuff[] is filled with zero's. Therefore we don't
need this check.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:23:35 +0000 (23:23 +0200)]
r8169: improve rtl8169_init_ring
This function doesn't use the net_device, therefore change the
parameter to type struct rtl8169_private * to simplify the code.
In addition we don't need the calculations in the memset
statements, we can use the size of the arrays directly.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:22:14 +0000 (23:22 +0200)]
r8169: simplify rtl8169_alloc_rx_data
dev->dev.parent has the same value as tp_to_dev(tp)
(set by SET_NETDEV_DEV() in rtl_init_one()) and we know it can't be NULL.
This allows us to simplify the code.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:21:01 +0000 (23:21 +0200)]
r8169: switch to napi_schedule_irqoff
napi_schedule() is called from hard irq context, so we can switch to
napi_schedule_irqoff() and avoid some overhead.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:20:03 +0000 (23:20 +0200)]
r8169: use constant NAPI_POLL_WAIT
We can use generic constant NAPI_POLL_WAIT instead of defining an own
constant for the same value.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:19:07 +0000 (23:19 +0200)]
r8169: use skb_copy_to_linear_data in rtl8169_try_rx_copy
Not a giant leap for mankind, but let's avoid the open-coded memcpy
and use standard helper skb_copy_to_linear_data instead.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:18:05 +0000 (23:18 +0200)]
r8169: remove member align from struct rtl_cfg_info
Since commit
6f0333b8fde4 "r8169: use 50% less ram for RX ring" member
align isn't used any longer, so remove it.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 17 Apr 2018 21:17:13 +0000 (23:17 +0200)]
r8169: remove unused member features from struct
Member features of struct rtl8169_private isn't used any longer since
commit
6c6aa15fdea5 "r8169: improve interrupt handling", so remove it.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Thu, 19 Apr 2018 01:00:58 +0000 (21:00 -0400)]
Merge branch 'netcp-K2G-SoC-support'
Murali Karicheri says:
====================
Add support for netcp driver on K2G SoC
K2G SoC is another variant of Keystone family of SoCs. This patch
series add support for NetCP driver on this SoC. The QMSS found on
K2G SoC is a cut down version of the QMSS found on other keystone
devices with less number of queues, internal link ram etc. The patch
series has 2 patch sets that goes into the drivers/soc and the
rest has to be applied to net sub system. Please review and merge
if this looks good.
K2G TRM is located at http://www.ti.com/lit/ug/spruhy8g/spruhy8g.pdf
Thanks
The boot logs on K2G ICE board (tftp boot over Ethernet and from mmc)
https://pastebin.ubuntu.com/p/yvZ6drFhkW/
The boot logs on K2G GP board (tftp boot over Ethernet and from mmc)
https://pastebin.ubuntu.com/p/QTr6K7s4Zp/
Also regressed boot on K2HK and K2L EVMs as we have modified GBE
version detection logic (K2E uses same version of NetCP as in K2L.
So regression on one of them is needed).
Boot log on K2L and K2HK EVMs are at
https://pastebin.ubuntu.com/p/N9DBdPjbvR/
This series applies to net-next master branch.
Change history:
v4 - ready for merge to net-next
Folded the series "Add promiscous mode support in k2g network driver"
into this.
Fixed a typo in 5/11 (sgmii to rgmii) based on TI internal comment
Reworked 4/11 and title changed to reflect additional changes to
exclude sgmii configuration code for 2U cpsw. Use IS_SS_ID_2U()
macro for customization.
Added Reviewed-by from Rob Herring against 1/13
v3 - Addressed comments from Andrew Lunn and Grygorii Strashko
against v2.
v2 - Addressed following comments on initial version
- split patch 3/5 to multiple patches from Andrew Lunn
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
WingMan Kwok [Tue, 17 Apr 2018 21:30:42 +0000 (17:30 -0400)]
net: netcp: ethss: k2g: add promiscuous mode support
This patch adds support for promiscuous mode in k2g's network
driver. When upper layer instructs to transition from
non-promiscuous mode to promiscuous mode or vice versa
K2G network driver needs to configure ALE accordingly
so that in case of non-promiscuous mode, ALE will not flood
all unicast packets to host port, while in promiscuous
mode, it will pass all received unicast packets to
host port.
Signed-off-by: WingMan Kwok <w-kwok2@ti.com>
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
WingMan Kwok [Tue, 17 Apr 2018 21:30:41 +0000 (17:30 -0400)]
net: netcp: add api to support set rx mode in netcp modules
This patch adds an API to support setting rx mode in
netcp modules. If a netcp module needs to be notified
when upper layer transitions from one rx mode to
another and react accordingly, such a module will implement
the new API set_rx_mode added in this patch. Currently
rx modes supported are PROMISCUOUS and NON_PROMISCUOUS
modes.
Signed-off-by: WingMan Kwok <w-kwok2@ti.com>
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:40 +0000 (17:30 -0400)]
net: netcp: support probe deferral
The netcp driver shouldn't proceed until the knav qmss and dma
devices are ready. So return -EPROBE_DEFER if these devices are not
ready.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:39 +0000 (17:30 -0400)]
Revert "net: netcp: remove dead code from the driver"
As the probe sequence is not guaranteed contrary to the assumption
of the commit
2d8e276a9030, same has to be reverted.
commit
2d8e276a9030 ("net: netcp: remove dead code from the driver")
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:38 +0000 (17:30 -0400)]
net: netcp: ethss: use of_get_phy_mode() to support different RGMII modes
The phy used for K2G allows for internal delays to be added optionally
to the clock circuitry based on board desing. To add this support,
enhance the driver to use of_get_phy_mode() to read the phy-mode from
the phy device and pass the same to phy through of_phy_connect().
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:37 +0000 (17:30 -0400)]
net: netcp: ethss: re-use stats handling code for 2u hardware
The stats block in 2u cpsw hardware is similar to the one on nu
and hence handle it in a similar way by using a macro that includes
2u hardware as well.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:36 +0000 (17:30 -0400)]
net: netcp: ethss: map vlan priorities to zero flow
The driver currently support only vlan priority zero. So map the
vlan priorities to zero flow in hardware.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:35 +0000 (17:30 -0400)]
net: netcp: ethss: use rgmii link status for 2u cpsw hardware
Introduce rgmii link status to handle link state events for 2u
cpsw hardware on K2G.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:34 +0000 (17:30 -0400)]
net: netcp: ethss: add support for handling rgmii link interface
2u cpsw hardware on K2G uses rgmii link to interface with Phy. So add
support for this interface in the code so that driver can be re-used
for 2u hardware.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:33 +0000 (17:30 -0400)]
net: netcp: ethss: make sgmii configuration conditional
As a preparatory patch to add support for 2u cpsw hardware found on
K2G SoC, make sgmii configuration conditional. This is required
since 2u uses RGMII interface instead of SGMII and to allow for driver
re-use.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:32 +0000 (17:30 -0400)]
net: netcp: ethss: use macro for checking ss_version consistently
Driver currently uses macro for NU and XBE hardwrae, while other
places for older hardware such as that on K2H/K SoC (version 1.4
of the cpsw hardware, it explicitly check for the ss_version
inline. Add a new macro for version 1.4 and use it to customize
code in the driver. While at it also fix similar issue with
checking XBE version by re-using existing macro IS_SS_ID_XGBE().
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:31 +0000 (17:30 -0400)]
soc: ti: K2G: provide APIs to support driver probe deferral
This patch provide APIs to allow client drivers to support
probe deferral. On K2G SoC, devices can be probed only
after the ti_sci_pm_domains driver is probed and ready.
As drivers may get probed at different order, any driver
that depends on knav dma and qmss drivers, for example
netcp network driver, needs to defer probe until
knav devices are probed and ready to service. To do this,
add an API to query the device ready status from the knav
dma and qmss devices.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Murali Karicheri [Tue, 17 Apr 2018 21:30:30 +0000 (17:30 -0400)]
soc: ti: K2G: enhancement to support QMSS in K2G NAVSS
Navigator Subsystem (NAVSS) available on K2G SoC has a cut down
version of QMSS with less number of queues, internal linking ram
with lesser number of buffers etc. It doesn't have status and
explicit push register space as in QMSS available on other K2 SoCs.
So define reg indices specific to QMSS on K2G. This patch introduces
"ti,66ak2g-navss-qm" compatibility to identify QMSS on K2G NAVSS
and to customize the dts handling code. Per Device manual,
descriptors with index less than or equal to regions0_size is in region 0
in the case of K2 QMSS where as for QMSS on K2G, descriptors with index
less than regions0_size is in region 0. So update the size accordingly in
the regions0_size bits of the linking ram size 0 register.
Signed-off-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: WingMan Kwok <w-kwok2@ti.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 18 Apr 2018 03:41:18 +0000 (23:41 -0400)]
Merge branch 'ipv6-Separate-data-structures-for-FIB-and-data-path'
David Ahern says:
====================
net/ipv6: Separate data structures for FIB and data path
IPv6 uses the same data struct for both control plane (FIB entries) and
data path (dst entries). This struct has elements needed for both paths
adding memory overhead and complexity (taking a dst hold in most places
but an additional reference on rt6i_ref in a few). Furthermore, because
of the dst_alloc tie, all FIB entries are allocated with GFP_ATOMIC.
This patch set separates FIB entries from dst entries, better aligning
IPv6 code with IPv4, simplifying the reference counting and allowing
FIB entries added by userspace (not autoconf) to use GFP_KERNEL. It is
first step to a number of performance and scalability changes.
The end result of this patch set:
- FIB entries (fib6_info):
/* size: 208, cachelines: 4, members: 25 */
/* sum members: 207, holes: 1, sum holes: 1 */
- dst entries (rt6_info)
/* size: 240, cachelines: 4, members: 11 */
Versus the the single rt6_info struct today for both paths:
/* size: 320, cachelines: 5, members: 28 */
This amounts to a 35% reduction in memory use for FIB entries and a
25% reduction for dst entries.
With respect to locking FIB entries use RCU and a single atomic
counter with fib6_info_hold and fib6_info_release helpers to manage
the reference counting. dst entries use only the traditional dst
refcounts with dst_hold and dst_release.
FIB entries for host routes are referenced by inet6_ifaddr and
ifacaddr6. In both cases, additional holds are taken -- similar to
what is done for devices.
This set is the first of many changes to improve the scalability of the
IPv6 code. Follow on changes include:
- consolidating duplicate fib6_info references like IPv4 does with
duplicate fib_info
- moving fib6_info into a slab cache to avoid allocation roundups to
power of 2 (the 208 size becomes a 256 actual allocation)
- Allow FIB lookups without generating a dst (e.g., most rt6_lookup
users just want to verify the egress device). Means moving dst
allocation to the other side of fib6_rule_lookup which again aligns
with IPv4 behavior
- using separate standalone nexthop objects which have performance
benefits beyond fib_info consolidation
At this point I am not seeing any refcount leaks or underflows, no
oops or bug_ons, or warnings from kasan, so I think it is ready for
others to beat up on it finding errors in code paths I have missed.
v2 changes
- rebased to top of tree
- improved commit message on patch 7
v1 changes
- rebased to top of tree
- fix memory leak of metrics as noted by Ido
- MTU fixes based on pmtu tests (thanks Stefano Brivio for writing)
RFC v2 changes
- improved commit messages
- move common metrics code from dst.c to net/ipv4/metrics.c (comment
from DaveM)
- address comments from Wei Wang and Martin KaFai Lau (let me know if
I missed something)
- fixes detected by kernel test robots
+ added fib6_metric_set to change metric on a FIB entry which could
be pointing to read-only dst_default_metrics
+ 0day testing found a problem with an intermediate patch; added
dst_hold_safe on rt->from. Code is removed 3 patches later
- allow cacheinfo to handle NULL dst; means only expires is pushed to
userspace
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:27 +0000 (17:33 -0700)]
net/ipv6: Remove unused code and variables for rt6_info
Drop unneeded elements from rt6_info struct and rearrange layout to
something more relevant for the data path.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:26 +0000 (17:33 -0700)]
net/ipv6: Flip FIB entries to fib6_info
Convert all code paths referencing a FIB entry from
rt6_info to fib6_info.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:25 +0000 (17:33 -0700)]
net/ipv6: separate handling of FIB entries from dst based routes
Last step before flipping the data type for FIB entries:
- use fib6_info_alloc to create FIB entries in ip6_route_info_create
and addrconf_dst_alloc
- use fib6_info_release in place of dst_release, ip6_rt_put and
rt6_release
- remove the dst_hold before calling __ip6_ins_rt or ip6_del_rt
- when purging routes, drop per-cpu routes
- replace inc and dec of rt6i_ref with fib6_info_hold and fib6_info_release
- use rt->from since it points to the FIB entry
- drop references to exception bucket, fib6_metrics and per-cpu from
dst entries (those are relevant for fib entries only)
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:24 +0000 (17:33 -0700)]
net/ipv6: introduce fib6_info struct and helpers
Add fib6_info struct and alloc, destroy, hold and release helpers.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:23 +0000 (17:33 -0700)]
net/ipv6: Cleanup exception and cache route handling
IPv6 FIB will only contain FIB entries with exception routes added to
the FIB entry. Once this transformation is complete, FIB lookups will
return a fib6_info with the lookup functions still returning a dst
based rt6_info. The current code uses rt6_info for both paths and
overloads the rt6_info variable usually called 'rt'.
This patch introduces a new 'f6i' variable name for the result of the FIB
lookup and keeps 'rt' as the dst based return variable. 'f6i' becomes a
fib6_info in a later patch which is why it is introduced as f6i now;
avoids the additional churn in the later patch.
In addition, remove RTF_CACHE and dst checks from fib6 add and delete
since they can not happen now and will never happen after the data
type flip.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:22 +0000 (17:33 -0700)]
net/ipv6: Add gfp_flags to route add functions
Most FIB entries can be added using memory allocated with GFP_KERNEL.
Add gfp_flags to ip6_route_add and addrconf_dst_alloc. Code paths that
can be reached from the packet path (e.g., ndisc and autoconfig) or
atomic notifiers use GFP_ATOMIC; paths from user context (adding
addresses and routes) use GFP_KERNEL.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:21 +0000 (17:33 -0700)]
net/ipv6: Create a neigh_lookup for FIB entries
The router discovery code has a FIB entry and wants to validate the
gateway has a neighbor entry. Refactor the existing dst_neigh_lookup
for IPv6 and create a new function that takes the gateway and device
and returns a neighbor entry. Use the new function in
ndisc_router_discovery to validate the gateway.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:20 +0000 (17:33 -0700)]
net/ipv6: Move dst flags to booleans in fib entries
Continuing to wean FIB paths off of dst_entry, use a bool to hold
requests for certain dst settings. Add a helper to convert the
flags to DST flags when a FIB entry is converted to a dst_entry.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:19 +0000 (17:33 -0700)]
net/ipv6: Add rt6_info create function for ip6_pol_route_lookup
ip6_pol_route_lookup is the lookup function for ip6_route_lookup and
rt6_lookup. At the moment it returns either a reference to a FIB entry
or a cached exception. To move FIB entries to a separate struct, this
lookup function needs to convert FIB entries to an rt6_info that is
returned to the caller.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:18 +0000 (17:33 -0700)]
net/ipv6: Add fib6_null_entry
ip6_null_entry will stay a dst based return for lookups that fail to
match an entry.
Add a new fib6_null_entry which constitutes the root node and leafs
for fibs. Replace existing references to ip6_null_entry with the
new fib6_null_entry when dealing with FIBs.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:17 +0000 (17:33 -0700)]
net/ipv6: move expires into rt6_info
Add expires to rt6_info for FIB entries, and add fib6 helpers to
manage it. Data path use of dst.expires remains.
The transition is fairly straightforward: when working with fib entries,
rt->dst.expires is just rt->expires, rt6_clean_expires is replaced with
fib6_clean_expires, rt6_set_expires becomes fib6_set_expires, and
rt6_check_expired becomes fib6_check_expired, where the fib6 versions
are added by this patch.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:16 +0000 (17:33 -0700)]
net/ipv6: move metrics from dst to rt6_info
Similar to IPv4, add fib metrics to the fib struct, which at the moment
is rt6_info. Will be moved to fib6_info in a later patch. Copy metrics
into dst by reference using refcount.
To make the transition:
- add dst_metrics to rt6_info. Default to dst_default_metrics if no
metrics are passed during route add. No need for a separate pmtu
entry; it can reference the MTU slot in fib6_metrics
- ip6_convert_metrics allocates memory in the FIB entry and uses
ip_metrics_convert to copy from netlink attribute to metrics entry
- the convert metrics call is done in ip6_route_info_create simplifying
the route add path
+ fib6_commit_metrics and fib6_copy_metrics and the temporary
mx6_config are no longer needed
- add fib6_metric_set helper to change the value of a metric in the
fib entry since dst_metric_set can no longer be used
- cow_metrics for IPv6 can drop to dst_cow_metrics_generic
- rt6_dst_from_metrics_check is no longer needed
- rt6_fill_node needs the FIB entry and dst as separate arguments to
keep compatibility with existing output. Current dst address is
renamed to dest.
(to be consistent with IPv4 rt6_fill_node really should be split
into 2 functions similar to fib_dump_info and rt_fill_info)
- rt6_fill_node no longer needs the temporary metrics variable
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:15 +0000 (17:33 -0700)]
net/ipv6: Defer initialization of dst to data path
Defer setting dst input, output and error until fib entry is copied.
The reject path from ip6_route_info_create is moved to a new function
ip6_rt_init_dst_reject with a helper doing the conversion from fib6_type
to dst error.
The remainder of the new ip6_rt_init_dst is an amalgamtion of dst code
from addrconf_dst_alloc and the non-reject path of ip6_route_info_create.
The dst output function is always ip6_output and the input function is
either ip6_input (local routes), ip6_mc_input (multicast routes) or
ip6_forward (anything else).
A couple of places using dst.error are updated to look at rt6i_flags.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:14 +0000 (17:33 -0700)]
net/ipv6: Move nexthop data to fib6_nh
Introduce fib6_nh structure and move nexthop related data from
rt6_info and rt6_info.dst to fib6_nh. References to dev, gateway or
lwtstate from a FIB lookup perspective are converted to use fib6_nh;
datapath references to dst version are left as is.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:13 +0000 (17:33 -0700)]
net/ipv6: Save route type in rt6_info
The RTN_ type for IPv6 FIB entries is currently embedded in rt6i_flags
and dst.error. Since dst is going to be removed, it can no longer be
relied on for FIB dumps so save the route type as fib6_type.
fc_type is set in current users based on the algorithm in rt6_fill_node:
- rt6i_flags contains RTF_LOCAL: fc_type = RTN_LOCAL
- rt6i_flags contains RTF_ANYCAST: fc_type = RTN_ANYCAST
- else fc_type = RTN_UNICAST
Similarly, fib6_type is set in the rt6_info templates based on the
RTF_REJECT section of rt6_fill_node converting dst.error to RTN type.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:12 +0000 (17:33 -0700)]
net/ipv6: Move support functions up in route.c
Code move only.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:11 +0000 (17:33 -0700)]
net/ipv6: Pass net namespace to route functions
Pass network namespace reference into route add, delete and get
functions.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:10 +0000 (17:33 -0700)]
net/ipv6: Pass net to fib6_update_sernum
Pass net namespace to fib6_update_sernum. It can not be marked const
as fib6_new_sernum will change ipv6.fib6_sernum.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:09 +0000 (17:33 -0700)]
vrf: Move fib6_table into net_vrf
A later patch removes rt6i_table from rt6_info. Save the ipv6
table for a VRF in net_vrf. fib tables can not be deleted so
no reference counting or locking is required.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:08 +0000 (17:33 -0700)]
net: Handle null dst in rtnl_put_cacheinfo
Need to keep expires time for IPv6 routes in a dump of FIB entries.
Update rtnl_put_cacheinfo to allow dst to be NULL in which case
rta_cacheinfo will only contain non-dst data.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Wed, 18 Apr 2018 00:33:07 +0000 (17:33 -0700)]
net: Move fib_convert_metrics to metrics file
Move logic of fib_convert_metrics into ip_metrics_convert. This allows
the code that converts netlink attributes into metrics struct to be
re-used in a later patch by IPv6.
This is mostly a code move with the following changes to variable names:
- fi->fib_net becomes net
- fc_mx and fc_mx_len are passed as inputs pulled from fib_config
- metrics array is passed as an input from fi->fib_metrics->metrics
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lorenzo Bianconi [Tue, 17 Apr 2018 09:54:39 +0000 (11:54 +0200)]
ipv6: send netlink notifications for manually configured addresses
Send a netlink notification when userspace adds a manually configured
address if DAD is enabled and optimistic flag isn't set.
Moreover send RTM_DELADDR notifications for tentative addresses.
Some userspace applications (e.g. NetworkManager) are interested in
addr netlink events albeit the address is still in tentative state,
however events are not sent if DAD process is not completed.
If the address is added and immediately removed userspace listeners
are not notified. This behaviour can be easily reproduced by using
veth interfaces:
$ ip -b - <<EOF
> link add dev vm1 type veth peer name vm2
> link set dev vm1 up
> link set dev vm2 up
> addr add 2001:db8:a:b:1:2:3:4/64 dev vm1
> addr del 2001:db8:a:b:1:2:3:4/64 dev vm1
EOF
This patch reverts the behaviour introduced by the commit
f784ad3d79e5
("ipv6: do not send RTM_DELADDR for tentative addresses")
Suggested-by: Thomas Haller <thaller@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ganesh Goudar [Tue, 17 Apr 2018 09:47:11 +0000 (15:17 +0530)]
cxgb4vf: display pause settings
Add support to display pause settings
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Hangbin Liu [Tue, 17 Apr 2018 06:11:28 +0000 (14:11 +0800)]
vxlan: add ttl inherit support
Like tos inherit, ttl inherit should also means inherit the inner protocol's
ttl values, which actually not implemented in vxlan yet.
But we could not treat ttl == 0 as "use the inner TTL", because that would be
used also when the "ttl" option is not specified and that would be a behavior
change, and breaking real use cases.
So add a different attribute IFLA_VXLAN_TTL_INHERIT when "ttl inherit" is
specified with ip cmd.
Reported-by: Jianlin Shi <jishi@redhat.com>
Suggested-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Samuel Mendoza-Jonas [Tue, 17 Apr 2018 04:23:23 +0000 (14:23 +1000)]
net/ncsi: Refactor MAC, VLAN filters
The NCSI driver defines a generic ncsi_channel_filter struct that can be
used to store arbitrarily formatted filters, and several generic methods
of accessing data stored in such a filter.
However in both the driver and as defined in the NCSI specification
there are only two actual filters: VLAN ID filters and MAC address
filters. The splitting of the MAC filter into unicast, multicast, and
mixed is also technically not necessary as these are stored in the same
location in hardware.
To save complexity, particularly in the set up and accessing of these
generic filters, remove them in favour of two specific structs. These
can be acted on directly and do not need several generic helper
functions to use.
This also fixes a memory error found by KASAN on ARM32 (which is not
upstream yet), where response handlers accessing a filter's data field
could write past allocated memory.
[ 114.926512] ==================================================================
[ 114.933861] BUG: KASAN: slab-out-of-bounds in ncsi_configure_channel+0x4b8/0xc58
[ 114.941304] Read of size 2 at addr
94888558 by task kworker/0:2/546
[ 114.947593]
[ 114.949146] CPU: 0 PID: 546 Comm: kworker/0:2 Not tainted
4.16.0-rc6-00119-ge156398bfcad #13
...
[ 115.170233] The buggy address belongs to the object at
94888540
[ 115.170233] which belongs to the cache kmalloc-32 of size 32
[ 115.181917] The buggy address is located 24 bytes inside of
[ 115.181917] 32-byte region [
94888540,
94888560)
[ 115.192115] The buggy address belongs to the page:
[ 115.196943] page:
9eeac100 count:1 mapcount:0 mapping:
94888000 index:0x94888fc1
[ 115.204200] flags: 0x100(slab)
[ 115.207330] raw:
00000100 94888000 94888fc1 0000003f 00000001 9eea2014 9eecaa74 96c003e0
[ 115.215444] page dumped because: kasan: bad access detected
[ 115.221036]
[ 115.222544] Memory state around the buggy address:
[ 115.227384]
94888400: fb fb fb fb fc fc fc fc 04 fc fc fc fc fc fc fc
[ 115.233959]
94888480: 00 00 00 fc fc fc fc fc 00 04 fc fc fc fc fc fc
[ 115.240529] >
94888500: 00 00 04 fc fc fc fc fc 00 00 04 fc fc fc fc fc
[ 115.247077] ^
[ 115.252523]
94888580: 00 04 fc fc fc fc fc fc 06 fc fc fc fc fc fc fc
[ 115.259093]
94888600: 00 00 06 fc fc fc fc fc 00 00 04 fc fc fc fc fc
[ 115.265639] ==================================================================
Reported-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Biggers [Mon, 16 Apr 2018 21:29:22 +0000 (14:29 -0700)]
KEYS: DNS: limit the length of option strings
Adding a dns_resolver key whose payload contains a very long option name
resulted in that string being printed in full. This hit the WARN_ONCE()
in set_precision() during the printk(), because printk() only supports a
precision of up to 32767 bytes:
precision
1000000 too large
WARNING: CPU: 0 PID: 752 at lib/vsprintf.c:2189 vsnprintf+0x4bc/0x5b0
Fix it by limiting option strings (combined name + value) to a much more
reasonable 128 bytes. The exact limit is arbitrary, but currently the
only recognized option is formatted as "dnserror=%lu" which fits well
within this limit.
Also ratelimit the printks.
Reproducer:
perl -e 'print "#", "A" x
1000000, "\x00"' | keyctl padd dns_resolver desc @s
This bug was found using syzkaller.
Reported-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 4a2d789267e0 ("DNS: If the DNS server returns an error, allow that to be cached [ver #2]")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Davide Caratti [Mon, 16 Apr 2018 20:59:26 +0000 (22:59 +0200)]
selftest: tc_flower: add testcase for 'ip_flags'
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stephen Suryaputra [Mon, 16 Apr 2018 17:42:16 +0000 (13:42 -0400)]
ipv6: Count interface receive statistics on the ingress netdev
The statistics such as InHdrErrors should be counted on the ingress
netdev rather than on the dev from the dst, which is the egress.
Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Ahern [Tue, 17 Apr 2018 17:00:39 +0000 (10:00 -0700)]
net/ipv6: Make __inet6_bind static
BPF core gets access to __inet6_bind via ipv6_bpf_stub_impl, so it is
not invoked directly outside of af_inet6.c. Make it static and move
inet6_bind after to avoid forward declaration.
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 17 Apr 2018 14:50:30 +0000 (10:50 -0400)]
Merge branch 'XDP-redirect-memory-return-API'
Jesper Dangaard Brouer says:
====================
XDP redirect memory return API
Submitted against net-next, as it contains NIC driver changes.
This patchset works towards supporting different XDP RX-ring memory
allocators. As this will be needed by the AF_XDP zero-copy mode.
The patchset uses mlx5 as the sample driver, which gets implemented
XDP_REDIRECT RX-mode, but not ndo_xdp_xmit (as this API is subject to
change thought the patchset).
A new struct xdp_frame is introduced (modeled after cpumap xdp_pkt).
And both ndo_xdp_xmit and the new xdp_return_frame end-up using this.
Support for a driver supplied allocator is implemented, and a
refurbished version of page_pool is the first return allocator type
introduced. This will be a integration point for AF_XDP zero-copy.
The mlx5 driver evolve into using the page_pool, and see a performance
increase (with ndo_xdp_xmit out ixgbe driver) from 6Mpps to 12Mpps.
The patchset stop at 16 patches (one over limit), but more API changes
are planned. Specifically extending ndo_xdp_xmit and xdp_return_frame
APIs to support bulking. As this will address some known limits.
V2: Updated according to Tariq's feedback
V3: Updated based on feedback from Jason Wang and Alex Duyck
V4: Updated based on feedback from Tariq and Jason
V5: Fix SPDX license, add Tariq's reviews, improve patch desc for perf test
V6: Updated based on feedback from Eric Dumazet and Alex Duyck
V7: Adapt to i40e that got XDP_REDIRECT support in-between
V8:
Updated based on feedback kbuild test robot, and adjust for mlx5 changes
page_pool only compiled into kernel when drivers Kconfig 'select' feature
V9:
Remove some inline statements, let compiler decide what to inline
Fix return value in virtio_net driver
Adjust for mlx5 changes in-between submissions
V10:
Minor adjust for mlx5 requested by Tariq
Resubmit against net-next
V11: avoid leaking info stored in frame data on page reuse
====================
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:43 +0000 (16:46 +0200)]
xdp: avoid leaking info stored in frame data on page reuse
The bpf infrastructure and verifier goes to great length to avoid
bpf progs leaking kernel (pointer) info.
For queueing an xdp_buff via XDP_REDIRECT, xdp_frame info stores
kernel info (incl pointers) in top part of frame data (xdp->data_hard_start).
Checks are in place to assure enough headroom is available for this.
This info is not cleared, and if the frame is reused, then a
malicious user could use bpf_xdp_adjust_head helper to move
xdp->data into this area. Thus, making this area readable.
This is not super critical as XDP progs requires root or
CAP_SYS_ADMIN, which are privileged enough for such info. An
effort (is underway) towards moving networking bpf hooks to the
lesser privileged mode CAP_NET_ADMIN, where leaking such info
should be avoided. Thus, this patch to clear the info when
needed.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:37 +0000 (16:46 +0200)]
xdp: transition into using xdp_frame for ndo_xdp_xmit
Changing API ndo_xdp_xmit to take a struct xdp_frame instead of struct
xdp_buff. This brings xdp_return_frame and ndp_xdp_xmit in sync.
This builds towards changing the API further to become a bulk API,
because xdp_buff is not a queue-able object while xdp_frame is.
V4: Adjust for commit
59655a5b6c83 ("tuntap: XDP_TX can use native XDP")
V7: Adjust for commit
d9314c474d4f ("i40e: add support for XDP_REDIRECT")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:32 +0000 (16:46 +0200)]
xdp: transition into using xdp_frame for return API
Changing API xdp_return_frame() to take struct xdp_frame as argument,
seems like a natural choice. But there are some subtle performance
details here that needs extra care, which is a deliberate choice.
When de-referencing xdp_frame on a remote CPU during DMA-TX
completion, result in the cache-line is change to "Shared"
state. Later when the page is reused for RX, then this xdp_frame
cache-line is written, which change the state to "Modified".
This situation already happens (naturally) for, virtio_net, tun and
cpumap as the xdp_frame pointer is the queued object. In tun and
cpumap, the ptr_ring is used for efficiently transferring cache-lines
(with pointers) between CPUs. Thus, the only option is to
de-referencing xdp_frame.
It is only the ixgbe driver that had an optimization, in which it can
avoid doing the de-reference of xdp_frame. The driver already have
TX-ring queue, which (in case of remote DMA-TX completion) have to be
transferred between CPUs anyhow. In this data area, we stored a
struct xdp_mem_info and a data pointer, which allowed us to avoid
de-referencing xdp_frame.
To compensate for this, a prefetchw is used for telling the cache
coherency protocol about our access pattern. My benchmarks show that
this prefetchw is enough to compensate the ixgbe driver.
V7: Adjust for commit
d9314c474d4f ("i40e: add support for XDP_REDIRECT")
V8: Adjust for commit
bd658dda4237 ("net/mlx5e: Separate dma base address
and offset in dma_sync call")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:27 +0000 (16:46 +0200)]
mlx5: use page_pool for xdp_return_frame call
This patch shows how it is possible to have both the driver local page
cache, which uses elevated refcnt for "catching"/avoiding SKB
put_page returns the page through the page allocator. And at the
same time, have pages getting returned to the page_pool from
ndp_xdp_xmit DMA completion.
The performance improvement for XDP_REDIRECT in this patch is really
good. Especially considering that (currently) the xdp_return_frame
API and page_pool_put_page() does per frame operations of both
rhashtable ID-lookup and locked return into (page_pool) ptr_ring.
(It is the plan to remove these per frame operation in a followup
patchset).
The benchmark performed was RX on mlx5 and XDP_REDIRECT out ixgbe,
with xdp_redirect_map (using devmap) . And the target/maximum
capability of ixgbe is 13Mpps (on this HW setup).
Before this patch for mlx5, XDP redirected frames were returned via
the page allocator. The single flow performance was 6Mpps, and if I
started two flows the collective performance drop to 4Mpps, because we
hit the page allocator lock (further negative scaling occurs).
Two test scenarios need to be covered, for xdp_return_frame API, which
is DMA-TX completion running on same-CPU or cross-CPU free/return.
Results were same-CPU=10Mpps, and cross-CPU=12Mpps. This is very
close to our 13Mpps max target.
The reason max target isn't reached in cross-CPU test, is likely due
to RX-ring DMA unmap/map overhead (which doesn't occur in ixgbe to
ixgbe testing). It is also planned to remove this unnecessary DMA
unmap in a later patchset
V2: Adjustments requested by Tariq
- Changed page_pool_create return codes not return NULL, only
ERR_PTR, as this simplifies err handling in drivers.
- Save a branch in mlx5e_page_release
- Correct page_pool size calc for MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ
V5: Updated patch desc
V8: Adjust for
b0cedc844c00 ("net/mlx5e: Remove rq_headroom field from params")
V9:
- Adjust for
121e89275471 ("net/mlx5e: Refactor RQ XDP_TX indication")
- Adjust for
73281b78a37a ("net/mlx5e: Derive Striding RQ size from MTU")
- Correct handling if page_pool_create fail for MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ
V10: Req from Tariq
- Change pool_size calc for MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:22 +0000 (16:46 +0200)]
xdp: allow page_pool as an allocator type in xdp_return_frame
New allocator type MEM_TYPE_PAGE_POOL for page_pool usage.
The registered allocator page_pool pointer is not available directly
from xdp_rxq_info, but it could be (if needed). For now, the driver
should keep separate track of the page_pool pointer, which it should
use for RX-ring page allocation.
As suggested by Saeed, to maintain a symmetric API it is the drivers
responsibility to allocate/create and free/destroy the page_pool.
Thus, after the driver have called xdp_rxq_info_unreg(), it is drivers
responsibility to free the page_pool, but with a RCU free call. This
is done easily via the page_pool helper page_pool_destroy() (which
avoids touching any driver code during the RCU callback, which could
happen after the driver have been unloaded).
V8: address issues found by kbuild test robot
- Address sparse should be static warnings
- Allow xdp.o to be compiled without page_pool.o
V9: Remove inline from .c file, compiler knows best
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:17 +0000 (16:46 +0200)]
page_pool: refurbish version of page_pool code
Need a fast page recycle mechanism for ndo_xdp_xmit API for returning
pages on DMA-TX completion time, which have good cross CPU
performance, given DMA-TX completion time can happen on a remote CPU.
Refurbish my page_pool code, that was presented[1] at MM-summit 2016.
Adapted page_pool code to not depend the page allocator and
integration into struct page. The DMA mapping feature is kept,
even-though it will not be activated/used in this patchset.
[1] http://people.netfilter.org/hawk/presentations/MM-summit2016/generic_page_pool_mm_summit2016.pdf
V2: Adjustments requested by Tariq
- Changed page_pool_create return codes, don't return NULL, only
ERR_PTR, as this simplifies err handling in drivers.
V4: many small improvements and cleanups
- Add DOC comment section, that can be used by kernel-doc
- Improve fallback mode, to work better with refcnt based recycling
e.g. remove a WARN as pointed out by Tariq
e.g. quicker fallback if ptr_ring is empty.
V5: Fixed SPDX license as pointed out by Alexei
V6: Adjustments requested by Eric Dumazet
- Adjust ____cacheline_aligned_in_smp usage/placement
- Move rcu_head in struct page_pool
- Free pages quicker on destroy, minimize resources delayed an RCU period
- Remove code for forward/backward compat ABI interface
V8: Issues found by kbuild test robot
- Address sparse should be static warnings
- Only compile+link when a driver use/select page_pool,
mlx5 selects CONFIG_PAGE_POOL, although its first used in two patches
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:12 +0000 (16:46 +0200)]
xdp: rhashtable with allocator ID to pointer mapping
Use the IDA infrastructure for getting a cyclic increasing ID number,
that is used for keeping track of each registered allocator per
RX-queue xdp_rxq_info. Instead of using the IDR infrastructure, which
uses a radix tree, use a dynamic rhashtable, for creating ID to
pointer lookup table, because this is faster.
The problem that is being solved here is that, the xdp_rxq_info
pointer (stored in xdp_buff) cannot be used directly, as the
guaranteed lifetime is too short. The info is needed on a
(potentially) remote CPU during DMA-TX completion time . In an
xdp_frame the xdp_mem_info is stored, when it got converted from an
xdp_buff, which is sufficient for the simple page refcnt based recycle
schemes.
For more advanced allocators there is a need to store a pointer to the
registered allocator. Thus, there is a need to guard the lifetime or
validity of the allocator pointer, which is done through this
rhashtable ID map to pointer. The removal and validity of of the
allocator and helper struct xdp_mem_allocator is guarded by RCU. The
allocator will be created by the driver, and registered with
xdp_rxq_info_reg_mem_model().
It is up-to debate who is responsible for freeing the allocator
pointer or invoking the allocator destructor function. In any case,
this must happen via RCU freeing.
Use the IDA infrastructure for getting a cyclic increasing ID number,
that is used for keeping track of each registered allocator per
RX-queue xdp_rxq_info.
V4: Per req of Jason Wang
- Use xdp_rxq_info_reg_mem_model() in all drivers implementing
XDP_REDIRECT, even-though it's not strictly necessary when
allocator==NULL for type MEM_TYPE_PAGE_SHARED (given it's zero).
V6: Per req of Alex Duyck
- Introduce rhashtable_lookup() call in later patch
V8: Address sparse should be static warnings (from kbuild test robot)
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:07 +0000 (16:46 +0200)]
mlx5: register a memory model when XDP is enabled
Now all the users of ndo_xdp_xmit have been converted to use xdp_return_frame.
This enable a different memory model, thus activating another code path
in the xdp_return_frame API.
V2: Fixed issues pointed out by Tariq.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:46:02 +0000 (16:46 +0200)]
i40e: convert to use generic xdp_frame and xdp_return_frame API
Also convert driver i40e, which very recently got XDP_REDIRECT support
in commit
d9314c474d4f ("i40e: add support for XDP_REDIRECT").
V7: This patch got added in V7 of this patchset.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:45:57 +0000 (16:45 +0200)]
bpf: cpumap convert to use generic xdp_frame
The generic xdp_frame format, was inspired by the cpumap own internal
xdp_pkt format. It is now time to convert it over to the generic
xdp_frame format. The cpumap needs one extra field dev_rx.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:45:52 +0000 (16:45 +0200)]
virtio_net: convert to use generic xdp_frame and xdp_return_frame API
The virtio_net driver assumes XDP frames are always released based on
page refcnt (via put_page). Thus, is only queues the XDP data pointer
address and uses virt_to_head_page() to retrieve struct page.
Use the XDP return API to get away from such assumptions. Instead
queue an xdp_frame, which allow us to use the xdp_return_frame API,
when releasing the frame.
V8: Avoid endianness issues (found by kbuild test robot)
V9: Change __virtnet_xdp_xmit from bool to int return value (found by Dan Carpenter)
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:45:47 +0000 (16:45 +0200)]
tun: convert to use generic xdp_frame and xdp_return_frame API
The tuntap driver invented it's own driver specific way of queuing
XDP packets, by storing the xdp_buff information in the top of
the XDP frame data.
Convert it over to use the more generic xdp_frame structure. The
main problem with the in-driver method is that the xdp_rxq_info pointer
cannot be trused/used when dequeueing the frame.
V3: Remove check based on feedback from Jason
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:45:42 +0000 (16:45 +0200)]
xdp: introduce a new xdp_frame type
This is needed to convert drivers tuntap and virtio_net.
This is a generalization of what is done inside cpumap, which will be
converted later.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:45:37 +0000 (16:45 +0200)]
xdp: move struct xdp_buff from filter.h to xdp.h
This is done to prepare for the next patch, and it is also
nice to move this XDP related struct out of filter.h.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:45:32 +0000 (16:45 +0200)]
ixgbe: use xdp_return_frame API
Extend struct ixgbe_tx_buffer to store the xdp_mem_info.
Notice that this could be optimized further by putting this into
a union in the struct ixgbe_tx_buffer, but this patchset
works towards removing this again. Thus, this is not done.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:45:26 +0000 (16:45 +0200)]
xdp: introduce xdp_return_frame API and use in cpumap
Introduce an xdp_return_frame API, and convert over cpumap as
the first user, given it have queued XDP frame structure to leverage.
V3: Cleanup and remove C99 style comments, pointed out by Alex Duyck.
V6: Remove comment that id will be added later (Req by Alex Duyck)
V8: Rename enum mem_type to xdp_mem_type (found by kbuild test robot)
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jesper Dangaard Brouer [Tue, 17 Apr 2018 14:45:21 +0000 (16:45 +0200)]
mlx5: basic XDP_REDIRECT forward support
This implements basic XDP redirect support in mlx5 driver.
Notice that the ndo_xdp_xmit() is NOT implemented, because that API
need some changes that this patchset is working towards.
The main purpose of this patch is have different drivers doing
XDP_REDIRECT to show how different memory models behave in a cross
driver world.
Update(pre-RFCv2 Tariq): Need to DMA unmap page before xdp_do_redirect,
as the return API does not exist yet to to keep this mapped.
Update(pre-RFCv3 Saeed): Don't mix XDP_TX and XDP_REDIRECT flushing,
introduce xdpsq.db.redirect_flush boolian.
V9: Adjust for commit
121e89275471 ("net/mlx5e: Refactor RQ XDP_TX indication")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Intiyaz Basha [Tue, 17 Apr 2018 06:30:53 +0000 (23:30 -0700)]
liquidio: Enhanced ethtool stats
1. Added red_drops stats. Inbound packets dropped by RED, buffer exhaustion
2. Included fcs_err, jabber_err, l2_err and frame_err errors under
rx_errors
3. Included fifo_err, dmac_drop, red_drops, fw_err_pko, fw_err_link and
fw_err_drop under rx_dropped
4. Included max_collision_fail, max_deferral_fail, total_collisions,
fw_err_pko, fw_err_link, fw_err_drop and fw_err_pki under tx_dropped
5. Counting dma mapping errors
6. Added some firmware stats description and removed for some
Signed-off-by: Intiyaz Basha <intiyaz.basha@cavium.com>
Acked-by: Derek Chickles <derek.chickles@cavium.com>
Acked-by: Satanand Burla <satananda.burla@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Andrey Ignatov [Mon, 16 Apr 2018 22:07:13 +0000 (15:07 -0700)]
net: Remove unused tcp_set_state tracepoint
This tracepoint was replaced by inet_sock_set_state in
563e0bb and not
used anywhere in the kernel anymore. Remove it.
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 16 Apr 2018 22:55:05 +0000 (18:55 -0400)]
Merge branch 'pci-mrrs-consts'
Heiner Kallweit says:
====================
PCI: add two more values for PCIe Max_Read_Request_Size and initially use them in r8169 network driver
In r8169 network driver I stumbled across a magic number translating
to PCI MRRS size 4K. The PCI core is still missing constants for
values 2K and 4K (as defined in PCI standard).
So let's add these two constants and use the 4K constant in r8169.
Second patch depends on the first one, therefore both patches
preferrably should go through either PCI or netdev tree.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Mon, 16 Apr 2018 19:38:27 +0000 (21:38 +0200)]
r8169: replace magic numbers with PCI MRRS constant
Replace magic number "0x5 << MAX_READ_REQUEST_SHIFT" with the
appropriate constant as defined in PCI core.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Mon, 16 Apr 2018 19:37:13 +0000 (21:37 +0200)]
PCI: Add two more values for PCIe Max_Read_Request_Size
This patch adds missing values for the max read request size.
E.g. network driver r8169 uses a value of 4K.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 16 Apr 2018 22:50:12 +0000 (18:50 -0400)]
Merge branch 'net-stmmac-Stop-using-hard-coded-callbacks'
Jose Abreu says:
====================
net: stmmac: Stop using hard-coded callbacks
This a starting point for a cleanup and re-organization of stmmac.
In this series we stop using hard-coded callbacks along the code and use
instead helpers which are defined in a single place ("hwif.h").
This brings several advantages:
1) Less typing :)
2) Guaranteed function pointer check
3) More flexibility
By 2) we stop using the repeated pattern of:
if (priv->hw->mac->some_func)
priv->hw->mac->some_func(...)
I didn't check but I expect the final .ko will be bigger with this series
because *all* of function pointers are checked.
Anyway, I hope this can make the code more readable and more flexible now.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Jose Abreu [Mon, 16 Apr 2018 15:08:16 +0000 (16:08 +0100)]
net: stmmac: Switch stmmac_mode_ops to generic HW Interface Helpers
Switch stmmac_mode_ops to generic Hardware Interface Helpers instead of
using hard-coded callbacks. This makes the code more readable and more
flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jose Abreu [Mon, 16 Apr 2018 15:08:15 +0000 (16:08 +0100)]
net: stmmac: Switch stmmac_hwtimestamp to generic HW Interface Helpers
Switch stmmac_hwtimestamp to generic Hardware Interface Helpers instead
of using hard-coded callbacks. This makes the code more readable and
more flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jose Abreu [Mon, 16 Apr 2018 15:08:14 +0000 (16:08 +0100)]
net: stmmac: Switch stmmac_ops to generic HW Interface Helpers
Switch stmmac_ops to generic Hardware Interface Helpers instead of using
hard-coded callbacks. This makes the code more readable and more
flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jose Abreu [Mon, 16 Apr 2018 15:08:13 +0000 (16:08 +0100)]
net: stmmac: Switch stmmac_dma_ops to generic HW Interface Helpers
Switch stmmac_dma_ops to generic Hardware Interface Helpers instead of
using hard-coded callbacks. This makes the code more readable and more
flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jose Abreu [Mon, 16 Apr 2018 15:08:12 +0000 (16:08 +0100)]
net: stmmac: Switch stmmac_desc_ops to generic HW Interface Helpers
Switch stmmac_desc_ops to generic Hardware Interface Helpers instead of
using hard-coded callbacks. This makes the code more readable and more
flexible.
No functional change.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 16 Apr 2018 22:26:38 +0000 (18:26 -0400)]
Merge branch 'tcp-zero-copy-receive'
Eric Dumazet says:
====================
tcp: add zero copy receive
This patch series add mmap() support to TCP sockets for RX zero copy.
While tcp_mmap() patch itself is quite small (~100 LOC), optimal support
for asynchronous mmap() required better SO_RCVLOWAT behavior, and a
test program to demonstrate how mmap() on TCP sockets can be used.
Note that mmap() (and associated munmap()) calls are adding more
pressure on per-process VM semaphore, so might not show benefit
for processus with high number of threads.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Mon, 16 Apr 2018 17:33:39 +0000 (10:33 -0700)]
selftests: net: add tcp_mmap program
This is a reference program showing how mmap() can be used
on TCP flows to implement receive zero copy.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Mon, 16 Apr 2018 17:33:38 +0000 (10:33 -0700)]
tcp: implement mmap() for zero copy receive
Some networks can make sure TCP payload can exactly fit 4KB pages,
with well chosen MSS/MTU and architectures.
Implement mmap() system call so that applications can avoid
copying data without complex splice() games.
Note that a successful mmap( X bytes) on TCP socket is consuming
bytes, as if recvmsg() has been done. (tp->copied += X)
Only PROT_READ mappings are accepted, as skb page frags
are fundamentally shared and read only.
If tcp_mmap() finds data that is not a full page, or a patch of
urgent data, -EINVAL is returned, no bytes are consumed.
Application must fallback to recvmsg() to read the problematic sequence.
mmap() wont block, regardless of socket being in blocking or
non-blocking mode. If not enough bytes are in receive queue,
mmap() would return -EAGAIN, or -EIO if socket is in a state
where no other bytes can be added into receive queue.
An application might use SO_RCVLOWAT, poll() and/or ioctl( FIONREAD)
to efficiently use mmap()
On the sender side, MSG_EOR might help to clearly separate unaligned
headers and 4K-aligned chunks if necessary.
Tested:
mlx4 (cx-3) 40Gbit NIC, with tcp_mmap program provided in following patch.
MTU set to 4168 (4096 TCP payload, 40 bytes IPv6 header, 32 bytes TCP header)
Without mmap() (tcp_mmap -s)
received 32768 MB (0 % mmap'ed) in 8.13342 s, 33.7961 Gbit,
cpu usage user:0.034 sys:3.778, 116.333 usec per MB, 63062 c-switches
received 32768 MB (0 % mmap'ed) in 8.14501 s, 33.748 Gbit,
cpu usage user:0.029 sys:3.997, 122.864 usec per MB, 61903 c-switches
received 32768 MB (0 % mmap'ed) in 8.11723 s, 33.8635 Gbit,
cpu usage user:0.048 sys:3.964, 122.437 usec per MB, 62983 c-switches
received 32768 MB (0 % mmap'ed) in 8.39189 s, 32.7552 Gbit,
cpu usage user:0.038 sys:4.181, 128.754 usec per MB, 55834 c-switches
With mmap() on receiver (tcp_mmap -s -z)
received 32768 MB (100 % mmap'ed) in 8.03083 s, 34.2278 Gbit,
cpu usage user:0.024 sys:1.466, 45.4712 usec per MB, 65479 c-switches
received 32768 MB (100 % mmap'ed) in 7.98805 s, 34.4111 Gbit,
cpu usage user:0.026 sys:1.401, 43.5486 usec per MB, 65447 c-switches
received 32768 MB (100 % mmap'ed) in 7.98377 s, 34.4296 Gbit,
cpu usage user:0.028 sys:1.452, 45.166 usec per MB, 65496 c-switches
received 32768 MB (99.9969 % mmap'ed) in 8.01838 s, 34.281 Gbit,
cpu usage user:0.02 sys:1.446, 44.7388 usec per MB, 65505 c-switches
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>