* [PATCH net-next 6/6] net: ethernet: ti: cpsw: add macvlan and ucast/vlan filtering support
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
In-Reply-To: <20190226184556.16082-1-ivan.khoronzhuk@linaro.org>
The cpsw supports unicast filtering as for real as for vlan devices
now, but has no flag set for that. As result, once macvlan or vlan
adds new ucast address the cpsw is silently toggled to promiscuous
mode. That's smth not expected, so patch fixes it.
A unicast address for vlan has to be presented by vlan/unicast entry
in ALE table. At this moment, while vlan address change, entry is not
created in any form, even just like real device unicast used for
macvlan, leaving only address inherited from real device created
while vlan addition.
Therefore, program unicast entries for vlans by using IVDF, it allows
to add only vlan/unicast entries for vlans, omitting real device
ucast entries unless they are added for macvans or so, as they are
redundant for vlans and just consume forwarding table and in case of
matching packet income - CPU time.
So, after this patch, cpsw has ability to handle macvlan and vlan
ucasts, synchronizing ucast tables for these devices with cpsw ALE
table exclusively.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/cpsw.c | 62 ++++++++++++++++++++++++++++++----
1 file changed, 56 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index fd76d1f12911..c6d5ddc05299 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -693,6 +693,31 @@ static int cpsw_set_mc(struct net_device *ndev, const u8 *addr,
return ret;
}
+static int cpsw_set_uc(struct net_device *ndev, const u8 *addr,
+ int vid, int add)
+{
+ struct cpsw_priv *priv = netdev_priv(ndev);
+ struct cpsw_common *cpsw = priv->cpsw;
+ int flags, port, ret;
+
+ if (vid < 0) {
+ if (cpsw->data.dual_emac)
+ vid = cpsw->slaves[priv->emac_port].port_vlan;
+ else
+ vid = 0;
+ }
+
+ port = HOST_PORT_NUM;
+ flags = vid ? ALE_VLAN : 0;
+
+ if (add)
+ ret = cpsw_ale_add_ucast(cpsw->ale, addr, port, flags, vid);
+ else
+ ret = cpsw_ale_del_ucast(cpsw->ale, addr, port, flags, vid);
+
+ return ret;
+}
+
static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr)
{
u16 vid;
@@ -711,6 +736,24 @@ static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr)
return 0;
}
+static int cpsw_add_uc_addr(struct net_device *ndev, const u8 *addr)
+{
+ u16 vid;
+
+ vid = vlan_dev_get_addr_vid(ndev, addr);
+ cpsw_set_uc(ndev, addr, vid ? vid : -1, 1);
+ return 0;
+}
+
+static int cpsw_del_uc_addr(struct net_device *ndev, const u8 *addr)
+{
+ u16 vid;
+
+ vid = vlan_dev_get_addr_vid(ndev, addr);
+ cpsw_set_uc(ndev, addr, vid ? vid : -1, 0);
+ return 0;
+}
+
static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
{
struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
@@ -730,6 +773,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
/* add/remove mcast address either for real netdev or for vlan */
__dev_mc_sync(ndev, cpsw_add_mc_addr, cpsw_del_mc_addr);
+ __dev_uc_sync(ndev, cpsw_add_uc_addr, cpsw_del_uc_addr);
}
static void cpsw_intr_enable(struct cpsw_common *cpsw)
@@ -2009,6 +2053,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
cpsw_info(priv, ifdown, "shutting down cpsw device\n");
__dev_mc_unsync(ndev, cpsw_del_mc_addr);
+ __dev_uc_unsync(ndev, cpsw_del_uc_addr);
netif_tx_stop_all_queues(priv->ndev);
netif_carrier_off(priv->ndev);
@@ -2369,10 +2414,12 @@ static inline int cpsw_add_vlan_ale_entry(struct cpsw_priv *priv,
if (ret != 0)
return ret;
- ret = cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
- HOST_PORT_NUM, ALE_VLAN, vid);
- if (ret != 0)
- goto clean_vid;
+ if (!priv->ndev->vid_len) {
+ ret = cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
+ HOST_PORT_NUM, ALE_VLAN, vid);
+ if (ret != 0)
+ goto clean_vid;
+ }
ret = cpsw_ale_add_mcast(cpsw->ale, priv->ndev->broadcast,
mcast_mask, ALE_VLAN, vid, 0);
@@ -2381,8 +2428,9 @@ static inline int cpsw_add_vlan_ale_entry(struct cpsw_priv *priv,
return 0;
clean_vlan_ucast:
- cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
- HOST_PORT_NUM, ALE_VLAN, vid);
+ if (!priv->ndev->vid_len)
+ cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
+ HOST_PORT_NUM, ALE_VLAN, vid);
clean_vid:
cpsw_ale_del_vlan(cpsw->ale, vid, 0);
return ret;
@@ -3344,6 +3392,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
priv_sl2->emac_port = 1;
cpsw->slaves[1].ndev = ndev;
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->priv_flags |= IFF_UNICAST_FLT;
vlan_dev_ivdf_set(ndev, 1);
ndev->netdev_ops = &cpsw_netdev_ops;
@@ -3606,6 +3655,7 @@ static int cpsw_probe(struct platform_device *pdev)
}
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->priv_flags |= IFF_UNICAST_FLT;
vlan_dev_ivdf_set(ndev, 1);
ndev->netdev_ops = &cpsw_netdev_ops;
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 0/6] net: add individual virtual device filtering
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
One of the reasons of this proposition is safety and performance -
host should not receive traffic which is not designated for it.
Some network devices can hold separate address tables for vlans and
real device, but for some reason there is no possibility to apply it
with generic net addressing scheme easily. At this moment the fastest
solution is to add mcast/ucast entries for every created vlan
including real device. But it not only consumes forwarding table but
also adds holes in the filtering and thus wastes cpus cycles.
This patchseries tries to correct core to assign mcast and ucast
addresses only for vlans that really require it and as result an end
driver can exclusively and simply set its rx filters. As an example
it's implemented on cpsw TI driver, but generic changes provided by
this series can be reused by other ethernet drivers having similar
rx filter address possibilities.
An address+vid is considered as separate address. The reserved device
address length is 32 Bytes, for ethernet devices it's additional
opportunity to pass auxiliary address info, like virtual ID
identifying a device the address belongs to. This series makes it
possible at least for ETH_P_8021Q.
Thus end real device can setup separate tables for virtual devices
just retrieving VID from the address. A device address space can
maintain addresses and references on them separately for each virtual
device if it needs so, or only addresses for real device (and all its
vlans) it holds usually.
A vlan device can be in any place of device chain upper real device,
say smth like rdevice/bonding/vlan or even rdevice/macvlan/vlan.
This series is verified on TI am572x EVM that can hold separate tables
for vlans. Potentially it can be easily extended to netcp driver for
keystone 2 boards (including k2g) and also new am6 chipsets. As a
simple test case, different combinations of vlan+macvlan, macvlan+vlan
were used and tested as with unicast as multicast addresses.
Based on net-next/master
It's continuation of RFC:
[RFC PATCH net-next 0/5] net: allow hw addresses for virtual device
https://lkml.org/lkml/2018/12/3/817
Ivan Khoronzhuk (6):
net: core: dev_addr_lists: add VID to device address
net: 8021q: vlan_dev: add vid tag to addresses of uc and mc lists
net: 8021q: vlan_dev: add vid tag for vlan device own address
ethernet: eth: add default vid len for all ehternet kind devices
net: ethernet: ti: cpsw: update mc filtering to use IVDF
net: ethernet: ti: cpsw: add macvlan and ucast/vlan filtering support
drivers/net/ethernet/ti/Kconfig | 1 +
drivers/net/ethernet/ti/cpsw.c | 139 ++++++++++++--------------------
include/linux/if_vlan.h | 2 +
include/linux/netdevice.h | 4 +
net/8021q/Kconfig | 12 +++
net/8021q/vlan.c | 3 +
net/8021q/vlan.h | 2 +
net/8021q/vlan_core.c | 25 ++++++
net/8021q/vlan_dev.c | 103 ++++++++++++++++++-----
net/core/dev_addr_lists.c | 124 ++++++++++++++++++++++------
net/ethernet/eth.c | 10 ++-
11 files changed, 292 insertions(+), 133 deletions(-)
--
2.17.1
^ permalink raw reply
* [PATCH v2] iov_iter: optimize page_copy_sane()
From: Eric Dumazet @ 2019-02-26 18:42 UTC (permalink / raw)
To: Al Viro, David S . Miller
Cc: linux-kernel, netdev, Eric Dumazet, Eric Dumazet
Avoid cache line miss dereferencing struct page if we can.
page_copy_sane() mostly deals with order-0 pages.
Extra cache line miss is visible on TCP recvmsg() calls dealing
with GRO packets (typically 45 page frags are attached to one skb).
Bringing the 45 struct pages into cpu cache while copying the data
is not free, since the freeing of the skb (and associated
page frags put_page()) can happen after cache lines have been evicted.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
---
lib/iov_iter.c | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index be4bd627caf060cd89aa41ac88208946da568035..4d6b19c1b1294e1c30f6bbb7137e98cca5121f13 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -861,8 +861,21 @@ EXPORT_SYMBOL(_copy_from_iter_full_nocache);
static inline bool page_copy_sane(struct page *page, size_t offset, size_t n)
{
- struct page *head = compound_head(page);
- size_t v = n + offset + page_address(page) - page_address(head);
+ struct page *head;
+ size_t v = n + offset;
+
+ /*
+ * The general case needs to access the page order in order
+ * to compute the page size.
+ * However, we mostly deal with order-0 pages and thus can
+ * avoid a possible cache line miss for requests that fit all
+ * page orders.
+ */
+ if (n <= v && v <= PAGE_SIZE)
+ return true;
+
+ head = compound_head(page);
+ v += (page - head) << PAGE_SHIFT;
if (likely(n <= v && v <= (PAGE_SIZE << compound_order(head))))
return true;
--
2.21.0.rc2.261.ga7da99ff1b-goog
^ permalink raw reply related
* Re: [PATCH net] selftests: fixes for UDP GRO
From: Willem de Bruijn @ 2019-02-26 18:38 UTC (permalink / raw)
To: Paolo Abeni; +Cc: Network Development, David S. Miller, Willem de Bruijn
In-Reply-To: <2b1f4d9fe21346bc9f85c096e1b0922e4ff3c19d.1551173111.git.pabeni@redhat.com>
On Tue, Feb 26, 2019 at 9:28 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> The current implementation for UDP GRO tests is racy: the receiver
> may flush the RX queue while the sending is still transmitting and
> incorrectly report RX errors, with a wrong number of packet received.
>
> Add explicit timeouts to the receiver for both connection activation
> (first packet received for UDP) and reception completion, so that
> in the above critical scenario the receiver will wait for the
> transfer completion.
>
> Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO")
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
---
This is because of that "force termination after the second poll()"?
Could perhaps also just extend do_recv to wait while (!interrupted &&
tnow < tstart + 2000) and avoid the explicit arguments.
^ permalink raw reply
* [PATCH v3 net] net: phy: phylink: fix uninitialized variable in phylink_get_mac_state
From: Heiner Kallweit @ 2019-02-26 18:29 UTC (permalink / raw)
To: Russell King - ARM Linux, David Miller, Andrew Lunn,
Florian Fainelli
Cc: netdev@vger.kernel.org
When debugging an issue I found implausible values in state->pause.
Reason in that state->pause isn't initialized and later only single
bits are changed. Also the struct itself isn't initialized in
phylink_resolve(). So better initialize state->pause and other
not yet initialized fields.
v2:
- use right function name in subject
v3:
- initialize additional fields
Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
drivers/net/phy/phylink.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 59d175a5b..89750c7df 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -324,6 +324,10 @@ static int phylink_get_mac_state(struct phylink *pl, struct phylink_link_state *
linkmode_zero(state->lp_advertising);
state->interface = pl->link_config.interface;
state->an_enabled = pl->link_config.an_enabled;
+ state->speed = SPEED_UNKNOWN;
+ state->duplex = DUPLEX_UNKNOWN;
+ state->pause = MLO_PAUSE_NONE;
+ state->an_complete = 0;
state->link = 1;
return pl->ops->mac_link_state(ndev, state);
--
2.20.1
^ permalink raw reply related
* [PATCH net-next 2/8] devlink: add PF and VF port flavours
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Current port flavours cover simple switches and DSA. Add PF
and VF flavours to cover "switchdev" SR-IOV NICs.
Example devlink user space output:
$ devlink port
pci/0000:82:00.0/0: type eth netdev p4p1 flavour physical
pci/0000:82:00.0/10000: type eth netdev eth0 flavour pcie_pf pf 0
pci/0000:82:00.0/10001: type eth netdev eth1 flavour pcie_vf pf 0 vf 0
pci/0000:82:00.0/10002: type eth netdev eth2 flavour pcie_vf pf 0 vf 1
$ devlink -jp port
{
"port": {
"pci/0000:82:00.0/0": {
"type": "eth",
"netdev": "p4p1",
"flavour": "physical"
},
"pci/0000:82:00.0/10000": {
"type": "eth",
"netdev": "eth0",
"flavour": "pci_pf",
"pf": 0,
},
"pci/0000:82:00.0/10001": {
"type": "eth",
"netdev": "eth1",
"flavour": "pci_vf",
"pf": 0,
"vf": 0
},
"pci/0000:82:00.0/10002": {
"type": "eth",
"netdev": "eth2",
"flavour": "pci_vf",
"pf": 0,
"vf": 1
}
}
}
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
include/net/devlink.h | 25 ++++++++++--
include/uapi/linux/devlink.h | 5 +++
net/core/devlink.c | 73 +++++++++++++++++++++++++++++++-----
3 files changed, 91 insertions(+), 12 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 7f5a0bdca228..b5376ef492f1 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -42,9 +42,19 @@ struct devlink {
struct devlink_port_attrs {
bool set;
enum devlink_port_flavour flavour;
- u32 port_number; /* same value as "split group" */
- bool split;
- u32 split_subport_number;
+ union { /* port identifiers differ per-flavour */
+ /* PHYSICAL, CPU, DSA */
+ struct {
+ bool split;
+ u32 split_subport_number;
+ u32 port_number; /* same value as "split group" */
+ };
+ /* PCI_PF, PCI_VF */
+ struct {
+ u32 pf_number;
+ u32 vf_number;
+ } pci;
+ };
};
struct devlink_port {
@@ -568,6 +578,9 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
u32 port_number, bool split,
u32 split_subport_number);
+void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 pf_number, u32 vf_number);
int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
char *name, size_t len);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
@@ -782,6 +795,12 @@ static inline void devlink_port_attrs_set(struct devlink_port *devlink_port,
{
}
+static inline void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 pf_number, u32 vf_number)
+{
+}
+
static inline int
devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
char *name, size_t len)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 5bb4ea67d84f..9ce76d4f640d 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -167,6 +167,8 @@ enum devlink_port_flavour {
DEVLINK_PORT_FLAVOUR_DSA, /* Distributed switch architecture
* interconnect port.
*/
+ DEVLINK_PORT_FLAVOUR_PCI_PF, /* PCI Physical function port */
+ DEVLINK_PORT_FLAVOUR_PCI_VF, /* PCI Physical function port */
};
enum devlink_param_cmode {
@@ -332,6 +334,9 @@ enum devlink_attr {
DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, /* string */
DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, /* string */
+ DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u32 */
+ DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u32 */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index a49dee67e66f..af177284830b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -516,16 +516,35 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
return 0;
if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour))
return -EMSGSIZE;
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->port_number))
- return -EMSGSIZE;
- if (!attrs->split)
+
+ switch (attrs->flavour) {
+ case DEVLINK_PORT_FLAVOUR_PHYSICAL:
+ case DEVLINK_PORT_FLAVOUR_CPU:
+ case DEVLINK_PORT_FLAVOUR_DSA:
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER,
+ attrs->port_number))
+ return -EMSGSIZE;
+
+ if (attrs->split &&
+ (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,
+ attrs->port_number) ||
+ nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
+ attrs->split_subport_number)))
+ return -EMSGSIZE;
return 0;
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, attrs->port_number))
- return -EMSGSIZE;
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
- attrs->split_subport_number))
- return -EMSGSIZE;
- return 0;
+ case DEVLINK_PORT_FLAVOUR_PCI_VF:
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER,
+ attrs->pci.vf_number))
+ return -EMSGSIZE;
+ /* fall through */
+ case DEVLINK_PORT_FLAVOUR_PCI_PF:
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
+ attrs->pci.pf_number))
+ return -EMSGSIZE;
+ return 0;
+ default:
+ return -EINVAL;
+ }
}
static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
@@ -5410,6 +5429,9 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
+ WARN_ON(flavour == DEVLINK_PORT_FLAVOUR_PCI_PF ||
+ flavour == DEVLINK_PORT_FLAVOUR_PCI_VF);
+
attrs->set = true;
attrs->flavour = flavour;
attrs->port_number = port_number;
@@ -5419,6 +5441,32 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
}
EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
+/**
+ * devlink_port_attrs_pci_set - Set port attributes for a PCI port
+ *
+ * @devlink_port: devlink port
+ * @flavour: flavour of the port (PF or VF only)
+ * @pf_number: PCI PF number, in multi-host mapping to hosts depends
+ * on the platform
+ * @vf_number: PCI VF number within given PF (ignored for PF itself)
+ */
+void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 pf_number, u32 vf_number)
+{
+ struct devlink_port_attrs *attrs = &devlink_port->attrs;
+
+ WARN_ON(flavour != DEVLINK_PORT_FLAVOUR_PCI_PF &&
+ flavour != DEVLINK_PORT_FLAVOUR_PCI_VF);
+
+ attrs->set = true;
+ attrs->flavour = flavour;
+ attrs->pci.pf_number = pf_number;
+ attrs->pci.vf_number = vf_number;
+ devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+}
+EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_set);
+
int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
char *name, size_t len)
{
@@ -5443,6 +5491,13 @@ int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
*/
WARN_ON(1);
return -EINVAL;
+ case DEVLINK_PORT_FLAVOUR_PCI_PF:
+ n = snprintf(name, len, "pf%u", attrs->pci.pf_number);
+ break;
+ case DEVLINK_PORT_FLAVOUR_PCI_VF:
+ n = snprintf(name, len, "pf%uvf%u",
+ attrs->pf_number, attrs->pci.vf_number);
+ break;
}
if (n >= len)
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 5/8] nfp: switch to devlink_port_get_phys_port_name()
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Now that devlink understands all port flavours - switch
to the devlink_port_get_phys_port_name() helper.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
drivers/net/ethernet/netronome/nfp/nfp_port.c | 33 +------------------
1 file changed, 1 insertion(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.c b/drivers/net/ethernet/netronome/nfp/nfp_port.c
index 93c5bfc0510b..3e2ff8d35e8d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.c
@@ -117,44 +117,13 @@ struct nfp_eth_table_port *nfp_port_get_eth_port(struct nfp_port *port)
int
nfp_port_get_phys_port_name(struct net_device *netdev, char *name, size_t len)
{
- struct nfp_eth_table_port *eth_port;
struct nfp_port *port;
- int n;
port = nfp_port_from_netdev(netdev);
if (!port)
return -EOPNOTSUPP;
- switch (port->type) {
- case NFP_PORT_PHYS_PORT:
- eth_port = __nfp_port_get_eth_port(port);
- if (!eth_port)
- return -EOPNOTSUPP;
-
- if (!eth_port->is_split)
- n = snprintf(name, len, "p%d", eth_port->label_port);
- else
- n = snprintf(name, len, "p%ds%d", eth_port->label_port,
- eth_port->label_subport);
- break;
- case NFP_PORT_PF_PORT:
- if (!port->pf_split)
- n = snprintf(name, len, "pf%d", port->pf_id);
- else
- n = snprintf(name, len, "pf%ds%d", port->pf_id,
- port->pf_split_id);
- break;
- case NFP_PORT_VF_PORT:
- n = snprintf(name, len, "pf%dvf%d", port->pf_id, port->vf_id);
- break;
- default:
- return -EOPNOTSUPP;
- }
-
- if (n >= len)
- return -EINVAL;
-
- return 0;
+ return devlink_port_get_phys_port_name(&port->dl_port, name, len);
}
/**
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 8/8] devlink: fix kdoc
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
devlink suffers from a few kdoc warnings:
net/core/devlink.c:5292: warning: Function parameter or member 'dev' not described in 'devlink_register'
net/core/devlink.c:5351: warning: Function parameter or member 'port_index' not described in 'devlink_port_register'
net/core/devlink.c:5753: warning: Function parameter or member 'parent_resource_id' not described in 'devlink_resource_register'
net/core/devlink.c:5753: warning: Function parameter or member 'size_params' not described in 'devlink_resource_register'
net/core/devlink.c:5753: warning: Excess function parameter 'top_hierarchy' description in 'devlink_resource_register'
net/core/devlink.c:5753: warning: Excess function parameter 'reload_required' description in 'devlink_resource_register'
net/core/devlink.c:5753: warning: Excess function parameter 'parent_reosurce_id' description in 'devlink_resource_register'
net/core/devlink.c:6451: warning: Function parameter or member 'region' not described in 'devlink_region_snapshot_create'
net/core/devlink.c:6451: warning: Excess function parameter 'devlink_region' description in 'devlink_region_snapshot_create'
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
net/core/devlink.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index b514be300839..cd3f466496d3 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5287,6 +5287,7 @@ EXPORT_SYMBOL_GPL(devlink_alloc);
* devlink_register - Register devlink instance
*
* @devlink: devlink
+ * @dev: parent device
*/
int devlink_register(struct devlink *devlink, struct device *dev)
{
@@ -5337,7 +5338,7 @@ EXPORT_SYMBOL_GPL(devlink_free);
*
* @devlink: devlink
* @devlink_port: devlink port
- * @port_index
+ * @port_index: driver-specific numerical identifier of the port
*
* Register devlink port with provided port index. User can use
* any indexing, even hw-related one. devlink_port structure
@@ -5736,13 +5737,10 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister);
*
* @devlink: devlink
* @resource_name: resource's name
- * @top_hierarchy: top hierarchy
- * @reload_required: reload is required for new configuration to
- * apply
* @resource_size: resource's size
* @resource_id: resource's id
- * @parent_reosurce_id: resource's parent id
- * @size params: size parameters
+ * @parent_resource_id: resource's parent id
+ * @size_params: size parameters
*/
int devlink_resource_register(struct devlink *devlink,
const char *resource_name,
@@ -6439,7 +6437,7 @@ EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get);
* Multiple snapshots can be created on a region.
* The @snapshot_id should be obtained using the getter function.
*
- * @devlink_region: devlink region of the snapshot
+ * @region: devlink region of the snapshot
* @data_len: size of snapshot data
* @data: snapshot data
* @snapshot_id: snapshot id to be created
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 7/8] nfp: expose PF peer netdevs
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Expose PF netdevs as devlink port's peers.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
drivers/net/ethernet/netronome/nfp/abm/main.c | 1 +
drivers/net/ethernet/netronome/nfp/flower/main.c | 1 +
drivers/net/ethernet/netronome/nfp/nfp_devlink.c | 3 ++-
drivers/net/ethernet/netronome/nfp/nfp_port.h | 2 ++
4 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 4d4ff5844c47..8d7ff1200fd4 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -113,6 +113,7 @@ nfp_abm_spawn_repr(struct nfp_app *app, struct nfp_abm_link *alink,
port->pf_id = alink->abm->pf_id;
port->pf_split = app->pf->max_data_vnics > 1;
port->pf_split_id = alink->id;
+ port->peer = alink->vnic->dp.netdev;
port->vnic = alink->vnic->dp.ctrl_bar;
}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 408089133599..13aa21923bf7 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -300,6 +300,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
if (repr_type == NFP_REPR_TYPE_PF) {
port->pf_id = i;
port->vnic = priv->nn->dp.ctrl_bar;
+ port->peer = priv->nn->dp.netdev;
} else {
port->pf_id = 0;
port->vf_id = i;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index bb07be4117a3..3d59a57eda0c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -373,7 +373,8 @@ static int
nfp_devlink_port_init_pci(struct devlink *devlink, struct nfp_port *port,
u32 flavour)
{
- devlink_port_type_eth_set(&port->dl_port, port->netdev);
+ devlink_port_type_eth_set_peer(&port->dl_port, port->netdev,
+ port->peer);
devlink_port_attrs_pci_set(&port->dl_port, flavour,
port->pf_id, port->vf_id,
port->pf_split, port->pf_split_id);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h
index 09c55ca2371a..c75a25cc5cea 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h
@@ -51,6 +51,7 @@ enum nfp_port_flags {
* @eth_forced: for %NFP_PORT_PHYS_PORT port is forced UP or DOWN, don't change
* @eth_port: for %NFP_PORT_PHYS_PORT translated ETH Table port entry
* @eth_stats: for %NFP_PORT_PHYS_PORT MAC stats if available
+ * @peer: for %NFP_PORT_PF_PORT netdev of the actual vNIC, if reachable
* @pf_id: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT ID of the PCI PF (0-3)
* @vf_id: for %NFP_PORT_VF_PORT ID of the PCI VF within @pf_id
* @pf_split: for %NFP_PORT_PF_PORT %true if PCI PF has more than one vNIC
@@ -79,6 +80,7 @@ struct nfp_port {
};
/* NFP_PORT_PF_PORT, NFP_PORT_VF_PORT */
struct {
+ struct net_device *peer;
unsigned int pf_id;
unsigned int vf_id;
bool pf_split;
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 6/8] devlink: introduce port's peer netdevs
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Devlink ports represent ports of a switch device (or SR-IOV
NIC which has an embedded switch). In case of SR-IOV when
PCIe PFs are exposed the PFs which are directly connected
to the local machine may also spawn PF netdev (much like
VFs have a port/"repr" and an actual VF netdev).
Allow devlink to expose such linking. There is currently no
way to find out which netdev corresponds to which PF.
Example:
$ devlink port
pci/0000:82:00.0/0: type eth netdev p4p1 flavour physical
pci/0000:82:00.0/10000: type eth netdev eth1 flavour pci_pf pf 0 peer_netdev enp130s0
pci/0000:82:00.0/10001: type eth netdev eth0 flavour pci_vf pf 0 vf 0
pci/0000:82:00.0/10002: type eth netdev eth2 flavour pci_vf pf 0 vf 1
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
include/net/devlink.h | 11 ++++++++
include/uapi/linux/devlink.h | 3 +++
net/core/devlink.c | 51 +++++++++++++++++++++++++++++-------
3 files changed, 55 insertions(+), 10 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 13e0a479c546..15912cca5d16 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -68,6 +68,7 @@ struct devlink_port {
enum devlink_port_type type;
enum devlink_port_type desired_type;
void *type_dev;
+ void *type_peer;
struct devlink_port_attrs attrs;
};
@@ -573,6 +574,9 @@ int devlink_port_register(struct devlink *devlink,
void devlink_port_unregister(struct devlink_port *devlink_port);
void devlink_port_type_eth_set(struct devlink_port *devlink_port,
struct net_device *netdev);
+void devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer);
void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev);
void devlink_port_type_clear(struct devlink_port *devlink_port);
@@ -782,6 +786,13 @@ static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port,
{
}
+static inline void
+devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer)
+{
+}
+
static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev)
{
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 417ae8233cce..9ce4718f8b8b 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -338,6 +338,9 @@ enum devlink_attr {
DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u32 */
DEVLINK_ATTR_PORT_PCI_SUBPORT, /* u32 */
+ DEVLINK_ATTR_PORT_PEER_NETDEV_IFINDEX, /* u32 */
+ DEVLINK_ATTR_PORT_PEER_NETDEV_NAME, /* string */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6cdf7e87d7fc..b514be300839 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -552,6 +552,17 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
}
}
+static int devlink_nl_port_put_netdev(struct sk_buff *msg,
+ int attr_ifindex, int attr_name,
+ struct net_device *netdev)
+{
+ if (netdev &&
+ (nla_put_u32(msg, attr_ifindex, netdev->ifindex) ||
+ nla_put_string(msg, attr_name, netdev->name)))
+ return -EMSGSIZE;
+ return 0;
+}
+
static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
struct devlink_port *devlink_port,
enum devlink_command cmd, u32 portid,
@@ -574,13 +585,16 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
devlink_port->desired_type))
goto nla_put_failure;
if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
- struct net_device *netdev = devlink_port->type_dev;
+ if (devlink_nl_port_put_netdev(msg,
+ DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
+ DEVLINK_ATTR_PORT_NETDEV_NAME,
+ devlink_port->type_dev))
+ goto nla_put_failure;
- if (netdev &&
- (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
- netdev->ifindex) ||
- nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
- netdev->name)))
+ if (devlink_nl_port_put_netdev(msg,
+ DEVLINK_ATTR_PORT_PEER_NETDEV_IFINDEX,
+ DEVLINK_ATTR_PORT_PEER_NETDEV_NAME,
+ devlink_port->type_peer))
goto nla_put_failure;
}
if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
@@ -5369,10 +5383,11 @@ EXPORT_SYMBOL_GPL(devlink_port_unregister);
static void __devlink_port_type_set(struct devlink_port *devlink_port,
enum devlink_port_type type,
- void *type_dev)
+ void *type_dev, void *type_peer)
{
devlink_port->type = type;
devlink_port->type_dev = type_dev;
+ devlink_port->type_peer = type_peer;
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
}
@@ -5386,10 +5401,26 @@ void devlink_port_type_eth_set(struct devlink_port *devlink_port,
struct net_device *netdev)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_ETH, netdev);
+ DEVLINK_PORT_TYPE_ETH, netdev, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_eth_set);
+/**
+ * devlink_port_type_eth_set_peer - Set port type to Ethernet with peer
+ *
+ * @devlink_port: devlink port
+ * @netdev: related netdevice
+ * @peer: for PCIe ports the non-port netdev (actual VF or PF)
+ */
+void devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer)
+{
+ return __devlink_port_type_set(devlink_port,
+ DEVLINK_PORT_TYPE_ETH, netdev, peer);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_eth_set_peer);
+
/**
* devlink_port_type_ib_set - Set port type to InfiniBand
*
@@ -5400,7 +5431,7 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_IB, ibdev);
+ DEVLINK_PORT_TYPE_IB, ibdev, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
@@ -5412,7 +5443,7 @@ EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
void devlink_port_type_clear(struct devlink_port *devlink_port)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_NOTSET, NULL);
+ DEVLINK_PORT_TYPE_NOTSET, NULL, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_clear);
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 3/8] nfp: register devlink ports of all reprs
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Register all representors as devlink ports.
The port_index is slightly tricky to figure out, we use a bit of
arbitrary math to create unique IDs for PCI ports.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
.../net/ethernet/netronome/nfp/nfp_devlink.c | 47 ++++++++++++++++++-
.../net/ethernet/netronome/nfp/nfp_net_repr.c | 16 ++++++-
2 files changed, 60 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 9af3cb1f2f17..36976e37d162 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -350,7 +350,8 @@ const struct devlink_ops nfp_devlink_ops = {
.flash_update = nfp_devlink_flash_update,
};
-int nfp_devlink_port_init(struct nfp_app *app, struct nfp_port *port)
+static int
+nfp_devlink_port_init_phys(struct devlink *devlink, struct nfp_port *port)
{
struct nfp_eth_table_port eth_port;
int ret;
@@ -368,6 +369,34 @@ int nfp_devlink_port_init(struct nfp_app *app, struct nfp_port *port)
return 0;
}
+static int
+nfp_devlink_port_init_pci(struct devlink *devlink, struct nfp_port *port,
+ u32 flavour)
+{
+ devlink_port_type_eth_set(&port->dl_port, port->netdev);
+ devlink_port_attrs_pci_set(&port->dl_port, flavour,
+ port->pf_id, port->vf_id);
+ return 0;
+}
+
+int nfp_devlink_port_init(struct nfp_app *app, struct nfp_port *port)
+{
+ struct devlink *devlink = priv_to_devlink(app->pf);
+
+ switch (port->type) {
+ case NFP_PORT_PHYS_PORT:
+ return nfp_devlink_port_init_phys(devlink, port);
+ case NFP_PORT_PF_PORT:
+ return nfp_devlink_port_init_pci(devlink, port,
+ DEVLINK_PORT_FLAVOUR_PCI_PF);
+ case NFP_PORT_VF_PORT:
+ return nfp_devlink_port_init_pci(devlink, port,
+ DEVLINK_PORT_FLAVOUR_PCI_VF);
+ default:
+ return -EINVAL;
+ }
+}
+
void nfp_devlink_port_clean(struct nfp_port *port)
{
}
@@ -376,7 +405,21 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
{
struct devlink *devlink = priv_to_devlink(app->pf);
- return devlink_port_register(devlink, &port->dl_port, port->eth_id);
+ switch (port->type) {
+ case NFP_PORT_PHYS_PORT:
+ return devlink_port_register(devlink, &port->dl_port,
+ port->eth_id);
+ case NFP_PORT_PF_PORT:
+ return devlink_port_register(devlink, &port->dl_port,
+ (port->pf_id + 1) * 10000 +
+ port->pf_split_id * 1000);
+ case NFP_PORT_VF_PORT:
+ return devlink_port_register(devlink, &port->dl_port,
+ (port->pf_id + 1) * 10000 +
+ port->vf_id + 1);
+ default:
+ return -EINVAL;
+ }
}
void nfp_devlink_port_unregister(struct nfp_port *port)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index d2c803bb4e56..869d22760a6e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -292,7 +292,9 @@ nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower)
static void nfp_repr_clean(struct nfp_repr *repr)
{
+ nfp_devlink_port_unregister(repr->port);
unregister_netdev(repr->netdev);
+ nfp_devlink_port_clean(repr->port);
nfp_app_repr_clean(repr->app, repr->netdev);
dst_release((struct dst_entry *)repr->dst);
nfp_port_free(repr->port);
@@ -395,12 +397,24 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
if (err)
goto err_clean;
- err = register_netdev(netdev);
+ err = nfp_devlink_port_init(app, repr->port);
if (err)
goto err_repr_clean;
+ err = register_netdev(netdev);
+ if (err)
+ goto err_port_clean;
+
+ err = nfp_devlink_port_register(app, repr->port);
+ if (err)
+ goto err_unreg_netdev;
+
return 0;
+err_unreg_netdev:
+ unregister_netdev(repr->netdev);
+err_port_clean:
+ nfp_devlink_port_clean(repr->port);
err_repr_clean:
nfp_app_repr_clean(app, netdev);
err_clean:
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 4/8] devlink: allow subports on devlink PCI ports
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
PCI endpoint corresponds to a PCI device, but such device
can have one more more logical device ports associated with it.
We need a way to distinguish those. Add a PCI subport in the
dumps and print the info in phys_port_name appropriately.
This is not equivalent to port splitting, there is no split
group. It's just a way of representing multiple netdevs on
a single PCI function.
Note that the quality of being multiport pertains only to
the PCI function itself. A PF having multiple netdevs does
not mean that its VFs will also have multiple, or that VFs
are associated with any particular port of a multiport VF.
Example (bus 05 device has subports, bus 82 has only one port per
function):
$ devlink port
pci/0000:05:00.0/0: type eth netdev enp5s0np0 flavour physical
pci/0000:05:00.0/10000: type eth netdev enp5s0npf0s0 flavour pci_pf pf 0 subport 0
pci/0000:05:00.0/4: type eth netdev enp5s0np1 flavour physical
pci/0000:05:00.0/11000: type eth netdev enp5s0npf0s1 flavour pci_pf pf 0 subport 1
pci/0000:82:00.0/0: type eth netdev p4p1 flavour physical
pci/0000:82:00.0/10000: type eth netdev eth0 flavour pci_pf pf 0
$ devlink -jp port
{
"port": {
"pci/0000:05:00.0/0": {
"type": "eth",
"netdev": "enp5s0np0",
"flavour": "physical"
},
"pci/0000:05:00.0/10000": {
"type": "eth",
"netdev": "enp5s0npf0s0",
"flavour": "pci_pf",
"pf": 0,
"subport": 0
},
"pci/0000:05:00.0/4": {
"type": "eth",
"netdev": "enp5s0np1",
"flavour": "physical"
},
"pci/0000:05:00.0/11000": {
"type": "eth",
"netdev": "enp5s0npf0s1",
"flavour": "pci_pf",
"pf": 0,
"subport": 1
},
"pci/0000:82:00.0/0": {
"type": "eth",
"netdev": "p4p1",
"flavour": "physical"
},
"pci/0000:82:00.0/10000": {
"type": "eth",
"netdev": "eth0",
"flavour": "pci_pf",
"pf": 0
}
}
}
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
.../net/ethernet/netronome/nfp/nfp_devlink.c | 3 +-
include/net/devlink.h | 9 ++++--
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 29 ++++++++++++++++---
4 files changed, 35 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 36976e37d162..bb07be4117a3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -375,7 +375,8 @@ nfp_devlink_port_init_pci(struct devlink *devlink, struct nfp_port *port,
{
devlink_port_type_eth_set(&port->dl_port, port->netdev);
devlink_port_attrs_pci_set(&port->dl_port, flavour,
- port->pf_id, port->vf_id);
+ port->pf_id, port->vf_id,
+ port->pf_split, port->pf_split_id);
return 0;
}
diff --git a/include/net/devlink.h b/include/net/devlink.h
index b5376ef492f1..13e0a479c546 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -53,6 +53,8 @@ struct devlink_port_attrs {
struct {
u32 pf_number;
u32 vf_number;
+ bool multiport;
+ u32 subport_number;
} pci;
};
};
@@ -580,7 +582,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
u32 split_subport_number);
void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
- u32 pf_number, u32 vf_number);
+ u32 pf_number, u32 vf_number,
+ bool multiport, u32 subport_number);
int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
char *name, size_t len);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
@@ -797,7 +800,9 @@ static inline void devlink_port_attrs_set(struct devlink_port *devlink_port,
static inline void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
- u32 pf_number, u32 vf_number)
+ u32 pf_number, u32 vf_number,
+ bool multiport,
+ u32 subport_number)
{
}
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 9ce76d4f640d..417ae8233cce 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -336,6 +336,7 @@ enum devlink_attr {
DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u32 */
DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u32 */
+ DEVLINK_ATTR_PORT_PCI_SUBPORT, /* u32 */
/* add new attributes above here, update the policy in devlink.c */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index af177284830b..6cdf7e87d7fc 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -541,6 +541,11 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
if (nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
attrs->pci.pf_number))
return -EMSGSIZE;
+
+ if (attrs->pci.multiport &&
+ nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SUBPORT,
+ attrs->pci.subport_number))
+ return -EMSGSIZE;
return 0;
default:
return -EINVAL;
@@ -5449,10 +5454,13 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
* @pf_number: PCI PF number, in multi-host mapping to hosts depends
* on the platform
* @vf_number: PCI VF number within given PF (ignored for PF itself)
+ * @multiport: PCI function has more than one logical port
+ * @subport_number: PCI function has more than one logical port
*/
void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
- u32 pf_number, u32 vf_number)
+ u32 pf_number, u32 vf_number,
+ bool multiport, u32 subport_number)
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
@@ -5463,6 +5471,8 @@ void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
attrs->flavour = flavour;
attrs->pci.pf_number = pf_number;
attrs->pci.vf_number = vf_number;
+ attrs->pci.multiport = multiport;
+ attrs->pci.subport_number = subport_number;
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
}
EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_set);
@@ -5492,11 +5502,22 @@ int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
WARN_ON(1);
return -EINVAL;
case DEVLINK_PORT_FLAVOUR_PCI_PF:
- n = snprintf(name, len, "pf%u", attrs->pci.pf_number);
+ if (!attrs->pci.multiport)
+ n = snprintf(name, len, "pf%u", attrs->pci.pf_number);
+ else
+ n = snprintf(name, len, "pf%us%u", attrs->pci.pf_number,
+ attrs->pci.subport_number);
break;
case DEVLINK_PORT_FLAVOUR_PCI_VF:
- n = snprintf(name, len, "pf%uvf%u",
- attrs->pf_number, attrs->pci.vf_number);
+ if (!attrs->pci.multiport)
+ n = snprintf(name, len, "pf%uvf%u",
+ attrs->pci.pf_number,
+ attrs->pci.vf_number);
+ else
+ n = snprintf(name, len, "pf%uvf%us%u",
+ attrs->pci.pf_number,
+ attrs->pci.vf_number,
+ attrs->pci.subport_number);
break;
}
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 1/8] nfp: split devlink port init from registration
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
In the future we want to switch to using the
devlink_port_get_phys_port_name() helper for .ndo_phys_port_name.
This requires that we initialize the devlink ports before the
netdevs are registered. Split the registration from init.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
.../net/ethernet/netronome/nfp/nfp_devlink.c | 13 ++++++++++---
.../net/ethernet/netronome/nfp/nfp_net_main.c | 17 ++++++++++++++---
drivers/net/ethernet/netronome/nfp/nfp_port.h | 2 ++
3 files changed, 26 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index e9eca99cf493..9af3cb1f2f17 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -350,10 +350,9 @@ const struct devlink_ops nfp_devlink_ops = {
.flash_update = nfp_devlink_flash_update,
};
-int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
+int nfp_devlink_port_init(struct nfp_app *app, struct nfp_port *port)
{
struct nfp_eth_table_port eth_port;
- struct devlink *devlink;
int ret;
rtnl_lock();
@@ -366,8 +365,16 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
devlink_port_attrs_set(&port->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
eth_port.label_port, eth_port.is_split,
eth_port.label_subport);
+ return 0;
+}
+
+void nfp_devlink_port_clean(struct nfp_port *port)
+{
+}
- devlink = priv_to_devlink(app->pf);
+int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
+{
+ struct devlink *devlink = priv_to_devlink(app->pf);
return devlink_port_register(devlink, &port->dl_port, port->eth_id);
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 08f5fdbd8e41..39e87bb73ebf 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -150,9 +150,15 @@ nfp_net_pf_init_vnic(struct nfp_pf *pf, struct nfp_net *nn, unsigned int id)
nn->id = id;
+ if (nn->port) {
+ err = nfp_devlink_port_init(pf->app, nn->port);
+ if (err)
+ return err;
+ }
+
err = nfp_net_init(nn);
if (err)
- return err;
+ goto err_port_clean;
nfp_net_debugfs_vnic_add(nn, pf->ddir);
@@ -167,17 +173,20 @@ nfp_net_pf_init_vnic(struct nfp_pf *pf, struct nfp_net *nn, unsigned int id)
if (nfp_net_is_data_vnic(nn)) {
err = nfp_app_vnic_init(pf->app, nn);
if (err)
- goto err_devlink_port_clean;
+ goto err_port_unreg;
}
return 0;
-err_devlink_port_clean:
+err_port_unreg:
if (nn->port)
nfp_devlink_port_unregister(nn->port);
err_dfs_clean:
nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
nfp_net_clean(nn);
+err_port_clean:
+ if (nn->port)
+ nfp_devlink_port_clean(nn->port);
return err;
}
@@ -224,6 +233,8 @@ static void nfp_net_pf_clean_vnic(struct nfp_pf *pf, struct nfp_net *nn)
nfp_devlink_port_unregister(nn->port);
nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
nfp_net_clean(nn);
+ if (nn->port)
+ nfp_devlink_port_clean(nn->port);
}
static int nfp_net_pf_alloc_irqs(struct nfp_pf *pf)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h
index 90ae053f5c07..09c55ca2371a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h
@@ -129,6 +129,8 @@ int nfp_net_refresh_eth_port(struct nfp_port *port);
void nfp_net_refresh_port_table(struct nfp_port *port);
int nfp_net_refresh_port_table_sync(struct nfp_pf *pf);
+int nfp_devlink_port_init(struct nfp_app *app, struct nfp_port *port);
+void nfp_devlink_port_clean(struct nfp_port *port);
int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port);
void nfp_devlink_port_unregister(struct nfp_port *port);
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 0/8] devlink: add PF and VF port flavours
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
Hi!
This series brings port flavours for SR-IOV NICs.
First patch reshuffles nfp port registration to make the
port info available at netdev registration time. Next
the VF and PF port flavours are added to the core and
the nfp driver. The existing port information (split)
is now physical port-specific.
The currently deployed NFPs have a single PF per PCIe
link which means multiport cards have multiple logical
ports (netdevs) per function. This forces us to add
a notion of a PCIe subport (implemented in patches
4 and 5).
With that in place nfp driver can now switch to using
the devlink_port_get_phys_port_name() helper (patch 6).
Next two patches add a notion of a peer netdev, this
is the netdev "on the other side of the link". It can
be used to inform users which PF and VF corresponds
to which port/"representor" without the need for bus
info parsing.
Last but not least - I fix some kdoc warnings :)
Jakub Kicinski (8):
nfp: split devlink port init from registration
devlink: add PF and VF port flavours
nfp: register devlink ports of all reprs
devlink: allow subports on devlink PCI ports
nfp: switch to devlink_port_get_phys_port_name()
devlink: introduce port's peer netdevs
nfp: expose PF peer netdevs
devlink: fix kdoc
drivers/net/ethernet/netronome/nfp/abm/main.c | 1 +
.../net/ethernet/netronome/nfp/flower/main.c | 1 +
.../net/ethernet/netronome/nfp/nfp_devlink.c | 60 ++++++-
.../net/ethernet/netronome/nfp/nfp_net_main.c | 17 +-
.../net/ethernet/netronome/nfp/nfp_net_repr.c | 16 +-
drivers/net/ethernet/netronome/nfp/nfp_port.c | 33 +---
drivers/net/ethernet/netronome/nfp/nfp_port.h | 4 +
include/net/devlink.h | 41 ++++-
include/uapi/linux/devlink.h | 9 ++
net/core/devlink.c | 153 +++++++++++++++---
10 files changed, 268 insertions(+), 67 deletions(-)
--
2.19.2
^ permalink raw reply
* Re: [PATCH RFC] net: Validate size of non-TSO packets in validate_xmit_skb().
From: Michael Chan @ 2019-02-26 18:22 UTC (permalink / raw)
To: David Miller
Cc: Mahesh Bandewar (महेश बंडेवार),
Eric Dumazet, Netdev, Daniel Axtens
In-Reply-To: <20190226.091324.1656342529138987636.davem@davemloft.net>
On Tue, Feb 26, 2019 at 9:13 AM David Miller <davem@davemloft.net> wrote:
>
> From: Michael Chan <michael.chan@broadcom.com>
> Date: Tue, 26 Feb 2019 05:56:41 -0500
>
> > There have been reports of oversize UDP packets being sent to the
> > driver to be transmitted, causing error conditions. The issue is
> > likely caused by the dst of the SKB switching between 'lo' with
> > 64K MTU and the hardware device with a smaller MTU. Patches are
> > being proposed by Mahesh Bandewar <maheshb@google.com> to fix the
> > issue.
> >
> > Separately, we should add a length check in validate_xmit_skb()
> > to drop these oversize packets before they reach the driver.
> > This patch only validates non-TSO packets. Complete validation
> > of segmented TSO packet size will probably be too slow.
> >
> > Signed-off-by: Michael Chan <michael.chan@broadcom.com>
>
> Anything which changes the dst of an SKB really is responsible for
> fixing up whatever became "incompatible" in the new path.
>
> So like Eric I want to see this out of the fast path.
Ok. In the meantime, will you take a 2-line bnxt_en patch that will
prevent this issue in kernel 5.0?
^ permalink raw reply
* Re: [PATCH] x86, retpolines: raise limit for generating indirect calls from switch-case
From: Björn Töpel @ 2019-02-26 18:20 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: Daniel Borkmann, tglx, LKML, Netdev, David S . Miller,
Björn Töpel, Magnus Karlsson, Alexei Starovoitov,
Peter Zijlstra, David Woodhouse, Andy Lutomirski, Borislav Petkov,
Linus Torvalds
In-Reply-To: <20190222083131.5a141e23@carbon>
On Fri, 22 Feb 2019 at 08:32, Jesper Dangaard Brouer <brouer@redhat.com> wrote:
>
> On Thu, 21 Feb 2019 23:19:41 +0100
> Daniel Borkmann <daniel@iogearbox.net> wrote:
>
> > Recent work on XDP from Björn and Magnus additionally found that
> > manually transforming the XDP return code switch statement with
> > more than 5 cases into if-else combination would result in a
> > considerable speedup in XDP layer due to avoidance of indirect
> > calls in CONFIG_RETPOLINE enabled builds. On i40e driver with
> > XDP prog attached, a 20-26% speedup has been observed [0]. Aside
> > from XDP, there are many other places later in the networking
> > stack's critical path with similar switch-case processing. Rather
> > than fixing every XDP-enabled driver and locations in stack by
> > hand, it would be good to instead raise the limit where gcc would
> > emit expensive indirect calls from the switch under retpolines
>
> I'm very happy to see this. Thanks to Björn for finding, analyzing and
> providing hand-coded-if-else code that demonstrated the performance
> issue for XDP. But I do think this GCC case-values-threshold param is
> a better and more generic solution to the issue we observed and
> measured in XDP land. And hopefully other parts of the network stack
> and kernel will also benefit.
>
> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
>
> Thanks for following up on this Daniel,
I definitely prefer a switch-statement over the if-else-messiness in
this context. Thanks for doing the deep-dive, Daniel!
FWIW,
Acked-by: Björn Töpel <bjorn.topel@intel.com>
> --
> Best regards,
> Jesper Dangaard Brouer
> MSc.CS, Principal Kernel Engineer at Red Hat
> LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Re: [PATCH] bpf: decrease usercnt if bpf_map_new_fd() fails in bpf_map_get_fd_by_id()
From: Daniel Borkmann @ 2019-02-26 18:12 UTC (permalink / raw)
To: Martin Lau, zerons
Cc: ast@kernel.org, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
In-Reply-To: <20190226173355.chm6gwvwyer57yco@kafai-mbp.dhcp.thefacebook.com>
On 02/26/2019 06:33 PM, Martin Lau wrote:
> On Tue, Feb 26, 2019 at 10:15:37PM +0800, zerons wrote:
>> [ Upstream commit c91951f15978f1a0c6b65f063d30f7ea7bc6fb42 ]
>>
>> In bpf/syscall.c, bpf_map_get_fd_by_id() use bpf_map_inc_not_zero() to increase
>> the refcount, both map->refcnt and map->usercnt. Then, if bpf_map_new_fd() fails,
>> should handle map->usercnt too.
> Good catch! Thanks for the fix.
+1
> Fixes: bd5f5f4ecb78 ("bpf: Add BPF_MAP_GET_FD_BY_ID")
> Acked-by: Martin KaFai Lau <kafai@fb.com>
Applied, thanks!
^ permalink raw reply
* Re: [PATCH v2 net] net: phy: phylink: fix uninitialized variable in phylink_get_mac_state
From: Heiner Kallweit @ 2019-02-26 18:08 UTC (permalink / raw)
To: Russell King - ARM Linux admin
Cc: David Miller, Andrew Lunn, Florian Fainelli,
netdev@vger.kernel.org
In-Reply-To: <20190226084313.v3uhd6yjmovzz24j@shell.armlinux.org.uk>
On 26.02.2019 09:43, Russell King - ARM Linux admin wrote:
> On Tue, Feb 26, 2019 at 08:25:41AM +0100, Heiner Kallweit wrote:
>> When debugging an issue I found implausible values in state->pause.
>> Reason in that state->pause isn't initialized and later only single
>> bits are changed. Also the struct itself isn't initialized in
>> phylink_resolve(). So better initialize state->pause.
>
> mac_link_state() is expected to always set this, but this is safer.
>
I've seen cases where mac_link_state() just initializes the relevant
bits. Therefore there's no functional problem, but it's not nice
(and disturbs in debug output) if all other bits have a random value.
> Maybe also set state->speed to SPEED_UNKNOWN, state->duplex to
> DUPLEX_UNKNOWN and state->an_complete to zero?
>
OK. Will include this in a v3.
>>
>> v2:
>> - use right function name in subject
>>
>> Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
>> Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
>> ---
>> drivers/net/phy/phylink.c | 1 +
>> 1 file changed, 1 insertion(+)
>>
>> diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
>> index 59d175a5b..a9954c205 100644
>> --- a/drivers/net/phy/phylink.c
>> +++ b/drivers/net/phy/phylink.c
>> @@ -324,6 +324,7 @@ static int phylink_get_mac_state(struct phylink *pl, struct phylink_link_state *
>> linkmode_zero(state->lp_advertising);
>> state->interface = pl->link_config.interface;
>> state->an_enabled = pl->link_config.an_enabled;
>> + state->pause = MLO_PAUSE_NONE;
>> state->link = 1;
>>
>> return pl->ops->mac_link_state(ndev, state);
>> --
>> 2.20.1
>>
>>
>
^ permalink raw reply
* [PATCH net-next 5/5] tcp: remove tcp_queue argument from tso_fragment()
From: Eric Dumazet @ 2019-02-26 17:49 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, Eric Dumazet, Eric Dumazet
In-Reply-To: <20190226174913.18824-1-edumazet@google.com>
tso_fragment() is only called for packets still in write queue.
Remove the tcp_queue parameter to make this more obvious,
even if the comment clearly states this.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/tcp_output.c | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 91f5cc5a3f88953da1043d051af9c5971c6006de..4522579aaca2d24b7be61abac658a3c8cbd2b960 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1846,17 +1846,17 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp,
* know that all the data is in scatter-gather pages, and that the
* packet has never been sent out before (and thus is not cloned).
*/
-static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
- struct sk_buff *skb, unsigned int len,
+static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
unsigned int mss_now, gfp_t gfp)
{
- struct sk_buff *buff;
int nlen = skb->len - len;
+ struct sk_buff *buff;
u8 flags;
/* All of a TSO frame must be composed of paged data. */
if (skb->len != skb->data_len)
- return tcp_fragment(sk, tcp_queue, skb, len, mss_now, gfp);
+ return tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
+ skb, len, mss_now, gfp);
buff = sk_stream_alloc_skb(sk, 0, gfp, true);
if (unlikely(!buff))
@@ -1892,7 +1892,7 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue,
/* Link BUFF into the send queue. */
__skb_header_release(buff);
- tcp_insert_write_queue_after(skb, buff, sk, tcp_queue);
+ tcp_insert_write_queue_after(skb, buff, sk, TCP_FRAG_IN_WRITE_QUEUE);
return 0;
}
@@ -2391,8 +2391,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
nonagle);
if (skb->len > limit &&
- unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE,
- skb, limit, mss_now, gfp)))
+ unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
break;
if (tcp_small_queue_check(sk, skb, 0))
--
2.21.0.rc2.261.ga7da99ff1b-goog
^ permalink raw reply related
* [PATCH net-next 4/5] tcp: use tcp_md5_needed for timewait sockets
From: Eric Dumazet @ 2019-02-26 17:49 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, Eric Dumazet, Eric Dumazet
In-Reply-To: <20190226174913.18824-1-edumazet@google.com>
This might speedup tcp_twsk_destructor() a bit,
avoiding a cache line miss.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/tcp_minisocks.c | 21 +++++++++++++--------
1 file changed, 13 insertions(+), 8 deletions(-)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 182595e2d40ff5b48cd6d095d4bd97b4cb26d3c0..79900f783e0d8a713712b0bf47700f16eebab4db 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -294,12 +294,15 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
* so the timewait ack generating code has the key.
*/
do {
- struct tcp_md5sig_key *key;
tcptw->tw_md5_key = NULL;
- key = tp->af_specific->md5_lookup(sk, sk);
- if (key) {
- tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
- BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool());
+ if (static_branch_unlikely(&tcp_md5_needed)) {
+ struct tcp_md5sig_key *key;
+
+ key = tp->af_specific->md5_lookup(sk, sk);
+ if (key) {
+ tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
+ BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool());
+ }
}
} while (0);
#endif
@@ -338,10 +341,12 @@ EXPORT_SYMBOL(tcp_time_wait);
void tcp_twsk_destructor(struct sock *sk)
{
#ifdef CONFIG_TCP_MD5SIG
- struct tcp_timewait_sock *twsk = tcp_twsk(sk);
+ if (static_branch_unlikely(&tcp_md5_needed)) {
+ struct tcp_timewait_sock *twsk = tcp_twsk(sk);
- if (twsk->tw_md5_key)
- kfree_rcu(twsk->tw_md5_key, rcu);
+ if (twsk->tw_md5_key)
+ kfree_rcu(twsk->tw_md5_key, rcu);
+ }
#endif
}
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
--
2.21.0.rc2.261.ga7da99ff1b-goog
^ permalink raw reply related
* [PATCH net-next 3/5] tcp: convert tcp_md5_needed to static_branch API
From: Eric Dumazet @ 2019-02-26 17:49 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, Eric Dumazet, Eric Dumazet
In-Reply-To: <20190226174913.18824-1-edumazet@google.com>
We prefer static_branch_unlikely() over static_key_false() these days.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/tcp.h | 4 ++--
net/ipv4/tcp.c | 2 +-
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv4/tcp_output.c | 4 ++--
4 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d66ac76a33d1298e48bb9dcef217beaedc8a7968..68ee02523b873db037aa9d6707edb14592e763fd 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1558,7 +1558,7 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
#ifdef CONFIG_TCP_MD5SIG
#include <linux/jump_label.h>
-extern struct static_key tcp_md5_needed;
+extern struct static_key_false tcp_md5_needed;
struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk,
const union tcp_md5_addr *addr,
int family);
@@ -1567,7 +1567,7 @@ tcp_md5_do_lookup(const struct sock *sk,
const union tcp_md5_addr *addr,
int family)
{
- if (!static_key_false(&tcp_md5_needed))
+ if (!static_branch_unlikely(&tcp_md5_needed))
return NULL;
return __tcp_md5_do_lookup(sk, addr, family);
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e2fa6eb9f81aa0244ea05d99e2870a3d9294673b..ad07dd71063da09843ccfbd3e00d3f41567e1205 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3699,7 +3699,7 @@ bool tcp_alloc_md5sig_pool(void)
if (!tcp_md5sig_pool_populated) {
__tcp_alloc_md5sig_pool();
if (tcp_md5sig_pool_populated)
- static_key_slow_inc(&tcp_md5_needed);
+ static_branch_inc(&tcp_md5_needed);
}
mutex_unlock(&tcp_md5sig_mutex);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4010ae3644f3101d01ee984c21256ca381588a3e..831d844a27ca20b52d590e17cb3eb2b2f8a697ce 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -973,7 +973,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
* We need to maintain these in the sk structure.
*/
-struct static_key tcp_md5_needed __read_mostly;
+DEFINE_STATIC_KEY_FALSE(tcp_md5_needed);
EXPORT_SYMBOL(tcp_md5_needed);
/* Find the Key structure for an address. */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e72aa0ff5785f177eb28ba8a3e4714997e58f35b..91f5cc5a3f88953da1043d051af9c5971c6006de 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -597,7 +597,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
*md5 = NULL;
#ifdef CONFIG_TCP_MD5SIG
- if (static_key_false(&tcp_md5_needed) &&
+ if (static_branch_unlikely(&tcp_md5_needed) &&
rcu_access_pointer(tp->md5sig_info)) {
*md5 = tp->af_specific->md5_lookup(sk, sk);
if (*md5) {
@@ -734,7 +734,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
*md5 = NULL;
#ifdef CONFIG_TCP_MD5SIG
- if (static_key_false(&tcp_md5_needed) &&
+ if (static_branch_unlikely(&tcp_md5_needed) &&
rcu_access_pointer(tp->md5sig_info)) {
*md5 = tp->af_specific->md5_lookup(sk, sk);
if (*md5) {
--
2.21.0.rc2.261.ga7da99ff1b-goog
^ permalink raw reply related
* [PATCH net-next 2/5] tcp: get rid of __tcp_add_write_queue_tail()
From: Eric Dumazet @ 2019-02-26 17:49 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, Eric Dumazet, Eric Dumazet
In-Reply-To: <20190226174913.18824-1-edumazet@google.com>
This helper is only used from tcp_add_write_queue_tail(), and does
not make the code more readable.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/tcp.h | 7 +------
1 file changed, 1 insertion(+), 6 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 813042c08dc5a7438279821890439b02490391d1..d66ac76a33d1298e48bb9dcef217beaedc8a7968 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1716,14 +1716,9 @@ static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk)
return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk);
}
-static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
-{
- __skb_queue_tail(&sk->sk_write_queue, skb);
-}
-
static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
{
- __tcp_add_write_queue_tail(sk, skb);
+ __skb_queue_tail(&sk->sk_write_queue, skb);
/* Queue it, remembering where we must start sending. */
if (sk->sk_write_queue.next == skb)
--
2.21.0.rc2.261.ga7da99ff1b-goog
^ permalink raw reply related
* [PATCH net-next 1/5] tcp: get rid of tcp_check_send_head()
From: Eric Dumazet @ 2019-02-26 17:49 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, Eric Dumazet, Eric Dumazet
In-Reply-To: <20190226174913.18824-1-edumazet@google.com>
This helper is used only once, and its name is no longer relevant.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/tcp.h | 6 ------
net/ipv4/tcp.c | 3 ++-
2 files changed, 2 insertions(+), 7 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index a6e0355921e1d0cf6df3bb20fba8b3d4e9d9ef08..813042c08dc5a7438279821890439b02490391d1 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1716,12 +1716,6 @@ static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk)
return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk);
}
-static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
-{
- if (tcp_write_queue_empty(sk))
- tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
-}
-
static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
{
__skb_queue_tail(&sk->sk_write_queue, skb);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 769508c75dce5a39bd78766d801ca01abb77f4bb..e2fa6eb9f81aa0244ea05d99e2870a3d9294673b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1412,7 +1412,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
/* It is the one place in all of TCP, except connection
* reset, where we can be unlinking the send_head.
*/
- tcp_check_send_head(sk, skb);
+ if (tcp_write_queue_empty(sk))
+ tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
sk_wmem_free_skb(sk, skb);
}
--
2.21.0.rc2.261.ga7da99ff1b-goog
^ permalink raw reply related
* [PATCH net-next 0/5] tcp: cleanups for linux-5.1
From: Eric Dumazet @ 2019-02-26 17:49 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, Eric Dumazet, Eric Dumazet
This small patch series cleanups few things, and add a small
timewait optimization for hosts not using md5.
Eric Dumazet (5):
tcp: get rid of tcp_check_send_head()
tcp: get rid of __tcp_add_write_queue_tail()
tcp: convert tcp_md5_needed to static_branch API
tcp: use tcp_md5_needed for timewait sockets
tcp: remove tcp_queue argument from tso_fragment()
include/net/tcp.h | 17 +++--------------
net/ipv4/tcp.c | 5 +++--
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv4/tcp_minisocks.c | 21 +++++++++++++--------
net/ipv4/tcp_output.c | 17 ++++++++---------
5 files changed, 28 insertions(+), 34 deletions(-)
--
2.21.0.rc2.261.ga7da99ff1b-goog
^ permalink raw reply
* Re: [PATCH net-next 1/2] vxlan: add extack support for create and changelink
From: Petr Machata @ 2019-02-26 17:45 UTC (permalink / raw)
To: Roopa Prabhu
Cc: davem@davemloft.net, netdev@vger.kernel.org,
dsa@cumulusnetworks.com, sd@queasysnail.net,
johannes@sipsolutions.net
In-Reply-To: <CAJieiUhKFrhoMcy-Bz1JmWEQ=8OooeZpb_sbD6zcKwotfJooBQ@mail.gmail.com>
Roopa Prabhu <roopa@cumulusnetworks.com> writes:
> On Tue, Feb 26, 2019 at 5:51 AM Petr Machata <petrm@mellanox.com> wrote:
>>
>> Many of the flags for which you call this don't actually have the else
>> branch. However I suspect there are no good reasons not to allow
>> resetting a flag.
>>
>> Reviewed-by: Petr Machata <petrm@mellanox.com>
>
> yes, correct, that was intentional.
> also, I am not sure what is the best way to support reseting of a NLA_FLAG.
> Absence of the flag attribute in the request cannot be the reason for
> resetting or clearing the flag.
Yeah, I was thinking about that. It looks like this would need a new set
of u8 attributes :-(
> None of the NLA_FLAG attributes support changing the flag today. This
> patch does not change that.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox