* [PATCH v2 4/6] ARM: dts: rockchip: add gmac info for rk3288
From: Roger Chen @ 2014-11-27 2:53 UTC (permalink / raw)
To: heiko
Cc: peppe.cavallaro, netdev, linux-kernel, linux-rockchip, kever.yang,
eddie.cai, roger.chen
In-Reply-To: <1417056591-3570-1-git-send-email-roger.chen@rock-chips.com>
add gmac info in rk3288.dtsi for GMAC driver
Signed-off-by: Roger Chen <roger.chen@rock-chips.com>
---
arch/arm/boot/dts/rk3288.dtsi | 49 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 49 insertions(+)
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 0f50d5d..22f7019 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -358,6 +358,22 @@
status = "disabled";
};
+ gmac: ethernet@ff290000 {
+ compatible = "rockchip,rk3288-gmac";
+ reg = <0xff290000 0x10000>;
+ interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq";
+ rockchip,grf = <&grf>;
+ clocks = <&cru SCLK_MAC>, <&cru SCLK_MAC_PLL>,
+ <&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
+ <&cru SCLK_MACREF>, <&cru SCLK_MACREF_OUT>,
+ <&cru ACLK_GMAC>, <&cru PCLK_GMAC>;
+ clock-names = "stmmaceth", "clk_mac_pll",
+ "mac_clk_rx", "mac_clk_tx",
+ "clk_mac_ref", "clk_mac_refout",
+ "aclk_mac", "pclk_mac";
+ };
+
usb_host0_ehci: usb@ff500000 {
compatible = "generic-ehci";
reg = <0xff500000 0x100>;
@@ -1040,5 +1056,38 @@
rockchip,pins = <7 23 3 &pcfg_pull_none>;
};
};
+
+ gmac {
+ rgmii_pins: rgmii-pins {
+ rockchip,pins = <3 30 3 &pcfg_pull_none>,
+ <3 31 3 &pcfg_pull_none>,
+ <3 26 3 &pcfg_pull_none>,
+ <3 27 3 &pcfg_pull_none>,
+ <3 28 3 &pcfg_pull_none>,
+ <3 29 3 &pcfg_pull_none>,
+ <3 24 3 &pcfg_pull_none>,
+ <3 25 3 &pcfg_pull_none>,
+ <4 0 3 &pcfg_pull_none>,
+ <4 5 3 &pcfg_pull_none>,
+ <4 6 3 &pcfg_pull_none>,
+ <4 9 3 &pcfg_pull_none>,
+ <4 4 3 &pcfg_pull_none>,
+ <4 1 3 &pcfg_pull_none>,
+ <4 3 3 &pcfg_pull_none>;
+ };
+
+ rmii_pins: rmii-pins {
+ rockchip,pins = <3 30 3 &pcfg_pull_none>,
+ <3 31 3 &pcfg_pull_none>,
+ <3 28 3 &pcfg_pull_none>,
+ <3 29 3 &pcfg_pull_none>,
+ <4 0 3 &pcfg_pull_none>,
+ <4 5 3 &pcfg_pull_none>,
+ <4 4 3 &pcfg_pull_none>,
+ <4 1 3 &pcfg_pull_none>,
+ <4 2 3 &pcfg_pull_none>,
+ <4 3 3 &pcfg_pull_none>;
+ };
+ };
};
};
--
1.7.9.5
^ permalink raw reply related
* [PATCH v2 5/6] ARM: dts: rockchip: enable gmac on RK3288 evb board
From: Roger Chen @ 2014-11-27 2:53 UTC (permalink / raw)
To: heiko
Cc: peppe.cavallaro, netdev, linux-kernel, linux-rockchip, kever.yang,
eddie.cai, roger.chen
In-Reply-To: <1417056591-3570-1-git-send-email-roger.chen@rock-chips.com>
enable gmac in rk3288-evb-rk808.dts
Signed-off-by: Roger Chen <roger.chen@rock-chips.com>
---
arch/arm/boot/dts/rk3288-evb-rk808.dts | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/arch/arm/boot/dts/rk3288-evb-rk808.dts b/arch/arm/boot/dts/rk3288-evb-rk808.dts
index d8c775e6..13ad2d2 100644
--- a/arch/arm/boot/dts/rk3288-evb-rk808.dts
+++ b/arch/arm/boot/dts/rk3288-evb-rk808.dts
@@ -15,6 +15,13 @@
/ {
compatible = "rockchip,rk3288-evb-rk808", "rockchip,rk3288";
+
+ ext_gmac: external-gmac-clock {
+ compatible = "fixed-clock";
+ clock-frequency = <125000000>;
+ clock-output-names = "ext_gmac";
+ #clock-cells = <0>;
+ };
};
&cpu0 {
@@ -152,3 +159,20 @@
};
};
};
+
+&gmac {
+ //pmu_regulator = "act_ldo5";
+ //pmu_enable_level = <1>; //1->HIGH, 0->LOW
+ power-gpio = <&gpio0 6 GPIO_ACTIVE_HIGH>;
+ reset-gpio = <&gpio4 7 GPIO_ACTIVE_LOW>;
+ //phyirq-gpio = <&gpio4 2 GPIO_ACTIVE_LOW>;
+ phy-mode = "rgmii";
+ clock_in_out = "input";
+ assigned-clocks = <&cru SCLK_MAC>;
+ assigned-clock-parents = <&ext_gmac>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&rgmii_pins>;
+ tx_delay = <0x30>;
+ rx_delay = <0x10>;
+ status = "ok";
+};
--
1.7.9.5
^ permalink raw reply related
* [PATCH v2 6/6] GMAC: add document for Rockchip RK3288 GMAC
From: Roger Chen @ 2014-11-27 2:53 UTC (permalink / raw)
To: heiko
Cc: peppe.cavallaro, netdev, linux-kernel, linux-rockchip, kever.yang,
eddie.cai, roger.chen
In-Reply-To: <1417056591-3570-1-git-send-email-roger.chen@rock-chips.com>
The document descripts how to add properties for GMAC in device tree.
Signed-off-by: Roger Chen <roger.chen@rock-chips.com>
---
.../devicetree/bindings/net/rockchip-dwmac.txt | 71 ++++++++++++++++++++
1 file changed, 71 insertions(+)
create mode 100644 Documentation/devicetree/bindings/net/rockchip-dwmac.txt
diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
new file mode 100644
index 0000000..237442b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
@@ -0,0 +1,71 @@
+Rockchip SoC RK3288 10/100/1000 Ethernet driver(GMAC)
+
+The device node has following properties.
+
+Required properties:
+ - compatible: Can be "rockchip,rk3288-gmac".
+ - reg: addresses and length of the register sets for the device.
+ - interrupts: Should contain the GMAC interrupts.
+ - interrupt-names: Should contain the interrupt names "macirq".
+ - rockchip,grf: phandle to the syscon grf used to control speed and mode.
+ - clocks: <&cru SCLK_MAC>: clock selector for main clock, from PLL or PHY.
+ <&cru SCLK_MAC_PLL>: PLL clock for SCLK_MAC
+ <&cru SCLK_MAC_RX>: clock gate for RX
+ <&cru SCLK_MAC_TX>: clock gate for TX
+ <&cru SCLK_MACREF>: clock gate for RMII referce clock
+ <&cru SCLK_MACREF_OUT> clock gate for RMII reference clock output
+ <&cru ACLK_GMAC>: AXI clock gate for GMAC
+ <&cru PCLK_GMAC>: APB clock gate for GMAC
+ - clock-names: One name for each entry in the clocks property.
+ - phy-mode: See ethernet.txt file in the same directory.
+ - pinctrl-names: Names corresponding to the numbered pinctrl states.
+ - pinctrl-0: pin-control mode. can be <&rgmii_pins> or <&rmii_pins>.
+ - clock_in_out: For RGMII, it must be "input", means main clock(125MHz)
+ is not sourced from SoC's PLL, but input from PHY; For RMII, "input" means
+ PHY provides the reference clock(50MHz), "output" means GMAC provides the
+ reference clock.
+ - assigned-clocks: main clock, should be <&cru SCLK_MAC>;
+ - assigned-clock-parents = parent of main clock.
+ can be <&ext_gmac> or <&cru SCLK_MAC_PLL>.
+ - reset-gpio: GPIO for reset
+
+Optional properties:
+ - tx_delay: Delay value for TXD timing. Range value is 0~0x7F, 0x30 as default.
+ - rx_delay: Delay value for RXD timing. Range value is 0~0x7F, 0x10 as default.
+ - pmu_regulator: PMIC's integrated LDO power for PHY. Can be "act_ldo5".
+ - pmu_enable_level: Enable level of LDO. Can be <1> or <0>. 1->HIGH, 0->LOW.
+ - power-gpio: GPIO used to control PHY power. Normally,
+ power-gpio and pmu_regulator can not be used at the same time.
+ - phyirq-gpio: GPIO used as PHY irq.
+
+Example:
+
+gmac: ethernet@ff290000 {
+ compatible = "rockchip,rk3288-gmac";
+ reg = <0xff290000 0x10000>;
+ interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq";
+ rockchip,grf = <&grf>;
+ clocks = <&cru SCLK_MAC>, <&cru SCLK_MAC_PLL>,
+ <&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
+ <&cru SCLK_MACREF>, <&cru SCLK_MACREF_OUT>,
+ <&cru ACLK_GMAC>, <&cru PCLK_GMAC>;
+ clock-names = "stmmaceth", "clk_mac_pll",
+ "mac_clk_rx", "mac_clk_tx",
+ "clk_mac_ref", "clk_mac_refout",
+ "aclk_mac", "pclk_mac";
+ phy-mode = "rgmii";
+ pinctrl-names = "default";
+ pinctrl-0 = <&rgmii_pins /*&rmii_pins*/>;
+
+ clock_in_out = "input";
+ assigned-clocks = <&cru SCLK_MAC>;
+ assigned-clock-parents = <&ext_gmac>;
+ tx_delay = <0x30>;
+ rx_delay = <0x10>;
+
+ power-gpio = <&gpio0 6 GPIO_ACTIVE_HIGH>;
+ reset-gpio = <&gpio4 7 GPIO_ACTIVE_LOW>;
+
+ status = "ok";
+};
--
1.7.9.5
^ permalink raw reply related
* Re: [patch net-next v3 04/17] net: introduce generic switch devices support
From: Simon Horman @ 2014-11-27 3:13 UTC (permalink / raw)
To: Jamal Hadi Salim
Cc: Thomas Graf, Jiri Pirko, netdev, davem, nhorman, andy, dborkman,
ogerlitz, jesse, pshelar, azhou, ben, stephen, jeffrey.t.kirsher,
vyasevic, xiyou.wangcong, john.r.fastabend, edumazet, sfeldma,
f.fainelli, roopa, linville, jasowang, ebiederm, nicolas.dichtel,
ryazanov.s.a, buytenh, aviadr, nbd, alexei.starovoitov,
Neil.Jerram, ronye, alexander.h.duyck, john.ronciak, mleitner,
shrijeet, gospo, bcrl
In-Reply-To: <54754A10.6020601@mojatatu.com>
On Tue, Nov 25, 2014 at 10:33:36PM -0500, Jamal Hadi Salim wrote:
> On 11/25/14 16:54, Thomas Graf wrote:
> >On 11/25/14 at 12:08pm, Jamal Hadi Salim wrote:
>
> >It would definitely help if you could expose some more details on the
> >"some network processor" you have. We're all very eager ;-)
> >
>
> Well, this thing doesnt run ovs ;-> (/me runs). If you come
> to netdev i may let you play with it ;-> Its a humongous device
> (think multi 100G ports).
>
> On a serious note: Even if you took what Simon/Netronome has
> (yes, I know they use ovs;->)
FWIW, we are also interested in non-OVS use cases.
> - there is really no need for a switch
> abstraction *at all* if all you want to is hang a packet
> processing graph that ingresses at a port and egress at another port.
> As you know, Linux supports it just fine with tc.
I may be missing the point but I see two problems that are solved by
the switch abstraction.
- Cases where no ports are configured.
Perhaps no such use cases exist for the API in question.
But it does seem plausible to me that non-physical ports could
be added at run-time and that thus a "switch" could initially
exist with no configured port. Something like how bridges
initially have no ports (IIRC).
- Discovering the association between ports and "switches".
My recollection from the double round table discussion on the last day of
the Düsseldorf sessions was that these were reasons that simply accessing
any port belonging to the "switch" were not entirely satisfactory.
> >I'm with Jiri but I agree it's not a perfect fit. I doubt there is but
> >if you can come up with something that fits better I'm open to it.
> >
> >I considered "dataplane" or "dp" for a bit but it's quite generic as
> >well.
> >
>
> The purpose is to offload. I think any name would be better than
> mapping it to a specific abstraction called "switch". Especially
> if it is hanging off a port and there is no switch in the pipeline.
>
> cheers,
> jamal
^ permalink raw reply
* [PATCH] stmmac: platform: Move plat_dat checking earlier
From: Huacai Chen @ 2014-11-27 3:14 UTC (permalink / raw)
To: Giuseppe Cavallaro; +Cc: Vince Bridgers, David S. Miller, netdev, Huacai Chen
Original code only check/alloc plat_dat for the CONFIG_OF case, this
patch check/alloc it earlier and unconditionally to avoid kernel build
warnings:
drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c:275
stmmac_pltfr_probe() warn: variable dereferenced before check 'plat_dat'
Signed-off-by: Huacai Chen <chenhc@lemote.com>
---
.../net/ethernet/stmicro/stmmac/stmmac_platform.c | 18 +++++++++---------
1 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5b0da39..d254950 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -265,6 +265,15 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
plat_dat = dev_get_platdata(&pdev->dev);
+ if (!plat_dat)
+ plat_dat = devm_kzalloc(&pdev->dev,
+ sizeof(struct plat_stmmacenet_data),
+ GFP_KERNEL);
+ if (!plat_dat) {
+ pr_err("%s: ERROR: no memory", __func__);
+ return -ENOMEM;
+ }
+
/* Set default value for multicast hash bins */
plat_dat->multicast_filter_bins = HASH_TABLE_SIZE;
@@ -272,15 +281,6 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
plat_dat->unicast_filter_entries = 1;
if (pdev->dev.of_node) {
- if (!plat_dat)
- plat_dat = devm_kzalloc(&pdev->dev,
- sizeof(struct plat_stmmacenet_data),
- GFP_KERNEL);
- if (!plat_dat) {
- pr_err("%s: ERROR: no memory", __func__);
- return -ENOMEM;
- }
-
ret = stmmac_probe_config_dt(pdev, plat_dat, &mac);
if (ret) {
pr_err("%s: main dt probe failed", __func__);
--
1.7.7.3
^ permalink raw reply related
* Re: [PATCH] xen-netfront: Remove BUGs on paged skb data which crosses a page boundary
From: Seth Forshee @ 2014-11-27 3:53 UTC (permalink / raw)
To: David Miller
Cc: konrad.wilk, boris.ostrovsky, david.vrabel, zoltan.kiss,
eric.dumazet, stefan.bader, xen-devel, netdev, linux-kernel
In-Reply-To: <20141126.122812.223757363894961994.davem@davemloft.net>
On Wed, Nov 26, 2014 at 12:28:12PM -0500, David Miller wrote:
> From: Seth Forshee <seth.forshee@canonical.com>
> Date: Tue, 25 Nov 2014 20:28:24 -0600
>
> > These BUGs can be erroneously triggered by frags which refer to
> > tail pages within a compound page. The data in these pages may
> > overrun the hardware page while still being contained within the
> > compound page, but since compound_order() evaluates to 0 for tail
> > pages the assertion fails. The code already iterates through
> > subsequent pages correctly in this scenario, so the BUGs are
> > unnecessary and can be removed.
> >
> > Fixes: f36c374782e4 ("xen/netfront: handle compound page fragments on transmit")
> > Cc: <stable@vger.kernel.org> # 3.7+
> > Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
>
> Can I get some Xen developer reviews?
Fwiw this issue was discussed previously and this was the recommended
fix.
http://article.gmane.org/gmane.linux.kernel/1825381
Since then I got some feedback from a tester that he didn't see any
problems with the BUGs removed (actually replaced with a WARN so I know
that he actually saw the condition which triggered the BUG).
Thanks,
Seth
^ permalink raw reply
* Re: Multiple DSA switch on shared MII
From: Rajib Karmakar @ 2014-11-27 4:47 UTC (permalink / raw)
To: Florian Fainelli; +Cc: netdev
In-Reply-To: <547636B7.3060706@gmail.com>
On Thu, Nov 27, 2014 at 1:53 AM, Florian Fainelli <f.fainelli@gmail.com> wrote:
> On 25/11/14 23:33, Rajib Karmakar wrote:
>> Hello Florian,
>>
>> Thanks for your reply.
>>
>> On Wed, Nov 26, 2014 at 10:52 AM, Florian Fainelli <f.fainelli@gmail.com> wrote:
>>> 2014-11-25 20:52 GMT-08:00 Rajib Karmakar <rajibkit@gmail.com>:
>>>> Hello,
>>>>
>>>> I am developing a DSA driver for Marvell 6172 and need to create 2 dsa
>>>> switch chip (one for WAN and one for LAN).
>>>
>>> This is not typically how it is designed to work, you would register
>>> one dsa switch chip with the ports assignment in this data structure.
>>> Right now, DSA does not support a dual Ethernet MAC configuration,
>>> although you could probably do per-port VLAN membership and create two
>>> default VLANs to allow that.
>>>
>>>>
>>>> My device has 2 MACs and one shared mii_bus. I have added two
>>>> dsa_platform_data structures and registered them but cannot probe as
>>>> dsa_probe tries mdio_register() on the same bus and fails.
>>>>
>>>> Is it possible to create two DSA switch on same (shared) mii?
>>>
>>> Not in its current form, and I am not exactly sure how we would support that.
>>
>> Yes, not with the current DSA implementation, but I can manage to
>> solve this by a small (ugly) patch - renamed the slave mii bus as
>> "<master_bus->id>:<pd->sw_addr>:<platform_device->id>" instead of
>> "<master_bus->id>:<pd->sw_addr>". Though I am not yet sure enough if
>> this could have any negative impact or not.
>
> This will register two virtual slave mii buses backed by the same real
> mdio bus driver, although that is not necessarily a problem, you want to
> make sure that they are not going to poll the same PHYs in the switch
> driver.
>
> This is probably the easiest way to achieve what you want, can you just
> introduce a check on the "id" being >= 0 (using -1 with platform_devices
> is valid when there is just one device in the system).
>
> Thanks!
>
yes, I handled that later. Thanks for your reply
>>
>> Comments please.
>>
>>>
>>>>
>>>> Regards,
>>>> Rajib
>>>> --
>>>> To unsubscribe from this list: send the line "unsubscribe netdev" in
>>>> the body of a message to majordomo@vger.kernel.org
>>>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>>>
>>>
>>>
>>> --
>>> Florian
>>
>> ----
>> diff -rup org/net/dsa/dsa.c mod/net/dsa/dsa.c
>> --- org/net/dsa/dsa.c
>> +++ mod/net/dsa/dsa.c
>> @@ -68,7 +68,7 @@ dsa_switch_probe(struct mii_bus *bus, in
>>
>> /* basic switch operations **************************************************/
>> static struct dsa_switch *
>> -dsa_switch_setup(struct dsa_switch_tree *dst, int index,
>> +dsa_switch_setup(struct dsa_switch_tree *dst, int index, int id,
>> struct device *parent, struct mii_bus *bus)
>> {
>> struct dsa_chip_data *pd = dst->pd->chip + index;
>> @@ -156,7 +156,7 @@ dsa_switch_setup(struct dsa_switch_tree
>> ret = -ENOMEM;
>> goto out;
>> }
>> - dsa_slave_mii_bus_init(ds);
>> + dsa_slave_mii_bus_init(ds, id);
>>
>> ret = mdiobus_register(ds->slave_mii_bus);
>> if (ret < 0)
>> @@ -349,7 +349,7 @@ static int dsa_probe(struct platform_dev
>> continue;
>> }
>>
>> - ds = dsa_switch_setup(dst, i, &pdev->dev, bus);
>> + ds = dsa_switch_setup(dst, i, pdev->id, &pdev->dev, bus);
>> if (IS_ERR(ds)) {
>> printk(KERN_ERR "%s[%d]: couldn't create dsa switch "
>> "instance (error %ld)\n", dev->name, i,
>> diff -rup org/net/dsa/dsa_priv.h mod/net/dsa/dsa_priv.h
>> --- org/net/dsa/dsa_priv.h
>> +++ mod/net/dsa/dsa_priv.h
>> @@ -163,7 +163,7 @@ void register_switch_driver(struct dsa_s
>> void unregister_switch_driver(struct dsa_switch_driver *type);
>>
>> /* slave.c */
>> -void dsa_slave_mii_bus_init(struct dsa_switch *ds);
>> +void dsa_slave_mii_bus_init(struct dsa_switch *ds, int id);
>> struct net_device *dsa_slave_create(struct dsa_switch *ds,
>> struct device *parent,
>> int port, char *name);
>> diff -rup org/net/dsa/slave.c mod/net/dsa/slave.c
>> --- org/net/dsa/slave.c
>> +++ mod/net/dsa/slave.c
>> @@ -35,14 +35,14 @@ static int dsa_slave_phy_write(struct mi
>> return 0;
>> }
>>
>> -void dsa_slave_mii_bus_init(struct dsa_switch *ds)
>> +void dsa_slave_mii_bus_init(struct dsa_switch *ds, int id)
>> {
>> ds->slave_mii_bus->priv = (void *)ds;
>> ds->slave_mii_bus->name = "dsa slave smi";
>> ds->slave_mii_bus->read = dsa_slave_phy_read;
>> ds->slave_mii_bus->write = dsa_slave_phy_write;
>> - snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "%s:%.2x",
>> - ds->master_mii_bus->id, ds->pd->sw_addr);
>> + snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "%s:%.2x:%.1x",
>> + ds->master_mii_bus->id, ds->pd->sw_addr, id);
>> ds->slave_mii_bus->parent = &ds->master_mii_bus->dev;
>> }
>>
>
^ permalink raw reply
* Re: [PATCH net-next V2] tun/macvtap: use consume_skb() instead of kfree_skb() when needed
From: Jason Wang @ 2014-11-27 5:02 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: davem, netdev, linux-kernel, Eric Dumazet
In-Reply-To: <20141126134742.GA5358@redhat.com>
On 11/26/2014 09:47 PM, Michael S. Tsirkin wrote:
> On Wed, Nov 26, 2014 at 03:43:30PM +0800, Jason Wang wrote:
>> >To be more friendly with drop monitor, we should only call kfree_skb() when
>> >the packets were dropped and use consume_skb() in other cases.
>> >
>> >Cc: Eric Dumazet<eric.dumazet@gmail.com>
>> >Signed-off-by: Jason Wang<jasowang@redhat.com>
>> >---
>> >Changes from V1:
>> >- check the return value of tun/macvtap_put_user()
>> >---
>> > drivers/net/macvtap.c | 5 ++++-
>> > drivers/net/tun.c | 5 ++++-
>> > 2 files changed, 8 insertions(+), 2 deletions(-)
>> >
>> >diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
>> >index 42a80d3..c171ab6 100644
>> >--- a/drivers/net/macvtap.c
>> >+++ b/drivers/net/macvtap.c
>> >@@ -862,7 +862,10 @@ static ssize_t macvtap_do_read(struct macvtap_queue *q,
>> > }
>> > iov_iter_init(&iter, READ, iv, segs, len);
>> > ret = macvtap_put_user(q, skb, &iter);
>> >- kfree_skb(skb);
>> >+ if (ret < 0)
> Maybe unlikely() here?
>
Better, will post V3.
Thanks
^ permalink raw reply
* [PATCH net] bpf: x86: fix epilogue generation for eBPF programs
From: Alexei Starovoitov @ 2014-11-27 5:02 UTC (permalink / raw)
To: David S. Miller
Cc: Zi Shen Lim, Eric Dumazet, Daniel Borkmann, H. Peter Anvin,
Thomas Gleixner, Ingo Molnar, netdev, linux-kernel
classic BPF has a restriction that last insn is always BPF_RET.
eBPF doesn't have BPF_RET instruction and this restriction.
It has BPF_EXIT insn which can appear anywhere in the program
one or more times and it doesn't have to be last insn.
Fix eBPF JIT to emit epilogue when first BPF_EXIT is seen
and all other BPF_EXIT instructions will be emitted as jump.
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
Note, this bug is applicable only to native eBPF programs
which first were introduced in 3.18, so no need to send it
to stable and therefore no 'Fixes' tag.
arm64 JIT has the same problem, but the fix is not as trivial,
so will be done as separate patch.
Since 3.18 can only load eBPF programs and cannot execute them,
this patch can even be done in net-next only, but I think it's worth
to apply it to 3.18(net), so that JITed output for native eBPF
programs is correct when bpf syscall loads it with net.core.bpf_jit_enable=2
arch/x86/net/bpf_jit_comp.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 3f62734..7e90244 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -178,7 +178,7 @@ static void jit_fill_hole(void *area, unsigned int size)
}
struct jit_context {
- unsigned int cleanup_addr; /* epilogue code offset */
+ int cleanup_addr; /* epilogue code offset */
bool seen_ld_abs;
};
@@ -192,6 +192,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
struct bpf_insn *insn = bpf_prog->insnsi;
int insn_cnt = bpf_prog->len;
bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
+ bool seen_exit = false;
u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
int i;
int proglen = 0;
@@ -854,10 +855,11 @@ common_load:
goto common_load;
case BPF_JMP | BPF_EXIT:
- if (i != insn_cnt - 1) {
+ if (seen_exit) {
jmp_offset = ctx->cleanup_addr - addrs[i];
goto emit_jmp;
}
+ seen_exit = true;
/* update cleanup_addr */
ctx->cleanup_addr = proglen;
/* mov rbx, qword ptr [rbp-X] */
--
1.7.9.5
^ permalink raw reply related
* [PATCH net-next] ipvlan: ipvlan depends on INET and IPV6
From: Mahesh Bandewar @ 2014-11-27 5:13 UTC (permalink / raw)
To: netdev; +Cc: David Miller, Jim Davis, Mahesh Bandewar
This driver uses ip_out_local() and ip6_route_output() which are
defined only if CONFIG_INET and CONFIG_IPV6 are enabled respectively.
Reported-by: Jim Davis <jim.epost@gmail.com>
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
---
drivers/net/Kconfig | 2 ++
drivers/net/ipvlan/ipvlan.h | 3 ++-
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index b6d64f546574..d6607ee9c855 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -148,6 +148,8 @@ config MACVTAP
config IPVLAN
tristate "IP-VLAN support"
+ depends on INET
+ depends on IPV6
---help---
This allows one to create virtual devices off of a main interface
and packets will be delivered based on the dest L3 (IPv6/IPv4 addr)
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index ab3e7614ed71..c44d29eca6c0 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -23,8 +23,9 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/inetdevice.h>
+#include <net/ip.h>
+#include <net/ip6_route.h>
#include <net/rtnetlink.h>
-#include <net/gre.h>
#include <net/route.h>
#include <net/addrconf.h>
--
2.2.0.rc0.207.ga3a616c
^ permalink raw reply related
* Re: [PATCH net-next] macvlan: delay the header check for dodgy packets into lower device
From: Jason Wang @ 2014-11-27 5:14 UTC (permalink / raw)
To: David Miller; +Cc: kaber, netdev, linux-kernel, mst, vyasevic
In-Reply-To: <20141126.153736.1815789848350571029.davem@davemloft.net>
On 11/27/2014 04:37 AM, David Miller wrote:
> From: Jason Wang <jasowang@redhat.com>
> Date: Wed, 26 Nov 2014 17:21:14 +0800
>
>> We do header check twice for a dodgy packet. One is done before
>> macvlan_start_xmit(), another is done before lower device's
>> ndo_start_xmit(). The first one seems redundant so this patch tries to
>> delay header check until a packet reaches its lower device (or macvtap)
>> through always enabling NETIF_F_GSO_ROBUST for macvlan device.
>>
>> Cc: Patrick McHardy <kaber@trash.net>
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>
> Hmmm, it's the idea that if we have a dodgy packet, we want to
> notice that as early as possible in the packet processing path?
>
Not late even with this patch. The check will be done immediately after
macvlan passing a packet to lower device which should be sufficient.
For good packets, this patch saves one time of header checking. For bad
packets, this patch just lets the dropping happens during the validation
before ndo_start_xmit() of lower device.
^ permalink raw reply
* [PATCH] e1000: remove unused variables
From: Sudip Mukherjee @ 2014-11-27 5:22 UTC (permalink / raw)
To: Jeff Kirsher, Jesse Brandeburg, Bruce Allan, Carolyn Wyborny,
Don Skidmore, Greg Rose, Matthew Vick, John Ronciak,
Mitch Williams, Linux NICS
Cc: e1000-devel, netdev, Sudip Mukherjee, linux-kernel
these variables were only being assigned some values, but were never
used.
Signed-off-by: Sudip Mukherjee <sudip@vectorindia.org>
---
drivers/net/ethernet/intel/e1000/e1000_hw.c | 142 ++++++++++++--------------
drivers/net/ethernet/intel/e1000/e1000_main.c | 3 -
2 files changed, 66 insertions(+), 79 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
index 45c8c864..7812f59 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
@@ -154,7 +154,6 @@ static s32 e1000_set_phy_type(struct e1000_hw *hw)
*/
static void e1000_phy_init_script(struct e1000_hw *hw)
{
- u32 ret_val;
u16 phy_saved_data;
if (hw->phy_init_script) {
@@ -163,7 +162,7 @@ static void e1000_phy_init_script(struct e1000_hw *hw)
/* Save off the current value of register 0x2F5B to be restored
* at the end of this routine.
*/
- ret_val = e1000_read_phy_reg(hw, 0x2F5B, &phy_saved_data);
+ e1000_read_phy_reg(hw, 0x2F5B, &phy_saved_data);
/* Disabled the PHY transmitter */
e1000_write_phy_reg(hw, 0x2F5B, 0x0003);
@@ -402,7 +401,6 @@ s32 e1000_reset_hw(struct e1000_hw *hw)
{
u32 ctrl;
u32 ctrl_ext;
- u32 icr;
u32 manc;
u32 led_ctrl;
s32 ret_val;
@@ -527,7 +525,7 @@ s32 e1000_reset_hw(struct e1000_hw *hw)
ew32(IMC, 0xffffffff);
/* Clear any pending interrupt events. */
- icr = er32(ICR);
+ er32(ICR);
/* If MWI was previously enabled, reenable it. */
if (hw->mac_type == e1000_82542_rev2_0) {
@@ -2396,16 +2394,13 @@ static s32 e1000_check_for_serdes_link_generic(struct e1000_hw *hw)
*/
s32 e1000_check_for_link(struct e1000_hw *hw)
{
- u32 rxcw = 0;
- u32 ctrl;
u32 status;
u32 rctl;
u32 icr;
- u32 signal = 0;
s32 ret_val;
u16 phy_data;
- ctrl = er32(CTRL);
+ er32(CTRL);
status = er32(STATUS);
/* On adapters with a MAC newer than 82544, SW Definable pin 1 will be
@@ -2414,12 +2409,9 @@ s32 e1000_check_for_link(struct e1000_hw *hw)
*/
if ((hw->media_type == e1000_media_type_fiber) ||
(hw->media_type == e1000_media_type_internal_serdes)) {
- rxcw = er32(RXCW);
+ er32(RXCW);
if (hw->media_type == e1000_media_type_fiber) {
- signal =
- (hw->mac_type >
- e1000_82544) ? E1000_CTRL_SWDPIN1 : 0;
if (status & E1000_STATUS_LU)
hw->get_link_status = false;
}
@@ -4698,78 +4690,76 @@ s32 e1000_led_off(struct e1000_hw *hw)
*/
static void e1000_clear_hw_cntrs(struct e1000_hw *hw)
{
- volatile u32 temp;
-
- temp = er32(CRCERRS);
- temp = er32(SYMERRS);
- temp = er32(MPC);
- temp = er32(SCC);
- temp = er32(ECOL);
- temp = er32(MCC);
- temp = er32(LATECOL);
- temp = er32(COLC);
- temp = er32(DC);
- temp = er32(SEC);
- temp = er32(RLEC);
- temp = er32(XONRXC);
- temp = er32(XONTXC);
- temp = er32(XOFFRXC);
- temp = er32(XOFFTXC);
- temp = er32(FCRUC);
-
- temp = er32(PRC64);
- temp = er32(PRC127);
- temp = er32(PRC255);
- temp = er32(PRC511);
- temp = er32(PRC1023);
- temp = er32(PRC1522);
-
- temp = er32(GPRC);
- temp = er32(BPRC);
- temp = er32(MPRC);
- temp = er32(GPTC);
- temp = er32(GORCL);
- temp = er32(GORCH);
- temp = er32(GOTCL);
- temp = er32(GOTCH);
- temp = er32(RNBC);
- temp = er32(RUC);
- temp = er32(RFC);
- temp = er32(ROC);
- temp = er32(RJC);
- temp = er32(TORL);
- temp = er32(TORH);
- temp = er32(TOTL);
- temp = er32(TOTH);
- temp = er32(TPR);
- temp = er32(TPT);
-
- temp = er32(PTC64);
- temp = er32(PTC127);
- temp = er32(PTC255);
- temp = er32(PTC511);
- temp = er32(PTC1023);
- temp = er32(PTC1522);
-
- temp = er32(MPTC);
- temp = er32(BPTC);
+ er32(CRCERRS);
+ er32(SYMERRS);
+ er32(MPC);
+ er32(SCC);
+ er32(ECOL);
+ er32(MCC);
+ er32(LATECOL);
+ er32(COLC);
+ er32(DC);
+ er32(SEC);
+ er32(RLEC);
+ er32(XONRXC);
+ er32(XONTXC);
+ er32(XOFFRXC);
+ er32(XOFFTXC);
+ er32(FCRUC);
+
+ er32(PRC64);
+ er32(PRC127);
+ er32(PRC255);
+ er32(PRC511);
+ er32(PRC1023);
+ er32(PRC1522);
+
+ er32(GPRC);
+ er32(BPRC);
+ er32(MPRC);
+ er32(GPTC);
+ er32(GORCL);
+ er32(GORCH);
+ er32(GOTCL);
+ er32(GOTCH);
+ er32(RNBC);
+ er32(RUC);
+ er32(RFC);
+ er32(ROC);
+ er32(RJC);
+ er32(TORL);
+ er32(TORH);
+ er32(TOTL);
+ er32(TOTH);
+ er32(TPR);
+ er32(TPT);
+
+ er32(PTC64);
+ er32(PTC127);
+ er32(PTC255);
+ er32(PTC511);
+ er32(PTC1023);
+ er32(PTC1522);
+
+ er32(MPTC);
+ er32(BPTC);
if (hw->mac_type < e1000_82543)
return;
- temp = er32(ALGNERRC);
- temp = er32(RXERRC);
- temp = er32(TNCRS);
- temp = er32(CEXTERR);
- temp = er32(TSCTC);
- temp = er32(TSCTFC);
+ er32(ALGNERRC);
+ er32(RXERRC);
+ er32(TNCRS);
+ er32(CEXTERR);
+ er32(TSCTC);
+ er32(TSCTFC);
if (hw->mac_type <= e1000_82544)
return;
- temp = er32(MGTPRC);
- temp = er32(MGTPDC);
- temp = er32(MGTPTC);
+ er32(MGTPRC);
+ er32(MGTPDC);
+ er32(MGTPTC);
}
/**
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 24f3986..a70ea46 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -2443,7 +2443,6 @@ static void e1000_watchdog(struct work_struct *work)
if (link) {
if (!netif_carrier_ok(netdev)) {
u32 ctrl;
- bool txb2b = true;
/* update snapshot of PHY registers on LSC */
e1000_get_speed_and_duplex(hw,
&adapter->link_speed,
@@ -2465,11 +2464,9 @@ static void e1000_watchdog(struct work_struct *work)
adapter->tx_timeout_factor = 1;
switch (adapter->link_speed) {
case SPEED_10:
- txb2b = false;
adapter->tx_timeout_factor = 16;
break;
case SPEED_100:
- txb2b = false;
/* maybe add some timeout factor ? */
break;
}
--
1.8.1.2
------------------------------------------------------------------------------
Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
from Actuate! Instantly Supercharge Your Business Reports and Dashboards
with Interactivity, Sharing, Native Excel Exports, App Integration & more
Get technology previously reserved for billion-dollar corporations, FREE
http://pubads.g.doubleclick.net/gampad/clk?id=157005751&iu=/4140/ostg.clktrk
_______________________________________________
E1000-devel mailing list
E1000-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired
^ permalink raw reply related
* Re: [RFC PATCH 1/3] net: Split netdev_alloc_frag into __alloc_page_frag and add __napi_alloc_frag
From: Alexei Starovoitov @ 2014-11-27 5:29 UTC (permalink / raw)
To: Alexander Duyck
Cc: Network Development, David S. Miller, Jesper Dangaard Brouer,
Jeff Kirsher, Eric Dumazet
In-Reply-To: <20141127000557.1617.88261.stgit@ahduyck-vm-fedora20>
On Wed, Nov 26, 2014 at 4:05 PM, Alexander Duyck
<alexander.h.duyck@redhat.com> wrote:
> This patch splits the netdev_alloc_frag function up so that it can be used
> on one of two page frag pools instead of being fixed on the
> netdev_alloc_cache. By doing this we can add a NAPI specific function
> __napi_alloc_frag that accesses a pool that is only used from softirq
> context. The advantage to this is that we do not need to call
> local_irq_save/restore which can be a significant savings.
>
> I also took the opportunity to refactor the core bits that were placed in
> __alloc_page_frag. First I updated the allocation to do either a 32K
> allocation or an order 0 page. Then I also rewrote the logic to work from
> the end of the page to the start. By doing this the size value doesn't
> have to be used unless we have run out of space for page fragments.
> Finally I cleaned up the atomic bits so that we just do an
> atomic_sub_return and if that returns 0 then we set the page->_count via an
> atomic_set. This way we can remove the extra conditional for the
> atomic_read since it would have led to an atomic_inc in the case of success
> anyway.
Nice simplification. Complicated, but looks good to me.
I think only replacement of loop with 32k+page begs
better explanation in the commit log. I'm guessing you're
killing intermediate sizes to simplify the code?
Thank you for doing it. It's a great improvement.
^ permalink raw reply
* Re: [PATCH v2 02/19] kbuild: kselftest_install - add a new make target to install selftests
From: Masami Hiramatsu @ 2014-11-27 5:32 UTC (permalink / raw)
To: Shuah Khan
Cc: gregkh, akpm, mmarek, davem, keescook, tranmanphong, dh.herrmann,
hughd, bobby.prani, ebiederm, serge.hallyn, linux-kbuild,
linux-kernel, linux-api, netdev
In-Reply-To: <a2344d4df903d673afe1631118f40917f773cc9a.1415735831.git.shuahkh@osg.samsung.com>
(2014/11/12 5:27), Shuah Khan wrote:
> Add a new make target to install to install kernel selftests.
> This new target will build and install selftests. kselftest
> target now depends on kselftest_install and runs the generated
> kselftest script to reduce duplicate work and for common look
> and feel when running tests.
>
> Approach:
>
> make kselftest_target:
kselftest_install?
> -- exports kselftest INSTALL_KSFT_PATH
> default $(INSTALL_MOD_PATH)/lib/kselftest/$(KERNELRELEASE)
> -- exports path for ksefltest.sh
> -- runs selftests make install target:
This direction is OK to me.
BTW, I've found another path to make selftest in Makefile,
Actually you can do
make -C tools/ selftest
And there are selftest_install and selftest_clean targets (but
currently it has a bug and doesn't work, anyway)
I think we'd better do subdir make instead of adding these targets.
This means that "make kselftest*" should be an alias of "make -C tools/ selftest*"
Also, I'd like to request passing some options like as O=$(objtree)
so that we can make test kmodules in selftests.
Thank you,
--
Masami HIRAMATSU
Software Platform Research Dept. Linux Technology Research Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@hitachi.com
^ permalink raw reply
* [PATCH net-next 0/6] allow eBPF programs to be attached to sockets
From: Alexei Starovoitov @ 2014-11-27 5:42 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Andy Lutomirski, Daniel Borkmann,
Hannes Frederic Sowa, Eric Dumazet,
linux-api-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
Introduce BPF_PROG_TYPE_SOCKET_FILTER type of eBPF programs that can be
attached to sockets with setsockopt().
Allow such programs to access maps via lookup/update/delete helpers.
This feature was previewed by bpf manpage in commit b4fc1a460f30("Merge branch 'bpf-next'")
Now it can actually run.
1st patch adds LD_ABS/LD_IND instruction verification and
2nd patch adds new setsockopt() flag.
Patches 3-6 are examples in assembler and in C.
Though native eBPF programs are way more powerful than classic filters
(attachable through similar setsockopt() call), they don't have skb field
accessors yet. Like skb->pkt_type, skb->dev->ifindex are not accessible.
There are sevaral ways to achieve that. That will be in the next set of patches.
So in this set native eBPF programs can only read data from packet and
access maps.
The most powerful example is sockex2_kern.c from patch 6 where ~200 lines of C
are compiled into ~300 of eBPF instructions.
It shows how quite complex packet parsing can be done.
LLVM used to build examples is at https://github.com/iovisor/llvm
which is fork of llvm trunk that I'm cleaning up for upstreaming.
Alexei Starovoitov (6):
bpf: verifier: add checks for BPF_ABS | BPF_IND instructions
net: sock: allow eBPF programs to be attached to sockets
samples: bpf: example of stateful socket filtering
samples: bpf: elf_bpf file loader
samples: bpf: trivial eBPF program in C
samples: bpf: large eBPF program in C
arch/alpha/include/uapi/asm/socket.h | 3 +
arch/avr32/include/uapi/asm/socket.h | 3 +
arch/cris/include/uapi/asm/socket.h | 3 +
arch/frv/include/uapi/asm/socket.h | 3 +
arch/ia64/include/uapi/asm/socket.h | 3 +
arch/m32r/include/uapi/asm/socket.h | 3 +
arch/mips/include/uapi/asm/socket.h | 3 +
arch/mn10300/include/uapi/asm/socket.h | 3 +
arch/parisc/include/uapi/asm/socket.h | 3 +
arch/powerpc/include/uapi/asm/socket.h | 3 +
arch/s390/include/uapi/asm/socket.h | 3 +
arch/sparc/include/uapi/asm/socket.h | 3 +
arch/xtensa/include/uapi/asm/socket.h | 3 +
include/linux/bpf.h | 4 +
include/linux/filter.h | 1 +
include/uapi/asm-generic/socket.h | 3 +
include/uapi/linux/bpf.h | 1 +
kernel/bpf/verifier.c | 70 ++++++++++-
net/core/filter.c | 97 +++++++++++++-
net/core/sock.c | 13 ++
samples/bpf/Makefile | 20 +++
samples/bpf/bpf_helpers.h | 40 ++++++
samples/bpf/bpf_load.c | 203 ++++++++++++++++++++++++++++++
samples/bpf/bpf_load.h | 24 ++++
samples/bpf/libbpf.c | 28 +++++
samples/bpf/libbpf.h | 15 ++-
samples/bpf/sock_example.c | 97 ++++++++++++++
samples/bpf/sockex1_kern.c | 23 ++++
samples/bpf/sockex1_user.c | 49 ++++++++
samples/bpf/sockex2_kern.c | 215 ++++++++++++++++++++++++++++++++
samples/bpf/sockex2_user.c | 44 +++++++
31 files changed, 981 insertions(+), 5 deletions(-)
create mode 100644 samples/bpf/bpf_helpers.h
create mode 100644 samples/bpf/bpf_load.c
create mode 100644 samples/bpf/bpf_load.h
create mode 100644 samples/bpf/sock_example.c
create mode 100644 samples/bpf/sockex1_kern.c
create mode 100644 samples/bpf/sockex1_user.c
create mode 100644 samples/bpf/sockex2_kern.c
create mode 100644 samples/bpf/sockex2_user.c
--
1.7.9.5
^ permalink raw reply
* [PATCH net-next 1/6] bpf: verifier: add checks for BPF_ABS | BPF_IND instructions
From: Alexei Starovoitov @ 2014-11-27 5:42 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Andy Lutomirski, Daniel Borkmann,
Hannes Frederic Sowa, Eric Dumazet, linux-api, netdev,
linux-kernel
In-Reply-To: <1417066951-1999-1-git-send-email-ast@plumgrid.com>
introduce program type BPF_PROG_TYPE_SOCKET_FILTER that is used
for attaching programs to sockets where ctx == skb.
add verifier checks for ABS/IND instructions which can only be seen
in socket filters, therefore the check:
if (env->prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER)
verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n");
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
include/uapi/linux/bpf.h | 1 +
kernel/bpf/verifier.c | 70 ++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 69 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4a3d0f84f178..45da7ec7d274 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -117,6 +117,7 @@ enum bpf_map_type {
enum bpf_prog_type {
BPF_PROG_TYPE_UNSPEC,
+ BPF_PROG_TYPE_SOCKET_FILTER,
};
/* flags for BPF_MAP_UPDATE_ELEM command */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b6a1f7c14a67..a28e09c7825d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1172,6 +1172,70 @@ static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn)
return 0;
}
+/* verify safety of LD_ABS|LD_IND instructions:
+ * - they can only appear in the programs where ctx == skb
+ * - since they are wrappers of function calls, they scratch R1-R5 registers,
+ * preserve R6-R9, and store return value into R0
+ *
+ * Implicit input:
+ * ctx == skb == R6 == CTX
+ *
+ * Explicit input:
+ * SRC == any register
+ * IMM == 32-bit immediate
+ *
+ * Output:
+ * R0 - 8/16/32-bit skb data converted to cpu endianness
+ */
+static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
+{
+ struct reg_state *regs = env->cur_state.regs;
+ u8 mode = BPF_MODE(insn->code);
+ struct reg_state *reg;
+ int i, err;
+
+ if (env->prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
+ verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n");
+ return -EINVAL;
+ }
+
+ if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+ (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
+ verbose("BPF_LD_ABS uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ /* check whether implicit source operand (register R6) is readable */
+ err = check_reg_arg(regs, BPF_REG_6, SRC_OP);
+ if (err)
+ return err;
+
+ if (regs[BPF_REG_6].type != PTR_TO_CTX) {
+ verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
+ return -EINVAL;
+ }
+
+ if (mode == BPF_IND) {
+ /* check explicit source operand */
+ err = check_reg_arg(regs, insn->src_reg, SRC_OP);
+ if (err)
+ return err;
+ }
+
+ /* reset caller saved regs to unreadable */
+ for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ reg = regs + caller_saved[i];
+ reg->type = NOT_INIT;
+ reg->imm = 0;
+ }
+
+ /* mark destination R0 register as readable, since it contains
+ * the value fetched from the packet
+ */
+ regs[BPF_REG_0].type = UNKNOWN_VALUE;
+ return 0;
+}
+
/* non-recursive DFS pseudo code
* 1 procedure DFS-iterative(G,v):
* 2 label v as discovered
@@ -1677,8 +1741,10 @@ process_bpf_exit:
u8 mode = BPF_MODE(insn->code);
if (mode == BPF_ABS || mode == BPF_IND) {
- verbose("LD_ABS is not supported yet\n");
- return -EINVAL;
+ err = check_ld_abs(env, insn);
+ if (err)
+ return err;
+
} else if (mode == BPF_IMM) {
err = check_ld_imm(env, insn);
if (err)
--
1.7.9.5
^ permalink raw reply related
* [PATCH net-next 2/6] net: sock: allow eBPF programs to be attached to sockets
From: Alexei Starovoitov @ 2014-11-27 5:42 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Andy Lutomirski, Daniel Borkmann,
Hannes Frederic Sowa, Eric Dumazet, linux-api, netdev,
linux-kernel
In-Reply-To: <1417066951-1999-1-git-send-email-ast@plumgrid.com>
introduce new setsockopt() command:
setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd, sizeof(prog_fd))
where prog_fd was received from syscall bpf(BPF_PROG_LOAD, attr, ...)
and attr->prog_type == BPF_PROG_TYPE_SOCKET_FILTER
setsockopt() calls bpf_prog_get() which increments refcnt of the program,
so it doesn't get unloaded while socket is using the program.
The same eBPF program can be attached to multiple sockets.
User task exit automatically closes socket which calls sk_filter_uncharge()
which decrements refcnt of eBPF program
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
Note, I'm not happy about 'ifdef', but 'select or depend BPF_SYSCALL' will
make tinification folks cringe, so use ifdef until native eBPF use cases
become widespread.
---
arch/alpha/include/uapi/asm/socket.h | 3 +
arch/avr32/include/uapi/asm/socket.h | 3 +
arch/cris/include/uapi/asm/socket.h | 3 +
arch/frv/include/uapi/asm/socket.h | 3 +
arch/ia64/include/uapi/asm/socket.h | 3 +
arch/m32r/include/uapi/asm/socket.h | 3 +
arch/mips/include/uapi/asm/socket.h | 3 +
arch/mn10300/include/uapi/asm/socket.h | 3 +
arch/parisc/include/uapi/asm/socket.h | 3 +
arch/powerpc/include/uapi/asm/socket.h | 3 +
arch/s390/include/uapi/asm/socket.h | 3 +
arch/sparc/include/uapi/asm/socket.h | 3 +
arch/xtensa/include/uapi/asm/socket.h | 3 +
include/linux/bpf.h | 4 ++
include/linux/filter.h | 1 +
include/uapi/asm-generic/socket.h | 3 +
net/core/filter.c | 97 +++++++++++++++++++++++++++++++-
net/core/sock.c | 13 +++++
18 files changed, 155 insertions(+), 2 deletions(-)
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index e2fe0700b3b4..9a20821b111c 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -89,4 +89,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 92121b0f5b98..2b65ed6b277c 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -82,4 +82,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h
index 60f60f5b9b35..e2503d9f1869 100644
--- a/arch/cris/include/uapi/asm/socket.h
+++ b/arch/cris/include/uapi/asm/socket.h
@@ -84,6 +84,9 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index 2c6890209ea6..4823ad125578 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -82,5 +82,8 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 09a93fb566f6..59be3d87f86d 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -91,4 +91,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index e8589819c274..7bc4cb273856 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -82,4 +82,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 2e9ee8c55a10..dec3c850f36b 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -100,4 +100,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index f3492e8c9f70..cab7d6d50051 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -82,4 +82,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 7984a1cab3da..a5cd40cd8ee1 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -81,4 +81,7 @@
#define SO_INCOMING_CPU 0x402A
+#define SO_ATTACH_BPF 0x402B
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index 3474e4ef166d..c046666038f8 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -89,4 +89,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 8457636c33e1..296942d56e6a 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -88,4 +88,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 4a8003a94163..e6a16c40be5f 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -78,6 +78,9 @@
#define SO_INCOMING_CPU 0x0033
+#define SO_ATTACH_BPF 0x0034
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index c46f6a696849..4120af086160 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -93,4 +93,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* _XTENSA_SOCKET_H */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 75e94eaa228b..bbfceb756452 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -128,7 +128,11 @@ struct bpf_prog_aux {
struct work_struct work;
};
+#ifdef CONFIG_BPF_SYSCALL
void bpf_prog_put(struct bpf_prog *prog);
+#else
+static inline void bpf_prog_put(struct bpf_prog *prog) {}
+#endif
struct bpf_prog *bpf_prog_get(u32 ufd);
/* verify correctness of eBPF program */
int bpf_check(struct bpf_prog *fp, union bpf_attr *attr);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index ca95abd2bed1..caac2087a4d5 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -381,6 +381,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
void bpf_prog_destroy(struct bpf_prog *fp);
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int sk_attach_bpf(u32 ufd, struct sock *sk);
int sk_detach_filter(struct sock *sk);
int bpf_check_classic(const struct sock_filter *filter, unsigned int flen);
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index f541ccefd4ac..5c15c2a5c123 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -84,4 +84,7 @@
#define SO_INCOMING_CPU 49
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/filter.c b/net/core/filter.c
index 647b12265e18..8cc3c03078b3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -44,6 +44,7 @@
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
#include <linux/if_vlan.h>
+#include <linux/bpf.h>
/**
* sk_filter - run a packet through a socket filter
@@ -813,8 +814,12 @@ static void bpf_release_orig_filter(struct bpf_prog *fp)
static void __bpf_prog_release(struct bpf_prog *prog)
{
- bpf_release_orig_filter(prog);
- bpf_prog_free(prog);
+ if (prog->aux->prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
+ bpf_prog_put(prog);
+ } else {
+ bpf_release_orig_filter(prog);
+ bpf_prog_free(prog);
+ }
}
static void __sk_filter_release(struct sk_filter *fp)
@@ -1088,6 +1093,94 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
}
EXPORT_SYMBOL_GPL(sk_attach_filter);
+#ifdef CONFIG_BPF_SYSCALL
+int sk_attach_bpf(u32 ufd, struct sock *sk)
+{
+ struct sk_filter *fp, *old_fp;
+ struct bpf_prog *prog;
+
+ if (sock_flag(sk, SOCK_FILTER_LOCKED))
+ return -EPERM;
+
+ prog = bpf_prog_get(ufd);
+ if (!prog)
+ return -EINVAL;
+
+ if (prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
+ /* valid fd, but invalid program type */
+ bpf_prog_put(prog);
+ return -EINVAL;
+ }
+
+ fp = kmalloc(sizeof(*fp), GFP_KERNEL);
+ if (!fp) {
+ bpf_prog_put(prog);
+ return -ENOMEM;
+ }
+ fp->prog = prog;
+
+ atomic_set(&fp->refcnt, 0);
+
+ if (!sk_filter_charge(sk, fp)) {
+ __sk_filter_release(fp);
+ return -ENOMEM;
+ }
+
+ old_fp = rcu_dereference_protected(sk->sk_filter,
+ sock_owned_by_user(sk));
+ rcu_assign_pointer(sk->sk_filter, fp);
+
+ if (old_fp)
+ sk_filter_uncharge(sk, old_fp);
+
+ return 0;
+}
+
+/* allow socket filters to call
+ * bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem()
+ */
+static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_map_lookup_elem:
+ return &bpf_map_lookup_elem_proto;
+ case BPF_FUNC_map_update_elem:
+ return &bpf_map_update_elem_proto;
+ case BPF_FUNC_map_delete_elem:
+ return &bpf_map_delete_elem_proto;
+ default:
+ return NULL;
+ }
+}
+
+static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+ /* skb fields cannot be accessed yet */
+ return false;
+}
+
+static struct bpf_verifier_ops sock_filter_ops = {
+ .get_func_proto = sock_filter_func_proto,
+ .is_valid_access = sock_filter_is_valid_access,
+};
+
+static struct bpf_prog_type_list tl = {
+ .ops = &sock_filter_ops,
+ .type = BPF_PROG_TYPE_SOCKET_FILTER,
+};
+
+static int __init register_sock_filter_ops(void)
+{
+ bpf_register_prog_type(&tl);
+ return 0;
+}
+late_initcall(register_sock_filter_ops);
+#else
+int sk_attach_bpf(u32 ufd, struct sock *sk)
+{
+ return -EOPNOTSUPP;
+}
+#endif
int sk_detach_filter(struct sock *sk)
{
int ret = -ENOENT;
diff --git a/net/core/sock.c b/net/core/sock.c
index 0725cf0cb685..9a56b2000c3f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -888,6 +888,19 @@ set_rcvbuf:
}
break;
+ case SO_ATTACH_BPF:
+ ret = -EINVAL;
+ if (optlen == sizeof(u32)) {
+ u32 ufd;
+
+ ret = -EFAULT;
+ if (copy_from_user(&ufd, optval, sizeof(ufd)))
+ break;
+
+ ret = sk_attach_bpf(ufd, sk);
+ }
+ break;
+
case SO_DETACH_FILTER:
ret = sk_detach_filter(sk);
break;
--
1.7.9.5
^ permalink raw reply related
* [PATCH net-next 6/6] samples: bpf: large eBPF program in C
From: Alexei Starovoitov @ 2014-11-27 5:42 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Andy Lutomirski, Daniel Borkmann,
Hannes Frederic Sowa, Eric Dumazet, linux-api, netdev,
linux-kernel
In-Reply-To: <1417066951-1999-1-git-send-email-ast@plumgrid.com>
sockex2_kern.c is purposefully large eBPF program in C.
llvm compiles ~200 lines of C code into ~300 eBPF instructions.
It's similar to __skb_flow_dissect() to demonstrate that complex packet parsing
can be done by eBPF.
Then it uses (struct flow_keys)->dst IP address (or hash of ipv6 dst) to keep
stats of number of packets per IP.
User space loads eBPF program, attaches it to loopback interface and prints
dest_ip->#packets stats every second.
Usage:
$sudo samples/bpf/sockex2
ip 127.0.0.1 count 19
ip 127.0.0.1 count 178115
ip 127.0.0.1 count 369437
ip 127.0.0.1 count 559841
ip 127.0.0.1 count 750539
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
samples/bpf/Makefile | 4 +
samples/bpf/sockex2_kern.c | 215 ++++++++++++++++++++++++++++++++++++++++++++
samples/bpf/sockex2_user.c | 44 +++++++++
3 files changed, 263 insertions(+)
create mode 100644 samples/bpf/sockex2_kern.c
create mode 100644 samples/bpf/sockex2_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 770d145186c3..b5b3600dcdf5 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -5,20 +5,24 @@ obj- := dummy.o
hostprogs-y := test_verifier test_maps
hostprogs-y += sock_example
hostprogs-y += sockex1
+hostprogs-y += sockex2
test_verifier-objs := test_verifier.o libbpf.o
test_maps-objs := test_maps.o libbpf.o
sock_example-objs := sock_example.o libbpf.o
sockex1-objs := bpf_load.o libbpf.o sockex1_user.o
+sockex2-objs := bpf_load.o libbpf.o sockex2_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
always += sockex1_kern.o
+always += sockex2_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
HOSTLOADLIBES_sockex1 += -lelf
+HOSTLOADLIBES_sockex2 += -lelf
# point this to your LLVM backend with bpf support
LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc
diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c
new file mode 100644
index 000000000000..6f0135f0f217
--- /dev/null
+++ b/samples/bpf/sockex2_kern.c
@@ -0,0 +1,215 @@
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+#include <uapi/linux/in.h>
+#include <uapi/linux/if.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/if_tunnel.h>
+#define IP_MF 0x2000
+#define IP_OFFSET 0x1FFF
+
+struct vlan_hdr {
+ __be16 h_vlan_TCI;
+ __be16 h_vlan_encapsulated_proto;
+};
+
+struct flow_keys {
+ __be32 src;
+ __be32 dst;
+ union {
+ __be32 ports;
+ __be16 port16[2];
+ };
+ __u16 thoff;
+ __u8 ip_proto;
+};
+
+static inline int proto_ports_offset(__u64 proto)
+{
+ switch (proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_DCCP:
+ case IPPROTO_ESP:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDPLITE:
+ return 0;
+ case IPPROTO_AH:
+ return 4;
+ default:
+ return 0;
+ }
+}
+
+static inline int ip_is_fragment(struct sk_buff *ctx, __u64 nhoff)
+{
+ return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off))
+ & (IP_MF | IP_OFFSET);
+}
+
+static inline __u32 ipv6_addr_hash(struct sk_buff *ctx, __u64 off)
+{
+ __u64 w0 = load_word(ctx, off);
+ __u64 w1 = load_word(ctx, off + 4);
+ __u64 w2 = load_word(ctx, off + 8);
+ __u64 w3 = load_word(ctx, off + 12);
+
+ return (__u32)(w0 ^ w1 ^ w2 ^ w3);
+}
+
+static inline __u64 parse_ip(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
+ struct flow_keys *flow)
+{
+ __u64 verlen;
+
+ if (unlikely(ip_is_fragment(skb, nhoff)))
+ *ip_proto = 0;
+ else
+ *ip_proto = load_byte(skb, nhoff + offsetof(struct iphdr, protocol));
+
+ if (*ip_proto != IPPROTO_GRE) {
+ flow->src = load_word(skb, nhoff + offsetof(struct iphdr, saddr));
+ flow->dst = load_word(skb, nhoff + offsetof(struct iphdr, daddr));
+ }
+
+ verlen = load_byte(skb, nhoff + 0/*offsetof(struct iphdr, ihl)*/);
+ if (likely(verlen == 0x45))
+ nhoff += 20;
+ else
+ nhoff += (verlen & 0xF) << 2;
+
+ return nhoff;
+}
+
+static inline __u64 parse_ipv6(struct sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
+ struct flow_keys *flow)
+{
+ *ip_proto = load_byte(skb,
+ nhoff + offsetof(struct ipv6hdr, nexthdr));
+ flow->src = ipv6_addr_hash(skb,
+ nhoff + offsetof(struct ipv6hdr, saddr));
+ flow->dst = ipv6_addr_hash(skb,
+ nhoff + offsetof(struct ipv6hdr, daddr));
+ nhoff += sizeof(struct ipv6hdr);
+
+ return nhoff;
+}
+
+static inline bool flow_dissector(struct sk_buff *skb, struct flow_keys *flow)
+{
+ __u64 nhoff = ETH_HLEN;
+ __u64 ip_proto;
+ __u64 proto = load_half(skb, 12);
+ int poff;
+
+ if (proto == ETH_P_8021AD) {
+ proto = load_half(skb, nhoff + offsetof(struct vlan_hdr,
+ h_vlan_encapsulated_proto));
+ nhoff += sizeof(struct vlan_hdr);
+ }
+
+ if (proto == ETH_P_8021Q) {
+ proto = load_half(skb, nhoff + offsetof(struct vlan_hdr,
+ h_vlan_encapsulated_proto));
+ nhoff += sizeof(struct vlan_hdr);
+ }
+
+ if (likely(proto == ETH_P_IP))
+ nhoff = parse_ip(skb, nhoff, &ip_proto, flow);
+ else if (proto == ETH_P_IPV6)
+ nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow);
+ else
+ return false;
+
+ switch (ip_proto) {
+ case IPPROTO_GRE: {
+ struct gre_hdr {
+ __be16 flags;
+ __be16 proto;
+ };
+
+ __u64 gre_flags = load_half(skb,
+ nhoff + offsetof(struct gre_hdr, flags));
+ __u64 gre_proto = load_half(skb,
+ nhoff + offsetof(struct gre_hdr, proto));
+
+ if (gre_flags & (GRE_VERSION|GRE_ROUTING))
+ break;
+
+ proto = gre_proto;
+ nhoff += 4;
+ if (gre_flags & GRE_CSUM)
+ nhoff += 4;
+ if (gre_flags & GRE_KEY)
+ nhoff += 4;
+ if (gre_flags & GRE_SEQ)
+ nhoff += 4;
+
+ if (proto == ETH_P_8021Q) {
+ proto = load_half(skb,
+ nhoff + offsetof(struct vlan_hdr,
+ h_vlan_encapsulated_proto));
+ nhoff += sizeof(struct vlan_hdr);
+ }
+
+ if (proto == ETH_P_IP)
+ nhoff = parse_ip(skb, nhoff, &ip_proto, flow);
+ else if (proto == ETH_P_IPV6)
+ nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow);
+ else
+ return false;
+ break;
+ }
+ case IPPROTO_IPIP:
+ nhoff = parse_ip(skb, nhoff, &ip_proto, flow);
+ break;
+ case IPPROTO_IPV6:
+ nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow);
+ break;
+ default:
+ break;
+ }
+
+ flow->ip_proto = ip_proto;
+ poff = proto_ports_offset(ip_proto);
+ if (poff >= 0) {
+ nhoff += poff;
+ flow->ports = load_word(skb, nhoff);
+ }
+
+ flow->thoff = (__u16) nhoff;
+
+ return true;
+}
+
+struct bpf_map_def SEC("maps") hash_map = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(__be32),
+ .value_size = sizeof(long),
+ .max_entries = 1024,
+};
+
+SEC("socket2")
+int bpf_prog2(struct sk_buff *skb)
+{
+ struct flow_keys flow;
+ long *value;
+ u32 key;
+
+ if (!flow_dissector(skb, &flow))
+ return 0;
+
+ key = flow.dst;
+ value = bpf_map_lookup_elem(&hash_map, &key);
+ if (value) {
+ __sync_fetch_and_add(value, 1);
+ } else {
+ long val = 1;
+
+ bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY);
+ }
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c
new file mode 100644
index 000000000000..d2d5f5a790d3
--- /dev/null
+++ b/samples/bpf/sockex2_user.c
@@ -0,0 +1,44 @@
+#include <stdio.h>
+#include <assert.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+#include <unistd.h>
+#include <arpa/inet.h>
+
+int main(int ac, char **argv)
+{
+ char filename[256];
+ FILE *f;
+ int i, sock;
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ sock = open_raw_sock("lo");
+
+ assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, prog_fd,
+ sizeof(prog_fd[0])) == 0);
+
+ f = popen("ping -c5 localhost", "r");
+ (void) f;
+
+ for (i = 0; i < 5; i++) {
+ int key = 0, next_key;
+ long long value;
+
+ while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
+ bpf_lookup_elem(map_fd[0], &next_key, &value);
+ printf("ip %s count %lld\n",
+ inet_ntoa((struct in_addr){htonl(next_key)}),
+ value);
+ key = next_key;
+ }
+ sleep(1);
+ }
+ return 0;
+}
--
1.7.9.5
^ permalink raw reply related
* [PATCH net-next 3/6] samples: bpf: example of stateful socket filtering
From: Alexei Starovoitov @ 2014-11-27 5:42 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Andy Lutomirski, Daniel Borkmann,
Hannes Frederic Sowa, Eric Dumazet, linux-api, netdev,
linux-kernel
In-Reply-To: <1417066951-1999-1-git-send-email-ast@plumgrid.com>
this socket filter example does:
- creates arraymap in kernel with key 4 bytes and value 8 bytes
- loads eBPF program:
r0 = skb[14 + 9]; // load one byte of ip->proto
*(u32*)(fp - 4) = r0;
value = bpf_map_lookup_elem(map_fd, fp - 4);
if (value)
(*(u64*)value) += 1;
- attaches this program to raw socket
- every second user space reads map[tcp], map[udp], map[icmp] to see
how many packets of given protocol were seen on loopback interface
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
samples/bpf/Makefile | 2 +
samples/bpf/libbpf.c | 28 +++++++++++++
samples/bpf/libbpf.h | 13 ++++++
samples/bpf/sock_example.c | 97 ++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 140 insertions(+)
create mode 100644 samples/bpf/sock_example.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 0718d9ce4619..f46d3492d032 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -3,9 +3,11 @@ obj- := dummy.o
# List of programs to build
hostprogs-y := test_verifier test_maps
+hostprogs-y += sock_example
test_verifier-objs := test_verifier.o libbpf.o
test_maps-objs := test_maps.o libbpf.o
+sock_example-objs := sock_example.o libbpf.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c
index 17bb520eb57f..46d50b7ddf79 100644
--- a/samples/bpf/libbpf.c
+++ b/samples/bpf/libbpf.c
@@ -7,6 +7,10 @@
#include <linux/netlink.h>
#include <linux/bpf.h>
#include <errno.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <linux/if_packet.h>
+#include <arpa/inet.h>
#include "libbpf.h"
static __u64 ptr_to_u64(void *ptr)
@@ -93,3 +97,27 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
}
+
+int open_raw_sock(const char *name)
+{
+ struct sockaddr_ll sll;
+ int sock;
+
+ sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL));
+ if (sock < 0) {
+ printf("cannot create raw socket\n");
+ return -1;
+ }
+
+ memset(&sll, 0, sizeof(sll));
+ sll.sll_family = AF_PACKET;
+ sll.sll_ifindex = if_nametoindex(name);
+ sll.sll_protocol = htons(ETH_P_ALL);
+ if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) {
+ printf("bind to %s: %s\n", name, strerror(errno));
+ close(sock);
+ return -1;
+ }
+
+ return sock;
+}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index f8678e5f48bf..cc62ad4d95de 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -99,6 +99,16 @@ extern char bpf_log_buf[LOG_BUF_SIZE];
BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
+
+#define BPF_LD_ABS(SIZE, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \
@@ -169,4 +179,7 @@ extern char bpf_log_buf[LOG_BUF_SIZE];
.off = 0, \
.imm = 0 })
+/* create RAW socket and bind to interface 'name' */
+int open_raw_sock(const char *name);
+
#endif
diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c
new file mode 100644
index 000000000000..d74b58523458
--- /dev/null
+++ b/samples/bpf/sock_example.c
@@ -0,0 +1,97 @@
+/* eBPF example program:
+ * - creates arraymap in kernel with key 4 bytes and value 8 bytes
+ *
+ * - loads eBPF program:
+ * r0 = skb[14 + 9]; // load one byte of ip->proto
+ * *(u32*)(fp - 4) = r0;
+ * value = bpf_map_lookup_elem(map_fd, fp - 4);
+ * if (value)
+ * (*(u64*)value) += 1;
+ *
+ * - attaches this program to eth0 raw socket
+ *
+ * - every second user space reads map[tcp], map[udp], map[icmp] to see
+ * how many packets of given protocol were seen on eth0
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <assert.h>
+#include <linux/bpf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include "libbpf.h"
+
+static int test_sock(void)
+{
+ int sock = -1, map_fd, prog_fd, i, key;
+ long long value = 0, tcp_cnt, udp_cnt, icmp_cnt;
+
+ map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value),
+ 256);
+ if (map_fd < 0) {
+ printf("failed to create map '%s'\n", strerror(errno));
+ goto cleanup;
+ }
+
+ struct bpf_insn prog[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_B, 14 + 9 /* R0 = ip->proto */),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+ BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */
+ BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+ BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */
+ BPF_EXIT_INSN(),
+ };
+
+ prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog, sizeof(prog),
+ "GPL");
+ if (prog_fd < 0) {
+ printf("failed to load prog '%s'\n", strerror(errno));
+ goto cleanup;
+ }
+
+ sock = open_raw_sock("lo");
+
+ if (setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd,
+ sizeof(prog_fd)) < 0) {
+ printf("setsockopt %s\n", strerror(errno));
+ goto cleanup;
+ }
+
+ for (i = 0; i < 10; i++) {
+ key = IPPROTO_TCP;
+ assert(bpf_lookup_elem(map_fd, &key, &tcp_cnt) == 0);
+
+ key = IPPROTO_UDP;
+ assert(bpf_lookup_elem(map_fd, &key, &udp_cnt) == 0);
+
+ key = IPPROTO_ICMP;
+ assert(bpf_lookup_elem(map_fd, &key, &icmp_cnt) == 0);
+
+ printf("TCP %lld UDP %lld ICMP %lld packets\n",
+ tcp_cnt, udp_cnt, icmp_cnt);
+ sleep(1);
+ }
+
+cleanup:
+ /* maps, programs, raw sockets will auto cleanup on process exit */
+ return 0;
+}
+
+int main(void)
+{
+ FILE *f;
+
+ f = popen("ping -c5 localhost", "r");
+ (void)f;
+
+ return test_sock();
+}
--
1.7.9.5
^ permalink raw reply related
* [PATCH net-next 4/6] samples: bpf: elf_bpf file loader
From: Alexei Starovoitov @ 2014-11-27 5:42 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Andy Lutomirski, Daniel Borkmann,
Hannes Frederic Sowa, Eric Dumazet, linux-api, netdev,
linux-kernel
In-Reply-To: <1417066951-1999-1-git-send-email-ast@plumgrid.com>
simple .o parser and loader using BPF syscall.
.o is a standard ELF generated by LLVM backend
It parses elf file compiled by llvm .c->.o
- parses 'maps' section and creates maps via BPF syscall
- parses 'license' section and passes it to syscall
- parses elf relocations for BPF maps and adjusts BPF_LD_IMM64 insns
by storing map_fd into insn->imm and marking such insns as BPF_PSEUDO_MAP_FD
- loads eBPF programs via BPF syscall
One ELF file can contain multiple BPF programs.
int load_bpf_file(char *path);
populates prog_fd[] and map_fd[] with FDs received from bpf syscall
bpf_helpers.h - helper functions available to eBPF programs written in C
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
These helpers and loader are done as separate patch to make eBPF C examples
(that follow in the next patches) to focus on demonstrating programming
of eBPF in restricted C.
---
samples/bpf/bpf_helpers.h | 40 +++++++++
samples/bpf/bpf_load.c | 203 +++++++++++++++++++++++++++++++++++++++++++++
samples/bpf/bpf_load.h | 24 ++++++
3 files changed, 267 insertions(+)
create mode 100644 samples/bpf/bpf_helpers.h
create mode 100644 samples/bpf/bpf_load.c
create mode 100644 samples/bpf/bpf_load.h
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
new file mode 100644
index 000000000000..ca0333146006
--- /dev/null
+++ b/samples/bpf/bpf_helpers.h
@@ -0,0 +1,40 @@
+#ifndef __BPF_HELPERS_H
+#define __BPF_HELPERS_H
+
+/* helper macro to place programs, maps, license in
+ * different sections in elf_bpf file. Section names
+ * are interpreted by elf_bpf loader
+ */
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+/* helper functions called from eBPF programs written in C */
+static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+ (void *) BPF_FUNC_map_lookup_elem;
+static int (*bpf_map_update_elem)(void *map, void *key, void *value,
+ unsigned long long flags) =
+ (void *) BPF_FUNC_map_update_elem;
+static int (*bpf_map_delete_elem)(void *map, void *key) =
+ (void *) BPF_FUNC_map_delete_elem;
+
+/* llvm builtin functions that eBPF C program may use to
+ * emit BPF_LD_ABS and BPF_LD_IND instructions
+ */
+struct sk_buff;
+unsigned long long load_byte(void *skb,
+ unsigned long long off) asm("llvm.bpf.load.byte");
+unsigned long long load_half(void *skb,
+ unsigned long long off) asm("llvm.bpf.load.half");
+unsigned long long load_word(void *skb,
+ unsigned long long off) asm("llvm.bpf.load.word");
+
+/* a helper structure used by eBPF C program
+ * to describe map attributes to elf_bpf loader
+ */
+struct bpf_map_def {
+ unsigned int type;
+ unsigned int key_size;
+ unsigned int value_size;
+ unsigned int max_entries;
+};
+
+#endif
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
new file mode 100644
index 000000000000..1831d236382b
--- /dev/null
+++ b/samples/bpf/bpf_load.c
@@ -0,0 +1,203 @@
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <libelf.h>
+#include <gelf.h>
+#include <errno.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include "libbpf.h"
+#include "bpf_helpers.h"
+#include "bpf_load.h"
+
+static char license[128];
+static bool processed_sec[128];
+int map_fd[MAX_MAPS];
+int prog_fd[MAX_PROGS];
+int prog_cnt;
+
+static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
+{
+ int fd;
+ bool is_socket = strncmp(event, "socket", 6) == 0;
+
+ if (!is_socket)
+ /* tracing events tbd */
+ return -1;
+
+ fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER,
+ prog, size, license);
+
+ if (fd < 0) {
+ printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
+ return -1;
+ }
+
+ prog_fd[prog_cnt++] = fd;
+
+ return 0;
+}
+
+static int load_maps(struct bpf_map_def *maps, int len)
+{
+ int i;
+
+ for (i = 0; i < len / sizeof(struct bpf_map_def); i++) {
+
+ map_fd[i] = bpf_create_map(maps[i].type,
+ maps[i].key_size,
+ maps[i].value_size,
+ maps[i].max_entries);
+ if (map_fd[i] < 0)
+ return 1;
+ }
+ return 0;
+}
+
+static int get_sec(Elf *elf, int i, GElf_Ehdr *ehdr, char **shname,
+ GElf_Shdr *shdr, Elf_Data **data)
+{
+ Elf_Scn *scn;
+
+ scn = elf_getscn(elf, i);
+ if (!scn)
+ return 1;
+
+ if (gelf_getshdr(scn, shdr) != shdr)
+ return 2;
+
+ *shname = elf_strptr(elf, ehdr->e_shstrndx, shdr->sh_name);
+ if (!*shname || !shdr->sh_size)
+ return 3;
+
+ *data = elf_getdata(scn, 0);
+ if (!*data || elf_getdata(scn, *data) != NULL)
+ return 4;
+
+ return 0;
+}
+
+static int parse_relo_and_apply(Elf_Data *data, Elf_Data *symbols,
+ GElf_Shdr *shdr, struct bpf_insn *insn)
+{
+ int i, nrels;
+
+ nrels = shdr->sh_size / shdr->sh_entsize;
+
+ for (i = 0; i < nrels; i++) {
+ GElf_Sym sym;
+ GElf_Rel rel;
+ unsigned int insn_idx;
+
+ gelf_getrel(data, i, &rel);
+
+ insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+
+ gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym);
+
+ if (insn[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
+ printf("invalid relo for insn[%d].code 0x%x\n",
+ insn_idx, insn[insn_idx].code);
+ return 1;
+ }
+ insn[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+ insn[insn_idx].imm = map_fd[sym.st_value / sizeof(struct bpf_map_def)];
+ }
+
+ return 0;
+}
+
+int load_bpf_file(char *path)
+{
+ int fd, i;
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr, shdr_prog;
+ Elf_Data *data, *data_prog, *symbols = NULL;
+ char *shname, *shname_prog;
+
+ if (elf_version(EV_CURRENT) == EV_NONE)
+ return 1;
+
+ fd = open(path, O_RDONLY, 0);
+ if (fd < 0)
+ return 1;
+
+ elf = elf_begin(fd, ELF_C_READ, NULL);
+
+ if (!elf)
+ return 1;
+
+ if (gelf_getehdr(elf, &ehdr) != &ehdr)
+ return 1;
+
+ /* scan over all elf sections to get license and map info */
+ for (i = 1; i < ehdr.e_shnum; i++) {
+
+ if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
+ continue;
+
+ if (0) /* helpful for llvm debugging */
+ printf("section %d:%s data %p size %zd link %d flags %d\n",
+ i, shname, data->d_buf, data->d_size,
+ shdr.sh_link, (int) shdr.sh_flags);
+
+ if (strcmp(shname, "license") == 0) {
+ processed_sec[i] = true;
+ memcpy(license, data->d_buf, data->d_size);
+ } else if (strcmp(shname, "maps") == 0) {
+ processed_sec[i] = true;
+ if (load_maps(data->d_buf, data->d_size))
+ return 1;
+ } else if (shdr.sh_type == SHT_SYMTAB) {
+ symbols = data;
+ }
+ }
+
+ /* load programs that need map fixup (relocations) */
+ for (i = 1; i < ehdr.e_shnum; i++) {
+
+ if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
+ continue;
+ if (shdr.sh_type == SHT_REL) {
+ struct bpf_insn *insns;
+
+ if (get_sec(elf, shdr.sh_info, &ehdr, &shname_prog,
+ &shdr_prog, &data_prog))
+ continue;
+
+ insns = (struct bpf_insn *) data_prog->d_buf;
+
+ processed_sec[shdr.sh_info] = true;
+ processed_sec[i] = true;
+
+ if (parse_relo_and_apply(data, symbols, &shdr, insns))
+ continue;
+
+ if (memcmp(shname_prog, "events/", 7) == 0 ||
+ memcmp(shname_prog, "socket", 6) == 0)
+ load_and_attach(shname_prog, insns, data_prog->d_size);
+ }
+ }
+
+ /* load programs that don't use maps */
+ for (i = 1; i < ehdr.e_shnum; i++) {
+
+ if (processed_sec[i])
+ continue;
+
+ if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
+ continue;
+
+ if (memcmp(shname, "events/", 7) == 0 ||
+ memcmp(shname, "socket", 6) == 0)
+ load_and_attach(shname, data->d_buf, data->d_size);
+ }
+
+ close(fd);
+ return 0;
+}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
new file mode 100644
index 000000000000..27789a34f5e6
--- /dev/null
+++ b/samples/bpf/bpf_load.h
@@ -0,0 +1,24 @@
+#ifndef __BPF_LOAD_H
+#define __BPF_LOAD_H
+
+#define MAX_MAPS 32
+#define MAX_PROGS 32
+
+extern int map_fd[MAX_MAPS];
+extern int prog_fd[MAX_PROGS];
+
+/* parses elf file compiled by llvm .c->.o
+ * . parses 'maps' section and creates maps via BPF syscall
+ * . parses 'license' section and passes it to syscall
+ * . parses elf relocations for BPF maps and adjusts BPF_LD_IMM64 insns by
+ * storing map_fd into insn->imm and marking such insns as BPF_PSEUDO_MAP_FD
+ * . loads eBPF programs via BPF syscall
+ *
+ * One ELF file can contain multiple BPF programs which will be loaded
+ * and their FDs stored stored in prog_fd array
+ *
+ * returns zero on success
+ */
+int load_bpf_file(char *path);
+
+#endif
--
1.7.9.5
^ permalink raw reply related
* [PATCH net-next 5/6] samples: bpf: trivial eBPF program in C
From: Alexei Starovoitov @ 2014-11-27 5:42 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Andy Lutomirski, Daniel Borkmann,
Hannes Frederic Sowa, Eric Dumazet, linux-api, netdev,
linux-kernel
In-Reply-To: <1417066951-1999-1-git-send-email-ast@plumgrid.com>
this example does the same task as previous socket example
in assembler, but this one does it in C.
eBPF program in kernel does:
int index = load_byte(skb, 14 + 9); /* ip_proto */
long *value;
value = bpf_map_lookup_elem(&my_map, &index);
if (value)
__sync_fetch_and_add(value, 1);
Corresponding user space reads map[tcp], map[udp], map[icmp]
and prints protocol stats every second
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
samples/bpf/Makefile | 14 +++++++++++++
samples/bpf/libbpf.h | 2 +-
samples/bpf/sockex1_kern.c | 23 +++++++++++++++++++++
samples/bpf/sockex1_user.c | 49 ++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 87 insertions(+), 1 deletion(-)
create mode 100644 samples/bpf/sockex1_kern.c
create mode 100644 samples/bpf/sockex1_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index f46d3492d032..770d145186c3 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -4,12 +4,26 @@ obj- := dummy.o
# List of programs to build
hostprogs-y := test_verifier test_maps
hostprogs-y += sock_example
+hostprogs-y += sockex1
test_verifier-objs := test_verifier.o libbpf.o
test_maps-objs := test_maps.o libbpf.o
sock_example-objs := sock_example.o libbpf.o
+sockex1-objs := bpf_load.o libbpf.o sockex1_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
+always += sockex1_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
+
+HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
+HOSTLOADLIBES_sockex1 += -lelf
+
+# point this to your LLVM backend with bpf support
+LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc
+
+%.o: %.c
+ clang $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) \
+ -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
+ -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index cc62ad4d95de..58c5fe1bdba1 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -15,7 +15,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, int insn_len,
const char *license);
-#define LOG_BUF_SIZE 8192
+#define LOG_BUF_SIZE 65536
extern char bpf_log_buf[LOG_BUF_SIZE];
/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c
new file mode 100644
index 000000000000..e662779467de
--- /dev/null
+++ b/samples/bpf/sockex1_kern.c
@@ -0,0 +1,23 @@
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") my_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(long),
+ .max_entries = 256,
+};
+
+SEC("socket1")
+int bpf_prog1(struct sk_buff *skb)
+{
+ int index = load_byte(skb, 14 + 9);
+ long *value;
+
+ value = bpf_map_lookup_elem(&my_map, &index);
+ if (value)
+ __sync_fetch_and_add(value, 1);
+
+ return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c
new file mode 100644
index 000000000000..34a443ff3831
--- /dev/null
+++ b/samples/bpf/sockex1_user.c
@@ -0,0 +1,49 @@
+#include <stdio.h>
+#include <assert.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+#include <unistd.h>
+#include <arpa/inet.h>
+
+int main(int ac, char **argv)
+{
+ char filename[256];
+ FILE *f;
+ int i, sock;
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ sock = open_raw_sock("lo");
+
+ assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, prog_fd,
+ sizeof(prog_fd[0])) == 0);
+
+ f = popen("ping -c5 localhost", "r");
+ (void) f;
+
+ for (i = 0; i < 5; i++) {
+ long long tcp_cnt, udp_cnt, icmp_cnt;
+ int key;
+
+ key = IPPROTO_TCP;
+ assert(bpf_lookup_elem(map_fd[0], &key, &tcp_cnt) == 0);
+
+ key = IPPROTO_UDP;
+ assert(bpf_lookup_elem(map_fd[0], &key, &udp_cnt) == 0);
+
+ key = IPPROTO_ICMP;
+ assert(bpf_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0);
+
+ printf("TCP %lld UDP %lld ICMP %lld packets\n",
+ tcp_cnt, udp_cnt, icmp_cnt);
+ sleep(1);
+ }
+
+ return 0;
+}
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH v2 03/19] selftests: add install target to enable installing selftests
From: Masami Hiramatsu @ 2014-11-27 5:45 UTC (permalink / raw)
To: Shuah Khan
Cc: gregkh, akpm, mmarek, davem, keescook, tranmanphong, dh.herrmann,
hughd, bobby.prani, ebiederm, serge.hallyn, linux-kbuild,
linux-kernel, linux-api, netdev, yrl.pp-manager.tt@hitachi.com
In-Reply-To: <5e33b40696debde24fd04f6711e795a8860b7aee.1415735831.git.shuahkh@osg.samsung.com>
(2014/11/12 5:27), Shuah Khan wrote:
> Add a new make target to enable installing selftests. This
> new target will call install targets for the tests that are
> specified in INSTALL_TARGETS. During install, a script is
> generated to run tests that are installed. This script will
> be installed in the selftest install directory. Individual
> test Makefiles are changed to add to the script. This will
> allow new tests to add install and run test commands to the
> generated kselftest script. run_tests target runs the
> generated kselftest script to run tests when it is initiated
> from from "make kselftest" from top level source directory.
>
> Approach:
>
> make kselftest_target:
> -- exports kselftest INSTALL_KSFT_PATH
> default $(INSTALL_MOD_PATH)/lib/kselftest/$(KERNELRELEASE)
> -- exports path for ksefltest.sh
> -- runs selftests make install target:
>
> selftests make install target
> -- creates kselftest.sh script in install install dir
> -- runs install targets for all INSTALL_TARGETS
> (Note: ftrace and powerpc aren't included in INSTALL_TARGETS,
> to not add more content to patch v1 series. This work
> will happen soon. In this series these two targets are
> run after running the generated kselftest script, without
> any regression in the way these tests are run with
> "make kselftest" prior to this work.)
> -- install target can be run only from top level source dir.
>
> Individual test make install targets:
> -- install test programs and/or scripts in install dir
> -- append to the ksefltest.sh file to add commands to run test
> -- install target can be run only from top level source dir.
>
> Adds the following new ways to initiate selftests:
> -- Installing and running kselftest from install directory
> by running "make kselftest"
> -- Running kselftest script from install directory
>
> Maintains the following ways to run tests:
> -- make -C tools/testing/selftests run_tests
> -- make -C tools/testing/selftests TARGETS=target run_tests
> Ability specify targets: e.g TARGETS=net
> -- make run_tests from tools/testing/selftests
> -- make run_tests from individual test directories:
> e.g: make run_tests in tools/testing/selftests/breakpoints
>
> Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
> ---
> tools/testing/selftests/Makefile | 31 ++++++++++++++++++++++++++++++-
> 1 file changed, 30 insertions(+), 1 deletion(-)
>
> diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
> index 45f145c..b9bdc1d 100644
> --- a/tools/testing/selftests/Makefile
> +++ b/tools/testing/selftests/Makefile
> @@ -16,6 +16,10 @@ TARGETS += sysctl
> TARGETS += firmware
> TARGETS += ftrace
>
> +INSTALL_TARGETS = breakpoints cpu-hotplug efivarfs firmware ipc
> +INSTALL_TARGETS += kcmp memfd memory-hotplug mqueue mount net
> +INSTALL_TARGETS += ptrace sysctl timers user vm
> +
> TARGETS_HOTPLUG = cpu-hotplug
> TARGETS_HOTPLUG += memory-hotplug
>
I think KSELFTEST itself should be defined here, since that is not
a parameter.
> @@ -24,10 +28,35 @@ all:
> make -C $$TARGET; \
> done;
>
> -run_tests: all
> +install:
> +ifdef INSTALL_KSFT_PATH
> + make all
> + @echo #!/bin/sh\n# Kselftest Run Tests .... >> $(KSELFTEST)
> + @echo # This file is generated during kselftest_install >> $(KSELFTEST)
> + @echo # Please don't change it !!\n >> $(KSELFTEST)
> + @echo echo ============================== >> $(KSELFTEST)
> + for TARGET in $(INSTALL_TARGETS); do \
> + echo Installing $$TARGET; \
> + make -C $$TARGET install; \
Please pass O= option and others here.
> + done;
> + chmod +x $(KSELFTEST)
> +else
> + @echo Run make kselftest_install in top level source directory
> +endif
> +
> +run_tests:
> +ifdef INSTALL_KSFT_PATH
> + @cd $(INSTALL_KSFT_PATH); ./kselftest.sh; cd -
We'd better use some macro instead of ./kselftest.sh?
Thank you,
> +# TODO: include ftrace and powerpc in install targets
> + for TARGET in ftrace powerpc; do \
> + make -C $$TARGET run_tests; \
> + done;
> +else
> + make all
> for TARGET in $(TARGETS); do \
> make -C $$TARGET run_tests; \
> done;
> +endif
>
> hotplug:
> for TARGET in $(TARGETS_HOTPLUG); do \
>
--
Masami HIRAMATSU
Software Platform Research Dept. Linux Technology Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@hitachi.com
^ permalink raw reply
* Re: [PATCH v2 11/19] selftests/memory-hotplug: add install target to enable installing test
From: Masami Hiramatsu @ 2014-11-27 5:49 UTC (permalink / raw)
To: Shuah Khan
Cc: gregkh, akpm, mmarek, davem, keescook, tranmanphong, dh.herrmann,
hughd, bobby.prani, ebiederm, serge.hallyn, linux-kbuild,
linux-kernel, linux-api, netdev, yrl.pp-manager.tt@hitachi.com
In-Reply-To: <8cdb2abb6eaa794801548e04ee6b9f403778e126.1415735831.git.shuahkh@osg.samsung.com>
(2014/11/12 5:27), Shuah Khan wrote:
> Add a new make target to enable installing test. This target
> installs test in the kselftest install location and add to the
> kselftest script to run the test. Install target can be run
> only from top level source dir.
>
> Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
> ---
> tools/testing/selftests/memory-hotplug/Makefile | 17 +-
> .../selftests/memory-hotplug/mem-on-off-test.sh | 238 +++++++++++++++++++++
> .../selftests/memory-hotplug/on-off-test.sh | 238 ---------------------
> 3 files changed, 253 insertions(+), 240 deletions(-)
> create mode 100644 tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
> delete mode 100644 tools/testing/selftests/memory-hotplug/on-off-test.sh
>
> diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
> index d46b8d4..8921631 100644
> --- a/tools/testing/selftests/memory-hotplug/Makefile
> +++ b/tools/testing/selftests/memory-hotplug/Makefile
> @@ -1,9 +1,22 @@
> +TEST_STR=/bin/bash ./mem-on-off-test.sh -r 2 || echo memory-hotplug selftests: [FAIL]
> +
> all:
>
> +install:
> +ifdef INSTALL_KSFT_PATH
> + install ./mem-on-off-test.sh $(INSTALL_KSFT_PATH)/mem-on-off-test.sh
> + @echo echo Start memory hotplug test .... >> $(KSELFTEST)
> + @echo "$(TEST_STR)" >> $(KSELFTEST) >> $(KSELFTEST)
> + @echo echo End memory hotplug test .... >> $(KSELFTEST)
> + @echo echo ============================== >> $(KSELFTEST)
> +else
> + @echo Run make kselftest_install in top level source directory
> +endif
I saw this pattern repeated many times in this series.
Can we make it a macro and include it instead of repeating this code?
Thank you,
--
Masami HIRAMATSU
Software Platform Research Dept. Linux Technology Research Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@hitachi.com
^ permalink raw reply
* Re: [patch net-next v3 04/17] net: introduce generic switch devices support
From: Scott Feldman @ 2014-11-27 5:58 UTC (permalink / raw)
To: Jamal Hadi Salim
Cc: Thomas Graf, Jiri Pirko, Netdev, David S. Miller,
nhorman@tuxdriver.com, Andy Gospodarek, dborkman@redhat.com,
ogerlitz@mellanox.com, jesse@nicira.com, pshelar@nicira.com,
azhou@nicira.com, ben@decadent.org.uk, stephen@networkplumber.org,
Kirsher, Jeffrey T, vyasevic@redhat.com, Cong Wang,
Fastabend, John R, Eric Dumazet, Florian Fainelli, Roopa Prabhu,
John Linville
In-Reply-To: <5475BB53.3070200@mojatatu.com>
On Wed, Nov 26, 2014 at 1:36 AM, Jamal Hadi Salim <jhs@mojatatu.com> wrote:
> On 11/25/14 23:18, Scott Feldman wrote:
>>
>> On Tue, Nov 25, 2014 at 5:33 PM, Jamal Hadi Salim <jhs@mojatatu.com>
>> wrote:
>
>
>>
>> You have a pointer to the kernel driver for that HW?
>
>
> I wasnt sure if that was a passive aggressive move there to
> question what i am claiming?(Only Canadians are allowed to be
> passive aggressive Scott). To answer your question, no
> code currently littered with vendor SDK unfortunately (as you
> would know!).
Drats, I was hoping there might be Open Source here. I'm actually not
familiar with Netronome offerings. I went to their web page and all
their Docs downloads require registration, so I should have guessed
same-old-same-old. But you teased us with it, so I thought I would
ask. Sorry for the trouble XOXOXOXO. I'm not Canadian, as far as I
know.
> But hopefully if we get these changes in correctly it would
> not be hard to show the driver working fully in the kernel.
> There are definetely a few other pieces of hardware that are
> making me come back here and invest time and effort in these
> long discussions.
You have access to the inside scope. We don't. Ok, I don't. We
(think we) know what the traditional L2/L3 and OVS-style flow stuff
looks like, but you know more, but you can't show us in code so it's
frustrating. Not your fault. Just continue to guide us and give some
disclaimer when we're your close to some proprietary knowledge, but it
is relevant to the discussion.
>> Can you show how
>> you're using Linux tc netlink msg in kernel to program HW? I'd like
>> to see the in-kernel API.
>>
>
> Lets do the L2/port thing first. But yes, I am using Linux tc in
> kernel.
>
> cheers,
> jamal
^ permalink raw reply
* Re: [PATCH] e1000: remove unused variables
From: Hisashi T Fujinaka @ 2014-11-27 5:59 UTC (permalink / raw)
To: Sudip Mukherjee
Cc: Jeff Kirsher, Jesse Brandeburg, Bruce Allan, Carolyn Wyborny,
Don Skidmore, Greg Rose, Matthew Vick, John Ronciak,
Mitch Williams, Linux NICS, e1000-devel, netdev, linux-kernel
In-Reply-To: <1417065728-5592-1-git-send-email-sudipm.mukherjee@gmail.com>
I'm pretty sure those double reads are there for a reason, so most of
this I'm going to have to check on Monday. We have a long holiday
weekend here in the US.
I'm not sure why you're bothering with an old driver like this, but if
you haven't actually tried this on all the hardware it pertains to, I'm
going want to NAK this.
I should do this from my todd.fujinaka@intel.com account but it's 10PM
on the first day of a long holiday weekend.
On Thu, 27 Nov 2014, Sudip Mukherjee wrote:
> these variables were only being assigned some values, but were never
> used.
>
> Signed-off-by: Sudip Mukherjee <sudip@vectorindia.org>
> ---
> drivers/net/ethernet/intel/e1000/e1000_hw.c | 142 ++++++++++++--------------
> drivers/net/ethernet/intel/e1000/e1000_main.c | 3 -
> 2 files changed, 66 insertions(+), 79 deletions(-)
>
> diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
> index 45c8c864..7812f59 100644
> --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
> +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
> @@ -154,7 +154,6 @@ static s32 e1000_set_phy_type(struct e1000_hw *hw)
> */
> static void e1000_phy_init_script(struct e1000_hw *hw)
> {
> - u32 ret_val;
> u16 phy_saved_data;
>
> if (hw->phy_init_script) {
> @@ -163,7 +162,7 @@ static void e1000_phy_init_script(struct e1000_hw *hw)
> /* Save off the current value of register 0x2F5B to be restored
> * at the end of this routine.
> */
> - ret_val = e1000_read_phy_reg(hw, 0x2F5B, &phy_saved_data);
> + e1000_read_phy_reg(hw, 0x2F5B, &phy_saved_data);
>
> /* Disabled the PHY transmitter */
> e1000_write_phy_reg(hw, 0x2F5B, 0x0003);
> @@ -402,7 +401,6 @@ s32 e1000_reset_hw(struct e1000_hw *hw)
> {
> u32 ctrl;
> u32 ctrl_ext;
> - u32 icr;
> u32 manc;
> u32 led_ctrl;
> s32 ret_val;
> @@ -527,7 +525,7 @@ s32 e1000_reset_hw(struct e1000_hw *hw)
> ew32(IMC, 0xffffffff);
>
> /* Clear any pending interrupt events. */
> - icr = er32(ICR);
> + er32(ICR);
>
> /* If MWI was previously enabled, reenable it. */
> if (hw->mac_type == e1000_82542_rev2_0) {
> @@ -2396,16 +2394,13 @@ static s32 e1000_check_for_serdes_link_generic(struct e1000_hw *hw)
> */
> s32 e1000_check_for_link(struct e1000_hw *hw)
> {
> - u32 rxcw = 0;
> - u32 ctrl;
> u32 status;
> u32 rctl;
> u32 icr;
> - u32 signal = 0;
> s32 ret_val;
> u16 phy_data;
>
> - ctrl = er32(CTRL);
> + er32(CTRL);
> status = er32(STATUS);
>
> /* On adapters with a MAC newer than 82544, SW Definable pin 1 will be
> @@ -2414,12 +2409,9 @@ s32 e1000_check_for_link(struct e1000_hw *hw)
> */
> if ((hw->media_type == e1000_media_type_fiber) ||
> (hw->media_type == e1000_media_type_internal_serdes)) {
> - rxcw = er32(RXCW);
> + er32(RXCW);
>
> if (hw->media_type == e1000_media_type_fiber) {
> - signal =
> - (hw->mac_type >
> - e1000_82544) ? E1000_CTRL_SWDPIN1 : 0;
> if (status & E1000_STATUS_LU)
> hw->get_link_status = false;
> }
> @@ -4698,78 +4690,76 @@ s32 e1000_led_off(struct e1000_hw *hw)
> */
> static void e1000_clear_hw_cntrs(struct e1000_hw *hw)
> {
> - volatile u32 temp;
> -
> - temp = er32(CRCERRS);
> - temp = er32(SYMERRS);
> - temp = er32(MPC);
> - temp = er32(SCC);
> - temp = er32(ECOL);
> - temp = er32(MCC);
> - temp = er32(LATECOL);
> - temp = er32(COLC);
> - temp = er32(DC);
> - temp = er32(SEC);
> - temp = er32(RLEC);
> - temp = er32(XONRXC);
> - temp = er32(XONTXC);
> - temp = er32(XOFFRXC);
> - temp = er32(XOFFTXC);
> - temp = er32(FCRUC);
> -
> - temp = er32(PRC64);
> - temp = er32(PRC127);
> - temp = er32(PRC255);
> - temp = er32(PRC511);
> - temp = er32(PRC1023);
> - temp = er32(PRC1522);
> -
> - temp = er32(GPRC);
> - temp = er32(BPRC);
> - temp = er32(MPRC);
> - temp = er32(GPTC);
> - temp = er32(GORCL);
> - temp = er32(GORCH);
> - temp = er32(GOTCL);
> - temp = er32(GOTCH);
> - temp = er32(RNBC);
> - temp = er32(RUC);
> - temp = er32(RFC);
> - temp = er32(ROC);
> - temp = er32(RJC);
> - temp = er32(TORL);
> - temp = er32(TORH);
> - temp = er32(TOTL);
> - temp = er32(TOTH);
> - temp = er32(TPR);
> - temp = er32(TPT);
> -
> - temp = er32(PTC64);
> - temp = er32(PTC127);
> - temp = er32(PTC255);
> - temp = er32(PTC511);
> - temp = er32(PTC1023);
> - temp = er32(PTC1522);
> -
> - temp = er32(MPTC);
> - temp = er32(BPTC);
> + er32(CRCERRS);
> + er32(SYMERRS);
> + er32(MPC);
> + er32(SCC);
> + er32(ECOL);
> + er32(MCC);
> + er32(LATECOL);
> + er32(COLC);
> + er32(DC);
> + er32(SEC);
> + er32(RLEC);
> + er32(XONRXC);
> + er32(XONTXC);
> + er32(XOFFRXC);
> + er32(XOFFTXC);
> + er32(FCRUC);
> +
> + er32(PRC64);
> + er32(PRC127);
> + er32(PRC255);
> + er32(PRC511);
> + er32(PRC1023);
> + er32(PRC1522);
> +
> + er32(GPRC);
> + er32(BPRC);
> + er32(MPRC);
> + er32(GPTC);
> + er32(GORCL);
> + er32(GORCH);
> + er32(GOTCL);
> + er32(GOTCH);
> + er32(RNBC);
> + er32(RUC);
> + er32(RFC);
> + er32(ROC);
> + er32(RJC);
> + er32(TORL);
> + er32(TORH);
> + er32(TOTL);
> + er32(TOTH);
> + er32(TPR);
> + er32(TPT);
> +
> + er32(PTC64);
> + er32(PTC127);
> + er32(PTC255);
> + er32(PTC511);
> + er32(PTC1023);
> + er32(PTC1522);
> +
> + er32(MPTC);
> + er32(BPTC);
>
> if (hw->mac_type < e1000_82543)
> return;
>
> - temp = er32(ALGNERRC);
> - temp = er32(RXERRC);
> - temp = er32(TNCRS);
> - temp = er32(CEXTERR);
> - temp = er32(TSCTC);
> - temp = er32(TSCTFC);
> + er32(ALGNERRC);
> + er32(RXERRC);
> + er32(TNCRS);
> + er32(CEXTERR);
> + er32(TSCTC);
> + er32(TSCTFC);
>
> if (hw->mac_type <= e1000_82544)
> return;
>
> - temp = er32(MGTPRC);
> - temp = er32(MGTPDC);
> - temp = er32(MGTPTC);
> + er32(MGTPRC);
> + er32(MGTPDC);
> + er32(MGTPTC);
> }
>
> /**
> diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
> index 24f3986..a70ea46 100644
> --- a/drivers/net/ethernet/intel/e1000/e1000_main.c
> +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
> @@ -2443,7 +2443,6 @@ static void e1000_watchdog(struct work_struct *work)
> if (link) {
> if (!netif_carrier_ok(netdev)) {
> u32 ctrl;
> - bool txb2b = true;
> /* update snapshot of PHY registers on LSC */
> e1000_get_speed_and_duplex(hw,
> &adapter->link_speed,
> @@ -2465,11 +2464,9 @@ static void e1000_watchdog(struct work_struct *work)
> adapter->tx_timeout_factor = 1;
> switch (adapter->link_speed) {
> case SPEED_10:
> - txb2b = false;
> adapter->tx_timeout_factor = 16;
> break;
> case SPEED_100:
> - txb2b = false;
> /* maybe add some timeout factor ? */
> break;
> }
>
--
Hisashi T Fujinaka - htodd@twofifty.com
BSEE + BSChem + BAEnglish + MSCS + $2.50 = coffee
^ 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