* [PATCH 6/9] net: ethernet: ti: cpsw: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Grygorii Strashko,
David S. Miller, linux-omap, netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/ethernet/ti/cpsw.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 16dcbf36f8cc..4753ae7178fb 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -3658,8 +3658,7 @@ static int cpsw_remove(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int cpsw_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
if (cpsw->data.dual_emac) {
@@ -3682,8 +3681,7 @@ static int cpsw_suspend(struct device *dev)
static int cpsw_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
/* Select default pin state */
--
2.19.0
^ permalink raw reply related
* [PATCH 7/9] net: ethernet: ti: davinci_emac: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Grygorii Strashko,
David S. Miller, linux-omap, netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/ethernet/ti/davinci_emac.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index f270beebb428..9153db120352 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -2002,8 +2002,7 @@ static int davinci_emac_remove(struct platform_device *pdev)
static int davinci_emac_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
if (netif_running(ndev))
emac_dev_stop(ndev);
@@ -2013,8 +2012,7 @@ static int davinci_emac_suspend(struct device *dev)
static int davinci_emac_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
if (netif_running(ndev))
emac_dev_open(ndev);
--
2.19.0
^ permalink raw reply related
* [PATCH 8/9] net: ethernet: wiznet: w5300: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel; +Cc: linux-renesas-soc, Wolfram Sang, David S. Miller, netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/ethernet/wiznet/w5300.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index 80fdbff67d82..f9da5d6172e3 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -661,8 +661,7 @@ static int w5300_remove(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int w5300_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
struct w5300_priv *priv = netdev_priv(ndev);
if (netif_running(ndev)) {
@@ -676,8 +675,7 @@ static int w5300_suspend(struct device *dev)
static int w5300_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
struct w5300_priv *priv = netdev_priv(ndev);
if (!netif_running(ndev)) {
--
2.19.0
^ permalink raw reply related
* [PATCH 9/9] net: phy: mdio-mux-bcm-iproc: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Andrew Lunn, Florian Fainelli,
David S. Miller, Ray Jui, Scott Branden, Jon Mason,
bcm-kernel-feedback-list, netdev, linux-arm-kernel
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/phy/mdio-mux-bcm-iproc.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index c017486e9b86..696bdf1e4576 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -289,8 +289,7 @@ static int mdio_mux_iproc_remove(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int mdio_mux_iproc_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
+ struct iproc_mdiomux_desc *md = dev_get_drvdata(dev);
clk_disable_unprepare(md->core_clk);
@@ -299,8 +298,7 @@ static int mdio_mux_iproc_suspend(struct device *dev)
static int mdio_mux_iproc_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
+ struct iproc_mdiomux_desc *md = dev_get_drvdata(dev);
clk_prepare_enable(md->core_clk);
mdio_mux_iproc_config(md);
--
2.19.0
^ permalink raw reply related
* [PATCH 0/1] ptp: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel; +Cc: linux-renesas-soc, Wolfram Sang, netdev
I got tired of fixing this in Renesas drivers manually, so I took the big
hammer. Remove this cumbersome code pattern which got copy-pasted too much
already:
- struct platform_device *pdev = to_platform_device(dev);
- struct ep93xx_keypad *keypad = platform_get_drvdata(pdev);
+ struct ep93xx_keypad *keypad = dev_get_drvdata(dev);
A branch, tested by buildbot, can be found here:
git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git coccinelle/get_drvdata
I have been asked if it couldn't be done for dev_set_drvdata as well. I checked
it and did not find one occasion where it could be simplified like this. Not
much of a surprise because driver_data is usually set in probe() functions
which access struct platform_device in many other ways.
I am open for other comments, suggestions, too, of course.
Here is the cocci-script I created:
@@
struct device* d;
identifier pdev;
expression *ptr;
@@
(
- struct platform_device *pdev = to_platform_device(d);
|
- struct platform_device *pdev;
...
- pdev = to_platform_device(d);
)
<... when != pdev
- &pdev->dev
+ d
...>
ptr =
- platform_get_drvdata(pdev)
+ dev_get_drvdata(d)
<... when != pdev
- &pdev->dev
+ d
...>
Kind regards,
Wolfram
Wolfram Sang (1):
ptp: ptp_dte: simplify getting .driver_data
drivers/ptp/ptp_dte.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
--
2.19.0
^ permalink raw reply
* [PATCH 1/1] ptp: ptp_dte: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel; +Cc: linux-renesas-soc, Wolfram Sang, Richard Cochran, netdev
In-Reply-To: <20181021200039.1933-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/ptp/ptp_dte.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/ptp/ptp_dte.c b/drivers/ptp/ptp_dte.c
index a7dc43368df4..5b6393e3ea27 100644
--- a/drivers/ptp/ptp_dte.c
+++ b/drivers/ptp/ptp_dte.c
@@ -288,8 +288,7 @@ static int ptp_dte_remove(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int ptp_dte_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct ptp_dte *ptp_dte = platform_get_drvdata(pdev);
+ struct ptp_dte *ptp_dte = dev_get_drvdata(dev);
u8 i;
for (i = 0; i < DTE_NUM_REGS_TO_RESTORE; i++) {
@@ -305,8 +304,7 @@ static int ptp_dte_suspend(struct device *dev)
static int ptp_dte_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct ptp_dte *ptp_dte = platform_get_drvdata(pdev);
+ struct ptp_dte *ptp_dte = dev_get_drvdata(dev);
u8 i;
for (i = 0; i < DTE_NUM_REGS_TO_RESTORE; i++) {
--
2.19.0
^ permalink raw reply related
* [PATCH] net/mlx5: Allocate enough space for the FDB sub-namespaces
From: Or Gerlitz @ 2018-10-21 11:05 UTC (permalink / raw)
To: David S. Miller; +Cc: Saeed Mahameed, netdev, Dan Carpenter
From: Dan Carpenter <dan.carpenter@oracle.com>
FDB_MAX_CHAIN is three. We wanted to allocate enough memory to hold four
structs but there are missing parentheses so we only allocate enough
memory for three structs and the first byte of the fourth one.
Fixes: 328edb499f99 ("net/mlx5: Split FDB fast path prio to multiple namespaces")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 67ba4c9..9d73eb9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2470,7 +2470,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
return -ENOMEM;
steering->fdb_sub_ns = kzalloc(sizeof(steering->fdb_sub_ns) *
- FDB_MAX_CHAIN + 1, GFP_KERNEL);
+ (FDB_MAX_CHAIN + 1), GFP_KERNEL);
if (!steering->fdb_sub_ns)
return -ENOMEM;
--
2.3.7
^ permalink raw reply related
* [PATCH 0/1] net: dsa: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:01 UTC (permalink / raw)
To: linux-kernel; +Cc: linux-renesas-soc, Wolfram Sang, netdev
I got tired of fixing this in Renesas drivers manually, so I took the big
hammer. Remove this cumbersome code pattern which got copy-pasted too much
already:
- struct platform_device *pdev = to_platform_device(dev);
- struct ep93xx_keypad *keypad = platform_get_drvdata(pdev);
+ struct ep93xx_keypad *keypad = dev_get_drvdata(dev);
A branch, tested by buildbot, can be found here:
git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git coccinelle/get_drvdata
I have been asked if it couldn't be done for dev_set_drvdata as well. I checked
it and did not find one occasion where it could be simplified like this. Not
much of a surprise because driver_data is usually set in probe() functions
which access struct platform_device in many other ways.
I am open for other comments, suggestions, too, of course.
Here is the cocci-script I created:
@@
struct device* d;
identifier pdev;
expression *ptr;
@@
(
- struct platform_device *pdev = to_platform_device(d);
|
- struct platform_device *pdev;
...
- pdev = to_platform_device(d);
)
<... when != pdev
- &pdev->dev
+ d
...>
ptr =
- platform_get_drvdata(pdev)
+ dev_get_drvdata(d)
<... when != pdev
- &pdev->dev
+ d
...>
Kind regards,
Wolfram
Wolfram Sang (1):
net: dsa: legacy: simplify getting .driver_data
net/dsa/legacy.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
--
2.19.0
^ permalink raw reply
* [PATCH 1/1] net: dsa: legacy: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:01 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Andrew Lunn, Vivien Didelot,
Florian Fainelli, David S. Miller, netdev
In-Reply-To: <20181021200105.2414-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
net/dsa/legacy.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
index 8aa92b09db76..cb42939db776 100644
--- a/net/dsa/legacy.c
+++ b/net/dsa/legacy.c
@@ -686,8 +686,7 @@ static void dsa_shutdown(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int dsa_suspend(struct device *d)
{
- struct platform_device *pdev = to_platform_device(d);
- struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+ struct dsa_switch_tree *dst = dev_get_drvdata(d);
int i, ret = 0;
for (i = 0; i < dst->pd->nr_chips; i++) {
@@ -702,8 +701,7 @@ static int dsa_suspend(struct device *d)
static int dsa_resume(struct device *d)
{
- struct platform_device *pdev = to_platform_device(d);
- struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
+ struct dsa_switch_tree *dst = dev_get_drvdata(d);
int i, ret = 0;
for (i = 0; i < dst->pd->nr_chips; i++) {
--
2.19.0
^ permalink raw reply related
* Re: Fw: [Bug 201423] New: eth0: hw csum failure
From: Andre Tomt @ 2018-10-21 13:34 UTC (permalink / raw)
To: Eric Dumazet, Eric Dumazet
Cc: Stephen Hemminger, netdev, rossi.f, Dimitris Michailidis
In-Reply-To: <cd6f5d1f-bd89-5da2-96be-85c2311ca0a1@gmail.com>
On 20.10.2018 00:25, Eric Dumazet wrote:
> On 10/19/2018 02:58 PM, Eric Dumazet wrote:
>> On 10/16/2018 06:00 AM, Eric Dumazet wrote:
>>> On Mon, Oct 15, 2018 at 11:30 PM Andre Tomt <andre@tomt.net> wrote:
>>>> I've seen similar on several systems with mlx4 cards when using 4.18.x -
>>>> that is hw csum failure followed by some backtrace.
>>>>
>>>> Only seems to happen on systems dealing with quite a bit of UDP.
>>>>
>>>
>>> Strange, because mlx4 on IPv6+UDP should not use CHECKSUM_COMPLETE,
>>> but CHECKSUM_UNNECESSARY
>>>
>>> I would be nice to track this a bit further, maybe by providing the
>>> full packet content.
>>>
<snip>
>>
>> As a matter of fact Dimitris found the issue in the patch and is working on a fix involving csum_block_sub()
>>
>> Problems comes from trimming an odd number of bytes.
>
> More exactly, trimming bytes starting at an odd offset.
No hw csum failures here since I deployed Dimitris fix on top of 4.18.16
32 hours ago.
Thanks
^ permalink raw reply
* Re: [PATCH 1/9] net: dsa: bcm_sf2: simplify getting .driver_data
From: Andrew Lunn @ 2018-10-21 23:16 UTC (permalink / raw)
To: Wolfram Sang
Cc: linux-kernel, linux-renesas-soc, Vivien Didelot, Florian Fainelli,
David S. Miller, netdev
In-Reply-To: <20181021200021.1693-2-wsa+renesas@sang-engineering.com>
On Sun, Oct 21, 2018 at 10:00:12PM +0200, Wolfram Sang wrote:
> We should get 'driver_data' from 'struct device' directly. Going via
> platform_device is an unneeded step back and forth.
>
> Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Andrew
^ permalink raw reply
* [PATCH V1 net-next] net: ena: fix compilation error in xtensa architecture
From: akiyano @ 2018-10-21 15:07 UTC (permalink / raw)
To: davem, netdev
Cc: Arthur Kiyanovski, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, gtzalik, netanel, alisaidi
From: Arthur Kiyanovski <akiyano@amazon.com>
linux/prefetch.h is never explicitly included in ena_com, although
functions from it, such as prefetchw(), are used throughout ena_com.
This is an inclusion bug, and we fix it here by explicitly including
linux/prefetch.h. The bug was exposed when the driver was compiled
for the xtensa architecture.
Fixes: 689b2bdaaa14 ("net: ena: add functions for handling Low Latency Queues in ena_com")
Fixes: 8c590f977638 ("ena: Fix Kconfig dependency on X86")
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_com.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index ae8b485..078d6f2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -38,6 +38,7 @@
#include <linux/dma-mapping.h>
#include <linux/gfp.h>
#include <linux/io.h>
+#include <linux/prefetch.h>
#include <linux/sched.h>
#include <linux/sizes.h>
#include <linux/spinlock.h>
--
2.7.4
^ permalink raw reply related
* Re: [PATCH bpf-next] selftests/bpf: enable (uncomment) all tests in test_libbpf.sh
From: Quentin Monnet @ 2018-10-21 15:37 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: Alexei Starovoitov, Daniel Borkmann, netdev, oss-drivers,
Quentin Monnet
In-Reply-To: <20181021115729.2095d2a0@redhat.com>
2018-10-21 11:57 UTC+0200 ~ Jesper Dangaard Brouer <brouer@redhat.com>
> On Sat, 20 Oct 2018 23:00:24 +0100
> Quentin Monnet <quentin.monnet@netronome.com> wrote:
>
[...]
>> --- a/tools/testing/selftests/bpf/test_libbpf.sh
>> +++ b/tools/testing/selftests/bpf/test_libbpf.sh
>> @@ -33,17 +33,11 @@ trap exit_handler 0 2 3 6 9
>>
>> libbpf_open_file test_l4lb.o
>>
>> -# TODO: fix libbpf to load noinline functions
>> -# [warning] libbpf: incorrect bpf_call opcode
>> -#libbpf_open_file test_l4lb_noinline.o
>> +libbpf_open_file test_l4lb_noinline.o
>>
>> -# TODO: fix test_xdp_meta.c to load with libbpf
>> -# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version
>> -#libbpf_open_file test_xdp_meta.o
>> +libbpf_open_file test_xdp_meta.o
>>
>> -# TODO: fix libbpf to handle .eh_frame
>> -# [warning] libbpf: relocation failed: no section(10)
>> -#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
>> +libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
>
> I don't like the ../../../../samples/bpf/ reference (even-through I
> added this TODO), as the kselftests AFAIK support installing the
> selftests and then this tests will fail.
> Maybe we can find another example kern.o file?
> (which isn't compiled with -target bpf)
Hi Jesper, yeah maybe making the test rely on something from samples/bpf
instead of just the selftests/bpf directory is not a good idea. But
there is no program compiled without the "-target-bpf" in that
directory. What we could do is explicitly compile one without the flag
in the Makefile, as in the patch below, but I am not sure that doing so
is acceptable? Or should tests for libbpf have a directory of their own,
with another Makefile?
Another question regarding the test with test_xdp_meta.o: does the fix I
suggested (setting a version in the .C file) makes sense, or did you
leave this test for testing someday that libbpf would be able to open
even programs that do not set a version (in which case this is still not
the case if program type is not provided, and in fact my fix ruins
everything? :s).
Thanks,
Quentin
---
tools/testing/selftests/bpf/Makefile | 10 ++++++++++
tools/testing/selftests/bpf/test_libbpf.sh | 14 +++++---------
tools/testing/selftests/bpf/test_xdp_meta.c | 2 ++
3 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e39dfb4e7970..ecd79b7fb107 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -135,6 +135,16 @@ endif
endif
endif
+# Have one program compiled without "-target bpf" to test whether libbpf loads
+# it successfully
+$(OUTPUT)/test_xdp.o: test_xdp.c
+ $(CLANG) $(CLANG_FLAGS) \
+ -O2 -emit-llvm -c $< -o - | \
+ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
+ifeq ($(DWARF2BTF),y)
+ $(BTF_PAHOLE) -J $@
+endif
+
$(OUTPUT)/%.o: %.c
$(CLANG) $(CLANG_FLAGS) \
-O2 -target bpf -emit-llvm -c $< -o - | \
diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh
index 156d89f1edcc..b45962a44243 100755
--- a/tools/testing/selftests/bpf/test_libbpf.sh
+++ b/tools/testing/selftests/bpf/test_libbpf.sh
@@ -33,17 +33,13 @@ trap exit_handler 0 2 3 6 9
libbpf_open_file test_l4lb.o
-# TODO: fix libbpf to load noinline functions
-# [warning] libbpf: incorrect bpf_call opcode
-#libbpf_open_file test_l4lb_noinline.o
+# Load a program with BPF-to-BPF calls
+libbpf_open_file test_l4lb_noinline.o
-# TODO: fix test_xdp_meta.c to load with libbpf
-# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version
-#libbpf_open_file test_xdp_meta.o
+libbpf_open_file test_xdp_meta.o
-# TODO: fix libbpf to handle .eh_frame
-# [warning] libbpf: relocation failed: no section(10)
-#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
+# Load a program compiled without the "-target bpf" flag
+libbpf_open_file test_xdp.o
# Success
exit 0
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/test_xdp_meta.c
index 8d0182650653..2f42de66e2bb 100644
--- a/tools/testing/selftests/bpf/test_xdp_meta.c
+++ b/tools/testing/selftests/bpf/test_xdp_meta.c
@@ -8,6 +8,8 @@
#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
#define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem
+int _version SEC("version") = 1;
+
SEC("t")
int ing_cls(struct __sk_buff *ctx)
{
--
2.7.4
^ permalink raw reply related
* Re: [PATCHv2 iproute2-next] ip/geneve: fix ttl inherit behavior
From: David Ahern @ 2018-10-21 15:55 UTC (permalink / raw)
To: Hangbin Liu, netdev; +Cc: Stephen Hemminger, Phil Sutter, Michal Kubecek
In-Reply-To: <1539846110-11607-1-git-send-email-liuhangbin@gmail.com>
On 10/18/18 1:01 AM, Hangbin Liu wrote:
> Currently when we add geneve with "ttl inherit", we only set ttl to 0, which
> is actually use whatever default value instead of inherit the inner protocol's
> ttl value.
>
> To make a difference with ttl inherit and ttl == 0, we add an attribute
> IFLA_GENEVE_TTL_INHERIT in kernel commit 52d0d404d39dd ("geneve: add ttl
> inherit support"). Now let's use "ttl inherit" to inherit the inner
> protocol's ttl, and use "ttl auto" to means "use whatever default value",
> the same behavior with ttl == 0.
>
> v2:
> 1) remove IFLA_GENEVE_TTL_INHERIT defination in if_link.h as it's already
> updated.
> 2) Still use addattr8() so we can enable/disable ttl inherit, as Michal
> suggested.
>
> Reported-by: Jianlin Shi <jishi@redhat.com>
> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
> ---
> ip/iplink_geneve.c | 20 +++++++++++++-------
> 1 file changed, 13 insertions(+), 7 deletions(-)
>
please update the man page as well.
^ permalink raw reply
* Re: [PATCH iproute2-next 3/3] rdma: Add an option to rename IB device interface
From: David Ahern @ 2018-10-21 16:02 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Leon Romanovsky, netdev, RDMA mailing list, Stephen Hemminger
In-Reply-To: <20181018115120.17893-4-leon@kernel.org>
On 10/18/18 5:51 AM, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@mellanox.com>
>
> Enrich rdmatool with an option to rename IB devices,
> the command interface follows Iproute2 convention:
> "rdma dev set [OLD-DEVNAME] name NEW-DEVNAME"
>
> Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
> ---
> rdma/dev.c | 35 +++++++++++++++++++++++++++++++++++
> 1 file changed, 35 insertions(+)
>
> diff --git a/rdma/dev.c b/rdma/dev.c
> index e2eafe47..760b7fb3 100644
> --- a/rdma/dev.c
> +++ b/rdma/dev.c
> @@ -14,6 +14,7 @@
> static int dev_help(struct rd *rd)
> {
> pr_out("Usage: %s dev show [DEV]\n", rd->filename);
> + pr_out(" %s dev set [DEV] name DEVNAME\n", rd->filename);
> return 0;
> }
>
> @@ -240,17 +241,51 @@ static int dev_one_show(struct rd *rd)
> return rd_exec_cmd(rd, cmds, "parameter");
> }
>
> +static int dev_set_name(struct rd *rd)
> +{
> + uint32_t seq;
> +
> + if (rd_no_arg(rd)) {
> + pr_err("Please provide device new name.\n");
> + return -EINVAL;
> + }
This is redundant with rd_exec_require_dev which is the required path to
get to this point.
^ permalink raw reply
* pull-request: bpf-next 2018-10-21
From: Daniel Borkmann @ 2018-10-21 19:24 UTC (permalink / raw)
To: davem; +Cc: daniel, ast, netdev
Hi David,
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Implement two new kind of BPF maps, that is, queue and stack
map along with new peek, push and pop operations, from Mauricio.
2) Add support for MSG_PEEK flag when redirecting into an ingress
psock sk_msg queue, and add a new helper bpf_msg_push_data() for
insert data into the message, from John.
3) Allow for BPF programs of type BPF_PROG_TYPE_CGROUP_SKB to use
direct packet access for __skb_buff, from Song.
4) Use more lightweight barriers for walking perf ring buffer for
libbpf and perf tool as well. Also, various fixes and improvements
from verifier side, from Daniel.
5) Add per-symbol visibility for DSO in libbpf and hide by default
global symbols such as netlink related functions, from Andrey.
6) Two improvements to nfp's BPF offload to check vNIC capabilities
in case prog is shared with multiple vNICs and to protect against
mis-initializing atomic counters, from Jakub.
7) Fix for bpftool to use 4 context mode for the nfp disassembler,
also from Jakub.
8) Fix a return value comparison in test_libbpf.sh and add several
bpftool improvements in bash completion, documentation of bpf fs
restrictions and batch mode summary print, from Quentin.
9) Fix a file resource leak in BPF selftest's load_kallsyms()
helper, from Peng.
10) Fix an unused variable warning in map_lookup_and_delete_elem(),
from Alexei.
11) Fix bpf_skb_adjust_room() signature in BPF UAPI helper doc,
from Nicolas.
12) Add missing executables to .gitignore in BPF selftests, from Anders.
Please consider pulling these changes from:
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
Thanks a lot!
----------------------------------------------------------------
The following changes since commit 2c59f06cc0442862d589c36bd2f29667f96c35e7:
Merge branch 'net-Kernel-side-filtering-for-route-dumps' (2018-10-16 00:14:18 -0700)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git
for you to fetch changes up to fe8ecccc10b3adc071de05ca7af728ca1a4ac9aa:
tools: bpftool: fix completion for "bpftool map update" (2018-10-21 20:45:14 +0200)
----------------------------------------------------------------
Alexei Starovoitov (6):
Merge branch 'nfp-improve-bpf-offload'
Merge branch 'queue_stack_maps'
Merge branch 'improve_perf_barriers'
Merge branch 'cg_skb_direct_pkt_access'
bpf: remove unused variable
Merge branch 'misc-improvements'
Anders Roxell (1):
selftests/bpf: add missing executables to .gitignore
Andrey Ignatov (1):
libbpf: Per-symbol visibility for DSO
Daniel Borkmann (11):
bpf, tls: add tls header to tools infrastructure
Merge branch 'bpf-sk-msg-peek'
tools, perf: add and use optimized ring_buffer_{read_head, write_tail} helpers
bpf, libbpf: use correct barriers in perf ring buffer walk
Merge branch 'bpf-msg-push-data'
ulp: remove uid and user_visible members
bpf, verifier: fix register type dump in xadd and st
bpf, verifier: reject xadd on flow key memory
bpf, verifier: remove unneeded flow key in check_helper_mem_access
bpf, verifier: avoid retpoline for map push/pop/peek operation
bpf, libbpf: simplify and cleanup perf ring buffer walk
Jakub Kicinski (3):
nfp: bpf: protect against mis-initializing atomic counters
nfp: bpf: double check vNIC capabilities after object sharing
tools: bpftool: use 4 context mode for the NFP disasm
John Fastabend (8):
bpf: sockmap, fix skmsg recvmsg handler to track size correctly
bpf: skmsg, improve sk_msg_used_element to work in cork context
bpf: sockmap, support for msg_peek in sk_msg with redirect ingress
bpf: sockmap, add msg_peek tests to test_sockmap
bpf: skmsg, fix psock create on existing kcm/tls port
bpf: sk_msg program helper bpf_msg_push_data
bpf: libbpf support for msg_push_data
bpf: test_sockmap add options to use msg_push_data
Mauricio Vasquez B (7):
bpf: rename stack trace map operations
bpf/syscall: allow key to be null in map functions
bpf/verifier: add ARG_PTR_TO_UNINIT_MAP_VALUE
bpf: add queue and stack maps
bpf: add MAP_LOOKUP_AND_DELETE_ELEM syscall
Sync uapi/bpf.h to tools/include
selftests/bpf: add test cases for queue and stack maps
Nicolas Dichtel (1):
bpf: fix doc of bpf_skb_adjust_room() in uapi
Peng Hao (1):
selftests/bpf: fix file resource leak in load_kallsyms
Quentin Monnet (4):
selftests/bpf: fix return value comparison for tests in test_libbpf.sh
tools: bpftool: document restriction on '.' in names to pin in bpffs
tools: bpftool: print nb of cmds to stdout (not stderr) for batch mode
tools: bpftool: fix completion for "bpftool map update"
Song Liu (2):
bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB
bpf: add tests for direct packet access from CGROUP_SKB
drivers/net/ethernet/netronome/nfp/bpf/main.h | 10 +-
drivers/net/ethernet/netronome/nfp/bpf/offload.c | 32 ++-
drivers/net/ethernet/netronome/nfp/bpf/verifier.c | 69 ++++-
include/linux/bpf.h | 7 +
include/linux/bpf_types.h | 4 +-
include/linux/filter.h | 21 ++
include/linux/skmsg.h | 42 ++-
include/net/tcp.h | 9 +-
include/uapi/linux/bpf.h | 50 +++-
kernel/bpf/Makefile | 2 +-
kernel/bpf/cgroup.c | 6 +
kernel/bpf/core.c | 3 +
kernel/bpf/helpers.c | 43 +++
kernel/bpf/queue_stack_maps.c | 288 +++++++++++++++++++++
kernel/bpf/stackmap.c | 2 +-
kernel/bpf/syscall.c | 91 ++++++-
kernel/bpf/verifier.c | 85 +++++-
net/bpf/test_run.c | 15 ++
net/core/filter.c | 176 ++++++++++++-
net/core/sock_map.c | 11 +-
net/ipv4/tcp_bpf.c | 41 ++-
net/tls/tls_main.c | 2 -
net/tls/tls_sw.c | 3 +-
tools/arch/arm64/include/asm/barrier.h | 70 +++++
tools/arch/ia64/include/asm/barrier.h | 13 +
tools/arch/powerpc/include/asm/barrier.h | 16 ++
tools/arch/s390/include/asm/barrier.h | 13 +
tools/arch/sparc/include/asm/barrier_64.h | 13 +
tools/arch/x86/include/asm/barrier.h | 14 +
tools/bpf/bpftool/Documentation/bpftool-map.rst | 4 +-
tools/bpf/bpftool/Documentation/bpftool-prog.rst | 8 +-
tools/bpf/bpftool/bash-completion/bpftool | 2 +-
tools/bpf/bpftool/common.c | 5 +-
tools/bpf/bpftool/jit_disasm.c | 4 +-
tools/bpf/bpftool/main.c | 3 +-
tools/bpf/bpftool/main.h | 6 +-
tools/bpf/bpftool/map_perf_ring.c | 10 +-
tools/bpf/bpftool/prog.c | 14 +-
tools/include/asm/barrier.h | 35 +++
tools/include/linux/ring_buffer.h | 73 ++++++
tools/include/uapi/linux/bpf.h | 50 +++-
tools/include/uapi/linux/tls.h | 78 ++++++
tools/lib/bpf/Makefile | 1 +
tools/lib/bpf/bpf.c | 12 +
tools/lib/bpf/bpf.h | 120 +++++----
tools/lib/bpf/btf.h | 22 +-
tools/lib/bpf/libbpf.c | 75 +++---
tools/lib/bpf/libbpf.h | 191 +++++++-------
tools/perf/util/mmap.h | 15 +-
tools/testing/selftests/bpf/.gitignore | 2 +
tools/testing/selftests/bpf/Makefile | 5 +-
tools/testing/selftests/bpf/bpf_helpers.h | 9 +
tools/testing/selftests/bpf/test_libbpf.sh | 2 +-
tools/testing/selftests/bpf/test_maps.c | 122 +++++++++
tools/testing/selftests/bpf/test_progs.c | 99 +++++++
tools/testing/selftests/bpf/test_queue_map.c | 4 +
tools/testing/selftests/bpf/test_queue_stack_map.h | 59 +++++
tools/testing/selftests/bpf/test_sockmap.c | 238 ++++++++++++-----
tools/testing/selftests/bpf/test_sockmap_kern.h | 97 +++++--
tools/testing/selftests/bpf/test_stack_map.c | 4 +
tools/testing/selftests/bpf/test_verifier.c | 181 ++++++++++++-
tools/testing/selftests/bpf/trace_helpers.c | 8 +-
62 files changed, 2315 insertions(+), 394 deletions(-)
create mode 100644 kernel/bpf/queue_stack_maps.c
create mode 100644 tools/include/linux/ring_buffer.h
create mode 100644 tools/include/uapi/linux/tls.h
create mode 100644 tools/testing/selftests/bpf/test_queue_map.c
create mode 100644 tools/testing/selftests/bpf/test_queue_stack_map.h
create mode 100644 tools/testing/selftests/bpf/test_stack_map.c
^ permalink raw reply
* bpf-next is CLOSED
From: Daniel Borkmann @ 2018-10-21 19:27 UTC (permalink / raw)
To: netdev; +Cc: ast
Given the merge window is opening shortly, please only submit bug
fixes to bpf tree at this time, thank you!
^ permalink raw reply
* Re: [PATCH 0/9] net: simplify getting .driver_data
From: David Miller @ 2018-10-22 4:11 UTC (permalink / raw)
To: wsa+renesas
Cc: linux-kernel, linux-renesas-soc, linux-arm-kernel, linux-omap,
netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sun, 21 Oct 2018 22:00:11 +0200
> I got tired of fixing this in Renesas drivers manually, so I took the big
> hammer. Remove this cumbersome code pattern which got copy-pasted too much
> already:
>
> - struct platform_device *pdev = to_platform_device(dev);
> - struct ep93xx_keypad *keypad = platform_get_drvdata(pdev);
> + struct ep93xx_keypad *keypad = dev_get_drvdata(dev);
>
> A branch, tested by buildbot, can be found here:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git coccinelle/get_drvdata
>
> I have been asked if it couldn't be done for dev_set_drvdata as well. I checked
> it and did not find one occasion where it could be simplified like this. Not
> much of a surprise because driver_data is usually set in probe() functions
> which access struct platform_device in many other ways.
>
> I am open for other comments, suggestions, too, of course.
>
> Here is the cocci-script I created:
...
Series applied to net-next, thanks.
^ permalink raw reply
* [PATCH 2/9] net: dsa: qca8k: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Andrew Lunn, Vivien Didelot,
Florian Fainelli, David S. Miller, netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/dsa/qca8k.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index cdcde7f8e0b2..7e97e620bd44 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -955,8 +955,7 @@ qca8k_set_pm(struct qca8k_priv *priv, int enable)
static int qca8k_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct qca8k_priv *priv = platform_get_drvdata(pdev);
+ struct qca8k_priv *priv = dev_get_drvdata(dev);
qca8k_set_pm(priv, 0);
@@ -965,8 +964,7 @@ static int qca8k_suspend(struct device *dev)
static int qca8k_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct qca8k_priv *priv = platform_get_drvdata(pdev);
+ struct qca8k_priv *priv = dev_get_drvdata(dev);
qca8k_set_pm(priv, 1);
--
2.19.0
^ permalink raw reply related
* Re: [RFC PATCH v2 00/10] udp: implement GRO support
From: Willem de Bruijn @ 2018-10-21 20:05 UTC (permalink / raw)
To: Paolo Abeni; +Cc: Network Development, Willem de Bruijn, steffen.klassert
In-Reply-To: <cover.1539957909.git.pabeni@redhat.com>
On Fri, Oct 19, 2018 at 10:30 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> This series implements GRO support for UDP sockets, as the RX counterpart
> of commit bec1f6f69736 ("udp: generate gso with UDP_SEGMENT").
> The core functionality is implemented by the second patch, introducing a new
> sockopt to enable UDP_GRO, while patch 3 implements support for passing the
> segment size to the user space via a new cmsg.
> UDP GRO performs a socket lookup for each ingress packets and aggregate datagram
> directed to UDP GRO enabled sockets with constant l4 tuple.
>
> UDP GRO packets can land on non GRO-enabled sockets, e.g. due to iptables NAT
> rules, and that could potentially confuse existing applications.
Good catch.
> The solution adopted here is to de-segment the GRO packet before enqueuing
> as needed. Since we must cope with packet reinsertion after de-segmentation,
> the relevant code is factored-out in ipv4 and ipv6 specific helpers and exposed
> to UDP usage.
>
> While the current code can probably be improved, this safeguard ,implemented in
> the patches 4-7, allows future enachements to enable UDP GSO offload on more
> virtual devices eventually even on forwarded packets.
>
> The last 4 for patches implement some performance and functional self-tests,
> re-using the existing udpgso infrastructure. The problematic scenario described
> above is explicitly tested.
This looks awesome! Impressive testing, too.
A few comments in the individual patches, mostly minor.
^ permalink raw reply
* Re: [RFC PATCH v2 02/10] udp: implement GRO for plain UDP sockets.
From: Willem de Bruijn @ 2018-10-21 20:06 UTC (permalink / raw)
To: Paolo Abeni; +Cc: Network Development, Willem de Bruijn, steffen.klassert
In-Reply-To: <3fa3822651e29b8484d598b10ae61b0efde6b14f.1539957909.git.pabeni@redhat.com>
On Fri, Oct 19, 2018 at 10:30 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> This is the RX counterpart of commit bec1f6f69736 ("udp: generate gso
> with UDP_SEGMENT"). When UDP_GRO is enabled, such socket is also
> eligible for GRO in the rx path: UDP segments directed to such socket
> are assembled into a larger GSO_UDP_L4 packet.
>
> The core UDP GRO support is enabled with setsockopt(UDP_GRO).
>
> Initial benchmark numbers:
>
> Before:
> udp rx: 1079 MB/s 769065 calls/s
>
> After:
> udp rx: 1466 MB/s 24877 calls/s
>
>
> This change introduces a side effect in respect to UDP tunnels:
> after a UDP tunnel creation, now the kernel performs a lookup per ingress
> UDP packet, while before such lookup happened only if the ingress packet
> carried a valid internal header csum.
>
> v1 -> v2:
> - use a new option to enable UDP GRO
> - use static keys to protect the UDP GRO socket lookup
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> include/linux/udp.h | 3 +-
> include/uapi/linux/udp.h | 1 +
> net/ipv4/udp.c | 7 +++
> net/ipv4/udp_offload.c | 109 +++++++++++++++++++++++++++++++--------
> net/ipv6/udp_offload.c | 6 +--
> 5 files changed, 98 insertions(+), 28 deletions(-)
>
> diff --git a/include/linux/udp.h b/include/linux/udp.h
> index a4dafff407fb..f613b329852e 100644
> --- a/include/linux/udp.h
> +++ b/include/linux/udp.h
> @@ -50,11 +50,12 @@ struct udp_sock {
> __u8 encap_type; /* Is this an Encapsulation socket? */
> unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
> no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
> - encap_enabled:1; /* This socket enabled encap
> + encap_enabled:1, /* This socket enabled encap
> * processing; UDP tunnels and
> * different encapsulation layer set
> * this
> */
> + gro_enabled:1; /* Can accept GRO packets */
>
> /*
> * Following member retains the information to create a UDP header
> * when the socket is uncorked.
> diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
> index 09502de447f5..30baccb6c9c4 100644
> --- a/include/uapi/linux/udp.h
> +++ b/include/uapi/linux/udp.h
> @@ -33,6 +33,7 @@ struct udphdr {
> #define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */
> #define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */
> #define UDP_SEGMENT 103 /* Set GSO segmentation size */
> +#define UDP_GRO 104 /* This socket can receive UDP GRO packets */
>
> /* UDP encapsulation types */
> #define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
> diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
> index 9fcb5374e166..3c277378814f 100644
> --- a/net/ipv4/udp.c
> +++ b/net/ipv4/udp.c
> @@ -115,6 +115,7 @@
> #include "udp_impl.h"
> #include <net/sock_reuseport.h>
> #include <net/addrconf.h>
> +#include <net/udp_tunnel.h>
>
> struct udp_table udp_table __read_mostly;
> EXPORT_SYMBOL(udp_table);
> @@ -2459,6 +2460,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
> up->gso_size = val;
> break;
>
> + case UDP_GRO:
> + if (valbool)
> + udp_tunnel_encap_enable(sk->sk_socket);
> + up->gro_enabled = valbool;
The socket lock is not held here, so multiple updates to
up->gro_enabled and the up->encap_enabled and the static branch can
race. Syzkaller is adept at generating those.
> +#define UDO_GRO_CNT_MAX 64
> +static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
> + struct sk_buff *skb)
> +{
> + struct udphdr *uh = udp_hdr(skb);
> + struct sk_buff *pp = NULL;
> + struct udphdr *uh2;
> + struct sk_buff *p;
> +
> + /* requires non zero csum, for simmetry with GSO */
symmetry
^ permalink raw reply
* Re: [RFC PATCH v2 03/10] udp: add support for UDP_GRO cmsg
From: Willem de Bruijn @ 2018-10-21 20:07 UTC (permalink / raw)
To: Paolo Abeni; +Cc: Network Development, Willem de Bruijn, steffen.klassert
In-Reply-To: <a8112a7fbbfc39d5b59e5ace0d3c1409824f9261.1539957909.git.pabeni@redhat.com>
On Fri, Oct 19, 2018 at 10:30 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> When UDP GRO is enabled, the UDP_GRO cmsg will carry the ingress
> datagram size. User-space can use such info to compute the original
> packets layout.
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> CHECK: should we use a separate setsockopt to explicitly enable
> gso_size cmsg reception? So that user space can enable UDP_GRO and
> fetch cmsg without forcefully receiving GRO related info.
A user can avoid the message by not passing control data. Though in
most practical cases it seems unsafe to do so, anyway, as the path MTU
can be lower than the expected device MTU.
> diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
> index 3c277378814f..2331ac9de954 100644
> --- a/net/ipv4/udp.c
> +++ b/net/ipv4/udp.c
> @@ -1714,6 +1714,10 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
> memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
> *addr_len = sizeof(*sin);
> }
> +
> + if (udp_sk(sk)->gro_enabled)
> + udp_cmsg_recv(msg, sk, skb);
> +
Perhaps we can avoid adding a branch by setting a bit in
inet->cmsg_flags for gso_size to let the below branch handle the cmsg
processing.
I'd still set that as part of the UDP_GRO setsockopt. Though if you
insist it could be a value 2 instead of 1, effectively allowing the
above mentioned opt-out.
> if (inet->cmsg_flags)
> ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off);
>
^ permalink raw reply
* Re: [RFC PATCH v2 06/10] udp: cope with UDP GRO packet misdirection
From: Willem de Bruijn @ 2018-10-21 20:08 UTC (permalink / raw)
To: Paolo Abeni; +Cc: Network Development, Willem de Bruijn, steffen.klassert
In-Reply-To: <63e4ceb238db122d3d831f0809285243701b2284.1539957909.git.pabeni@redhat.com>
On Fri, Oct 19, 2018 at 10:31 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> In some scenarios, the GRO engine can assemble an UDP GRO packet
> that ultimately lands on a non GRO-enabled socket.
> This patch tries to address the issue explicitly checking for the UDP
> socket features before enqueuing the packet, and eventually segmenting
> the unexpected GRO packet, as needed.
>
> We must also cope with re-insertion requests: after segmentation the
> UDP code calls the helper introduced by the previous patches, as needed.
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> +static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
> + struct sk_buff *skb)
> +{
> + struct sk_buff *segs;
> +
> + /* the GSO CB lays after the UDP one, no need to save and restore any
> + * CB fragment, just initialize it
> + */
> + segs = __skb_gso_segment(skb, NETIF_F_SG, false);
> + if (unlikely(IS_ERR(segs)))
> + kfree_skb(skb);
> + else if (segs)
> + consume_skb(skb);
> + return segs;
> +}
> +
> +
> +void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto);
> +
> +static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
> +{
> + struct sk_buff *next, *segs;
> + int ret;
> +
> + if (likely(!udp_unexpected_gso(sk, skb)))
> + return udp_queue_rcv_one_skb(sk, skb);
> +
> + BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET);
> + __skb_push(skb, -skb_mac_offset(skb));
> + segs = udp_rcv_segment(sk, skb);
> + for (skb = segs; skb; skb = next) {
need to check IS_ERR(segs) again?
^ permalink raw reply
* Re: [RFC PATCH v2 07/10] selftests: add GRO support to udp bench rx program
From: Willem de Bruijn @ 2018-10-21 20:08 UTC (permalink / raw)
To: Paolo Abeni; +Cc: Network Development, Willem de Bruijn, steffen.klassert
In-Reply-To: <883aae234bed25efdef98907507aa73b26054a38.1539957909.git.pabeni@redhat.com>
On Fri, Oct 19, 2018 at 10:31 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> And fix a couple of buglets (port option processing,
> clean termination on SIGINT). This is preparatory work
> for GRO tests.
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> tools/testing/selftests/net/udpgso_bench_rx.c | 37 +++++++++++++++----
> 1 file changed, 30 insertions(+), 7 deletions(-)
>
> diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
> @@ -167,10 +177,10 @@ static void do_verify_udp(const char *data, int len)
> /* Flush all outstanding datagrams. Verify first few bytes of each. */
> static void do_flush_udp(int fd)
> {
> - static char rbuf[ETH_DATA_LEN];
> + static char rbuf[65535];
we can use ETH_MAX_MTU.
^ permalink raw reply
* Re: [RFC PATCH v2 08/10] selftests: conditionally enable XDP support in udpgso_bench_rx
From: Willem de Bruijn @ 2018-10-21 20:09 UTC (permalink / raw)
To: Paolo Abeni; +Cc: Network Development, Willem de Bruijn, steffen.klassert
In-Reply-To: <76b1b20399a7d5c9d4249f97383bc711e9416f1e.1539957909.git.pabeni@redhat.com>
On Fri, Oct 19, 2018 at 10:31 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> XDP support will be used by a later patch to test the GRO path
> in a net namespace, leveraging the veth XDP implementation.
> To avoid breaking existing setup, XDP support is conditionally
> enabled and build only if llc is locally available.
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
> index 256d82d5fa87..176459b7c4d6 100644
> --- a/tools/testing/selftests/net/Makefile
> +++ b/tools/testing/selftests/net/Makefile
> @@ -16,8 +16,77 @@ TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
> TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
>
> KSFT_KHDR_INSTALL := 1
> +
> +# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
> +# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
> +LLC ?= llc
> +CLANG ?= clang
> +LLVM_OBJCOPY ?= llvm-objcopy
> +BTF_PAHOLE ?= pahole
> +HAS_LLC := $(shell which $(LLC) 2>/dev/null)
> +
> +# conditional enable testes requiring llc
> +ifneq (, $(HAS_LLC))
> +TEST_GEN_FILES += xdp_dummy.o
> +endif
> +
> include ../lib.mk
>
> +ifneq (, $(HAS_LLC))
> +
> +# Detect that we're cross compiling and use the cross compiler
> +ifdef CROSS_COMPILE
> +CLANG_ARCH_ARGS = -target $(ARCH)
> +endif
> +
> +PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
> +
> +# Let newer LLVM versions transparently probe the kernel for availability
> +# of full BPF instruction set.
> +ifeq ($(PROBE),)
> + CPU ?= probe
> +else
> + CPU ?= generic
> +endif
> +
> +SRC_PATH := $(abspath ../../../..)
> +LIB_PATH := $(SRC_PATH)/tools/lib
> +XDP_CFLAGS := -D SUPPORT_XDP=1 -I$(LIB_PATH)
> +LIBBPF = $(LIB_PATH)/bpf/libbpf.a
> +BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
> +BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
> +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
> +CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
> + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
> +CLANG_FLAGS = -I. -I$(SRC_PATH)/include -I../bpf/ \
> + $(CLANG_SYS_INCLUDES) -Wno-compare-distinct-pointer-types
> +
> +ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),)
> + CLANG_CFLAGS += -g
> + LLC_FLAGS += -mattr=dwarfris
> + DWARF2BTF = y
> +endif
> +
> +$(LIBBPF): FORCE
> +# Fix up variables inherited from Kbuild that tools/ build system won't like
> + $(MAKE) -C $(dir $@) RM='rm -rf' LDFLAGS= srctree=$(SRC_PATH) O= $(nodir $@)
> +
This is a lot of XDP specific code. Not for this patchset, per se, but
would be nice if we can reuse the logic in selftests/bpf for all this.
> --- a/tools/testing/selftests/net/udpgso_bench_rx.c
> @@ -227,6 +234,13 @@ static void parse_opts(int argc, char **argv)
> cfg_verify = true;
> cfg_read_all = true;
> break;
> +#ifdef SUPPORT_XDP
> + case 'x':
> + cfg_xdp_iface = if_nametoindex(optarg);
> + if (!cfg_xdp_iface)
> + error(1, errno, "unknown interface %s", optarg);
> + break;
> +#endif
nit: needs to be added to getopt string in this patch.
^ 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