* [patch net 0/2] RED qdisc fixes
From: Nogah Frankel @ 2017-12-04 11:31 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, mlxsw, Nogah Frankel
Add some input validation checks to RED qdisc.
Nogah Frankel (2):
net_sched: red: Avoid devision by zero
net_sched: red: Avoid illegal values
include/net/red.h | 13 ++++++++++++-
net/sched/sch_choke.c | 3 +++
net/sched/sch_gred.c | 3 +++
net/sched/sch_red.c | 2 ++
net/sched/sch_sfq.c | 3 +++
5 files changed, 23 insertions(+), 1 deletion(-)
--
2.4.3
^ permalink raw reply
* [PATCH net-next 4/4] qede: Use NETIF_F_GRO_HW.
From: Michael Chan @ 2017-12-04 11:12 UTC (permalink / raw)
To: davem; +Cc: netdev, Ariel Elior, everest-linux-l2
In-Reply-To: <1512385967-32339-1-git-send-email-michael.chan@broadcom.com>
Advertise NETIF_F_GRO_HW and turn on or off hardware GRO based on
NETIF_F_GRO_FW flag.
Cc: Ariel Elior <Ariel.Elior@cavium.com>
Cc: everest-linux-l2@cavium.com
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
drivers/net/ethernet/qlogic/qede/qede_filter.c | 9 ++-------
drivers/net/ethernet/qlogic/qede/qede_main.c | 4 ++--
2 files changed, 4 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index c1a0708..7ee49b4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -901,13 +901,8 @@ int qede_set_features(struct net_device *dev, netdev_features_t features)
netdev_features_t changes = features ^ dev->features;
bool need_reload = false;
- /* No action needed if hardware GRO is disabled during driver load */
- if (changes & NETIF_F_GRO) {
- if (dev->features & NETIF_F_GRO)
- need_reload = !edev->gro_disable;
- else
- need_reload = edev->gro_disable;
- }
+ if (changes & NETIF_F_GRO_HW)
+ need_reload = true;
if (need_reload) {
struct qede_reload_args args;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 8f9b3eb..b81620e 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -676,7 +676,7 @@ static void qede_init_ndev(struct qede_dev *edev)
ndev->priv_flags |= IFF_UNICAST_FLT;
/* user-changeble features */
- hw_features = NETIF_F_GRO | NETIF_F_SG |
+ hw_features = NETIF_F_GRO | NETIF_F_GRO_HW | NETIF_F_SG |
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_TSO | NETIF_F_TSO6;
@@ -1515,7 +1515,7 @@ static void qede_init_fp(struct qede_dev *edev)
edev->ndev->name, queue_id);
}
- edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO);
+ edev->gro_disable = !(edev->ndev->features & NETIF_F_GRO_HW);
}
static int qede_set_real_num_queues(struct qede_dev *edev)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 3/4] bnx2x: Use NETIF_F_GRO_HW.
From: Michael Chan @ 2017-12-04 11:12 UTC (permalink / raw)
To: davem; +Cc: netdev, Ariel Elior, everest-linux-l2
In-Reply-To: <1512385967-32339-1-git-send-email-michael.chan@broadcom.com>
Advertise NETIF_F_GRO_HW and turn on TPA_MODE_GRO when NETIF_F_GRO_HW
is set.
Cc: Ariel Elior <Ariel.Elior@cavium.com>
Cc: everest-linux-l2@cavium.com
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 10 +++-------
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 4 +++-
2 files changed, 6 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 4c739d5..79371fb 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2482,7 +2482,7 @@ static void bnx2x_bz_fp(struct bnx2x *bp, int index)
*/
if (bp->dev->features & NETIF_F_LRO)
fp->mode = TPA_MODE_LRO;
- else if (bp->dev->features & NETIF_F_GRO &&
+ else if (bp->dev->features & NETIF_F_GRO_HW &&
bnx2x_mtu_allows_gro(bp->dev->mtu))
fp->mode = TPA_MODE_GRO;
else
@@ -4933,13 +4933,9 @@ int bnx2x_set_features(struct net_device *dev, netdev_features_t features)
}
}
- /* if GRO is changed while LRO is enabled, don't force a reload */
- if ((changes & NETIF_F_GRO) && (features & NETIF_F_LRO))
- changes &= ~NETIF_F_GRO;
-
/* if GRO is changed while HW TPA is off, don't force a reload */
- if ((changes & NETIF_F_GRO) && bp->disable_tpa)
- changes &= ~NETIF_F_GRO;
+ if ((changes & NETIF_F_GRO_HW) && bp->disable_tpa)
+ changes &= ~NETIF_F_GRO_HW;
if (changes)
bnx2x_reload = true;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 54d15713..92d54b4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -13266,7 +13266,7 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 |
- NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO |
+ NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO | NETIF_F_GRO_HW |
NETIF_F_RXHASH | NETIF_F_HW_VLAN_CTAG_TX;
if (!chip_is_e1x) {
dev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM |
@@ -13302,6 +13302,8 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
dev->features |= dev->hw_features | NETIF_F_HW_VLAN_CTAG_RX;
dev->features |= NETIF_F_HIGHDMA;
+ if (dev->features & NETIF_F_GRO_HW)
+ dev->features &= ~NETIF_F_LRO;
/* Add Loopback capability to the device */
dev->hw_features |= NETIF_F_LOOPBACK;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 1/4] net: Introduce NETIF_F_GRO_HW
From: Michael Chan @ 2017-12-04 11:12 UTC (permalink / raw)
To: davem; +Cc: netdev, Ariel Elior, everest-linux-l2
In-Reply-To: <1512385967-32339-1-git-send-email-michael.chan@broadcom.com>
Introduce NETIF_F_GRO_HW feature flag for NICs that support hardware
GRO. With this flag, we can now independently turn on or off hardware
GRO when GRO is on. Hardware GRO guarantees that packets can be
re-segmented by TSO/GSO to reconstruct the original packet stream.
Cc: Ariel Elior <Ariel.Elior@cavium.com>
Cc: everest-linux-l2@cavium.com
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
Documentation/networking/netdev-features.txt | 7 +++++++
include/linux/netdev_features.h | 5 ++++-
net/core/dev.c | 13 +++++++++++++
net/core/ethtool.c | 1 +
4 files changed, 25 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/netdev-features.txt b/Documentation/networking/netdev-features.txt
index 7413eb0..d76d332 100644
--- a/Documentation/networking/netdev-features.txt
+++ b/Documentation/networking/netdev-features.txt
@@ -163,3 +163,10 @@ This requests that the NIC receive all possible frames, including errored
frames (such as bad FCS, etc). This can be helpful when sniffing a link with
bad packets on it. Some NICs may receive more packets if also put into normal
PROMISC mode.
+
+* rx-gro-hw
+
+This requests that the NIC enables Hardware GRO (generic receive offload).
+Hardware GRO is basically the exact reverse of TSO, and is generally
+stricter than Hardware LRO. A packet stream merged by Hardware GRO must
+be re-segmentable by GSO or TSO back to the exact packet stream.
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index dc8b489..d18ef6f 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -77,6 +77,8 @@ enum {
NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */
NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */
+ NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */
+
/*
* Add your fresh new feature above and remember to update
* netdev_features_strings[] in net/core/ethtool.c and maybe
@@ -96,6 +98,7 @@ enum {
#define NETIF_F_FRAGLIST __NETIF_F(FRAGLIST)
#define NETIF_F_FSO __NETIF_F(FSO)
#define NETIF_F_GRO __NETIF_F(GRO)
+#define NETIF_F_GRO_HW __NETIF_F(GRO_HW)
#define NETIF_F_GSO __NETIF_F(GSO)
#define NETIF_F_GSO_ROBUST __NETIF_F(GSO_ROBUST)
#define NETIF_F_HIGHDMA __NETIF_F(HIGHDMA)
@@ -193,7 +196,7 @@ enum {
* If upper/master device has these features disabled, they must be disabled
* on all lower/slave devices as well.
*/
-#define NETIF_F_UPPER_DISABLES NETIF_F_LRO
+#define NETIF_F_UPPER_DISABLES (NETIF_F_LRO | NETIF_F_GRO_HW)
/* changeable features with no special hardware requirements */
#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
diff --git a/net/core/dev.c b/net/core/dev.c
index 30b5fe3..09c2ad0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7392,6 +7392,19 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
features &= ~dev->gso_partial_features;
}
+ if (features & NETIF_F_GRO_HW) {
+ /* Hardware GRO depends on GRO. */
+ if (!(features & NETIF_F_GRO)) {
+ netdev_dbg(dev, "Dropping NETIF_F_GSO_HW since no GRO feature.\n");
+ features &= ~NETIF_F_GRO_HW;
+ }
+ /* Hardware GRO and LRO are mutually exclusive. */
+ if (features & NETIF_F_LRO) {
+ netdev_dbg(dev, "Dropping NETIF_F_LRO since GRO_HW is set.\n");
+ features &= ~NETIF_F_LRO;
+ }
+ }
+
return features;
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index f8fcf45..50a7920 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -73,6 +73,7 @@ int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info)
[NETIF_F_LLTX_BIT] = "tx-lockless",
[NETIF_F_NETNS_LOCAL_BIT] = "netns-local",
[NETIF_F_GRO_BIT] = "rx-gro",
+ [NETIF_F_GRO_HW_BIT] = "rx-gro-hw",
[NETIF_F_LRO_BIT] = "rx-lro",
[NETIF_F_TSO_BIT] = "tx-tcp-segmentation",
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 2/4] bnxt_en: Use NETIF_F_GRO_HW.
From: Michael Chan @ 2017-12-04 11:12 UTC (permalink / raw)
To: davem; +Cc: netdev
In-Reply-To: <1512385967-32339-1-git-send-email-michael.chan@broadcom.com>
Advertise NETIF_F_GRO_HW if hardware GRO is supported. Turn on or off
hardware GRO based on NETIF_F_GRO_HW.
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 33c49ad..5d15cdb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2751,7 +2751,7 @@ void bnxt_set_tpa_flags(struct bnxt *bp)
return;
if (bp->dev->features & NETIF_F_LRO)
bp->flags |= BNXT_FLAG_LRO;
- if (bp->dev->features & NETIF_F_GRO)
+ if (bp->dev->features & NETIF_F_GRO_HW)
bp->flags |= BNXT_FLAG_GRO;
}
@@ -6817,7 +6817,7 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features)
bool update_tpa = false;
flags &= ~BNXT_FLAG_ALL_CONFIG_FEATS;
- if ((features & NETIF_F_GRO) && !BNXT_CHIP_TYPE_NITRO_A0(bp))
+ if (features & NETIF_F_GRO_HW)
flags |= BNXT_FLAG_GRO;
if (features & NETIF_F_LRO)
flags |= BNXT_FLAG_LRO;
@@ -8093,7 +8093,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
NETIF_F_RXCSUM | NETIF_F_GRO;
if (!BNXT_CHIP_TYPE_NITRO_A0(bp))
- dev->hw_features |= NETIF_F_LRO;
+ dev->hw_features |= NETIF_F_LRO | NETIF_F_GRO_HW;
dev->hw_enc_features =
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
@@ -8107,6 +8107,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
dev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX;
dev->features |= dev->hw_features | NETIF_F_HIGHDMA;
+ if (dev->features & NETIF_F_GRO_HW)
+ dev->features &= ~NETIF_F_LRO;
dev->priv_flags |= IFF_UNICAST_FLT;
#ifdef CONFIG_BNXT_SRIOV
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 0/4] Introduce NETIF_F_GRO_HW
From: Michael Chan @ 2017-12-04 11:12 UTC (permalink / raw)
To: davem; +Cc: netdev
Introduce NETIF_F_GRO_HW feature flag and convert drivers that support
hardware GRO to use the flag.
Michael Chan (4):
net: Introduce NETIF_F_GRO_HW
bnxt_en: Use NETIF_F_GRO_HW.
bnx2x: Use NETIF_F_GRO_HW.
qede: Use NETIF_F_GRO_HW.
Documentation/networking/netdev-features.txt | 7 +++++++
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 10 +++-------
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 4 +++-
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++---
drivers/net/ethernet/qlogic/qede/qede_filter.c | 9 ++-------
drivers/net/ethernet/qlogic/qede/qede_main.c | 4 ++--
include/linux/netdev_features.h | 5 ++++-
net/core/dev.c | 13 +++++++++++++
net/core/ethtool.c | 1 +
9 files changed, 40 insertions(+), 21 deletions(-)
--
1.8.3.1
^ permalink raw reply
* Re: [PATCH net-next v3 7/8] netdevsim: add SR-IOV functionality
From: Phil Sutter @ 2017-12-04 10:56 UTC (permalink / raw)
To: Jakub Kicinski
Cc: netdev, oss-drivers, daniel, jiri, alexei.starovoitov,
Sabrina Dubroca
In-Reply-To: <20171201230902.20108-8-jakub.kicinski@netronome.com>
On Fri, Dec 01, 2017 at 03:09:01PM -0800, Jakub Kicinski wrote:
> dummy driver was extended with VF-related netdev APIs for testing
> SR-IOV-related software. netdevsim did not exist back then.
> Implement SR-IOV functionality in netdevsim. Notable difference
> is that since netdevsim has no module parameters, we will actually
> create a device with sriov_numvfs attribute for each netdev.
> The zero MAC address is accepted as some HW use it to mean any
> address is allowed. Link state is also now validated.
>
> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Phil Sutter <phil@nwl.cc>
^ permalink raw reply
* Linux network is damn fast, need more use XDP (Was: DC behaviors today)
From: Jesper Dangaard Brouer @ 2017-12-04 10:56 UTC (permalink / raw)
To: Dave Taht
Cc: netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
bloat-JXvr2/1DY2fm6VMwtOF2vx4hnT+Y9+D1, Christina Jacob,
Joel Wirāmu Pauling,
cerowrt-devel-JXvr2/1DY2fm6VMwtOF2vx4hnT+Y9+D1@public.gmane.org,
David Ahern, Tariq Toukan
In-Reply-To: <87bmjff7l6.fsf_-_-DEcvNJsl3XAMlNlIB+YWUg@public.gmane.org>
On Sun, 03 Dec 2017 20:19:33 -0800 Dave Taht <dave@taht.net> wrote:
> Changing the topic, adding bloat.
Adding netdev, and also adjust the topic to be a rant on that the Linux
kernel network stack is actually damn fast, and if you need something
faster then XDP can solved your needs...
> Joel Wirāmu Pauling <joel@aenertia.net> writes:
>
> > Just from a Telco/Industry perspective slant.
> >
> > Everything in DC has moved to SFP28 interfaces at 25Gbit as the server
> > port of interconnect. Everything TOR wise is now QSFP28 - 100Gbit.
> > Mellanox X5 cards are the current hotness, and their offload
> > enhancements (ASAP2 - which is sorta like DPDK on steroids) allows for
> > OVS flow rules programming into the card. We have a lot of customers
> > chomping at the bit for that feature (disclaimer I work for Nuage
> > Networks, and we are working on enhanced OVS to do just that) for NFV
> > workloads.
>
> What Jesper's been working on for ages has been to try and get linux's
> PPS up for small packets, which last I heard was hovering at about
> 4Gbits.
I hope you made a typo here Dave, the normal Linux kernel is definitely
way beyond 4Gbit/s, you must have misunderstood something, maybe you
meant 40Gbit/s? (which is also too low)
Scaling up to more CPUs and TCP-stream, Tariq[1] and I have showed the
Linux kernel network stack scales to 94Gbit/s (linerate minus overhead).
But when the drivers page-recycler fails, we hit bottlenecks in the
page-allocator, that cause negative scaling to around 43Gbit/s.
[1] http://lkml.kernel.org/r/cef85936-10b2-5d76-9f97-cb03b418fd94@mellanox.com
Linux have for a _long_ time been doing 10Gbit/s TCP-stream easily, on
a SINGLE CPU. This is mostly thanks to TSO/GRO aggregating packets,
but last couple of years the network stack have been optimized (with
UDP workloads), and as a result we can do 10G without TSO/GRO on a
single-CPU. This is "only" 812Kpps with MTU size frames.
It is important to NOTICE that I'm mostly talking about SINGLE-CPU
performance. But the Linux kernel scales very well to more CPUs, and
you can scale this up, although we are starting to hit scalability
issues in MM-land[1].
I've also demonstrated that netdev-community have optimized the kernels
per-CPU processing power to around 2Mpps. What does this really
mean... well with MTU size packets 812Kpps was 10Gbit/s, thus 25Gbit/s
should be around 2Mpps.... That implies Linux can do 25Gbit/s on a
single CPU without GRO (MTU size frames). Do you need more I ask?
> The route table lookup also really expensive on the main cpu.
Well, it used-to-be very expensive. Vincent Bernat wrote some excellent
blogposts[2][3] on the recent improvements over kernel versions, and
gave due credit to people involved.
[2] https://vincent.bernat.im/en/blog/2017-performance-progression-ipv4-route-lookup-linux
[3] https://vincent.bernat.im/en/blog/2017-performance-progression-ipv6-route-lookup-linux
He measured around 25 to 35 nanosec cost of route lookups. My own
recent measurements were 36.9 ns cost of fib_table_lookup.
> Does this stuff offload the route table lookup also?
If you have not heard, the netdev-community have worked on something
called XDP (eXpress Data Path). This is a new layer in the network
stack, that basically operates a the same "layer"/level as DPDK.
Thus, surprise we get the same performance numbers as DPDK. E.g. I can
do 13.4 Mpps forwarding with ixgbe on a single CPU (more CPUs=14.6Mps)
We can actually use XDP for (software) offloading the Linux routing
table. There are two methods we are experimenting with:
(1) externally monitor route changes from userspace and update BPF-maps
to reflect this. That approach is already accepted upstream[4][5]. I'm
measuring 9,513,746 pps per CPU with that approach.
(2) add a bpf helper to simply call fib_table_lookup() from the XDP hook.
This is still experimental patches (credit to David Ahern), and I've
measured 9,350,160 pps with this approach in a single CPU. Using more
CPUs we hit 14.6Mpps (only used 3 CPUs in that test)
[4] https://github.com/torvalds/linux/blob/master/samples/bpf/xdp_router_ipv4_user.c
[5] https://github.com/torvalds/linux/blob/master/samples/bpf/xdp_router_ipv4_kern.c
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
_______________________________________________
Bloat mailing list
Bloat@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/bloat
^ permalink raw reply
* RE: [PATCH net-next 0/8] Hisilicon Network Subsystem 3 VF Ethernet Driver
From: Salil Mehta @ 2017-12-04 10:48 UTC (permalink / raw)
To: gerlitz.or@gmail.com
Cc: davem@davemloft.net, Zhuangyuzeng (Yisen), lipeng (Y),
mehta.salil.lnk@gmail.com, netdev@vger.kernel.org,
andy@greyhouse.net, simon.horman@netronome.com, jiri@mellanox.com
In-Reply-To: <F4CC6FACFEB3C54C9141D49AD221F7F93BB5F85E@FRAEML521-MBX.china.huawei.com>
Hi Or,
>
> ---------- Forwarded message ----------
> From: Or Gerlitz <gerlitz.or@gmail.com>
> Date: Sun, Dec 3, 2017 at 1:22 PM
> Subject: Re: [PATCH net-next 0/8] Hisilicon Network Subsystem 3 VF
> Ethernet Driver
> To: Salil Mehta <salil.mehta@huawei.com>
> Cc: David Miller <davem@davemloft.net>, yisen.zhuang@huawei.com,
> lipeng321@huawei.com, mehta.salil.lnk@gmail.com, Linux Netdev List
> <netdev@vger.kernel.org>, Andy Gospodarek <andy@greyhouse.net>, Simon
> Horman <simon.horman@netronome.com>, Jiri Pirko <jiri@mellanox.com>
>
>
> On Sun, Dec 3, 2017 at 2:32 PM, Salil Mehta <salil.mehta@huawei.com>
> wrote:
> > This patch-set contains the support of the HNS3 (Hisilicon Network
> Subsystem 3)
> > Virtual Function Ethernet driver for hip08 family of SoCs. The
> Physical Function
> > driver is already part of the Linux mainline.
> >
> > This VF driver has its Hardware Compatibility Layer and has
> commom/unified ENET
> > layer/client/ethtool code with the PF driver. The basic architecture
> of VF driver
> > is derivative of the PF driver. Just like PF driver, this driver is
> also PCI
> > Express based.
>
> Hi,
>
> I wasn't sure if/what PF side control plane user space APIs are
> supported by this series,
> can you elaborate on that?
Current VF driver just supports very basic functionality. Idea was to
push basic RX/TX/RSS/TSO support along with this version.
> Please note that since 4.8, the kernel
> supports switchdev
> mode for SRIOV drivers and it's highly desirable for new drivers to
> support that. The old
> mode (called legacy) is inferior in functionality and design. We
> didn't do a clear statement
> asking new drivers not to support the legacy mode, but still, it would
> be good to support
> the new mode from day one.
We will support switchdev and other lined-up features after basic
version of the driver has gone through. We are in analysis phase right
now for all of these features.
Thanks
Salil
>
> Or.
^ permalink raw reply
* Re: [PATCH] netfilter: add overflow checks in xt_bpf.c
From: Pablo Neira Ayuso @ 2017-12-04 10:36 UTC (permalink / raw)
To: Jann Horn
Cc: Willem de Bruijn, Jozsef Kadlecsik, Florian Westphal,
David S. Miller, netdev, coreteam, netfilter-devel
In-Reply-To: <20171201004607.7389-1-jannh@google.com>
On Fri, Dec 01, 2017 at 01:46:07AM +0100, Jann Horn wrote:
> Check whether inputs from userspace are too long (explicit length field too
> big or string not null-terminated) to avoid out-of-bounds reads.
>
> As far as I can tell, this can at worst lead to very limited kernel heap
> memory disclosure or oopses.
>
> This bug can be triggered by an unprivileged user even if the xt_bpf module
> is not loaded: iptables is available in network namespaces, and the xt_bpf
> module can be autoloaded.
>
> Triggering the bug with a classic BPF filter with fake length 0x1000 causes
> the following KASAN report:
>
> ==================================================================
> BUG: KASAN: slab-out-of-bounds in bpf_prog_create+0x84/0xf0
> Read of size 32768 at addr ffff8801eff2c494 by task test/4627
>
> CPU: 0 PID: 4627 Comm: test Not tainted 4.15.0-rc1+ #1
> [...]
> Call Trace:
> dump_stack+0x5c/0x85
> print_address_description+0x6a/0x260
> kasan_report+0x254/0x370
> ? bpf_prog_create+0x84/0xf0
> memcpy+0x1f/0x50
> bpf_prog_create+0x84/0xf0
> bpf_mt_check+0x90/0xd6 [xt_bpf]
> [...]
> Allocated by task 4627:
> kasan_kmalloc+0xa0/0xd0
> __kmalloc_node+0x47/0x60
> xt_alloc_table_info+0x41/0x70 [x_tables]
> [...]
> The buggy address belongs to the object at ffff8801eff2c3c0
> which belongs to the cache kmalloc-2048 of size 2048
> The buggy address is located 212 bytes inside of
> 2048-byte region [ffff8801eff2c3c0, ffff8801eff2cbc0)
> [...]
> ==================================================================
Applied, thanks.
^ permalink raw reply
* [PATCH v4 1/4] phylib: Add device reset GPIO support
From: Geert Uytterhoeven @ 2017-12-04 10:34 UTC (permalink / raw)
To: David S . Miller, Andrew Lunn, Florian Fainelli, Simon Horman,
Magnus Damm
Cc: Sergei Shtylyov, Rob Herring, Mark Rutland, Nicolas Ferre,
Richard Leitner, netdev, devicetree, linux-renesas-soc,
linux-kernel, Geert Uytterhoeven
In-Reply-To: <1512383692-14009-1-git-send-email-geert+renesas@glider.be>
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
The PHY devices sometimes do have their reset signal (maybe even power
supply?) tied to some GPIO and sometimes it also does happen that a boot
loader does not leave it deasserted. So far this issue has been attacked
from (as I believe) a wrong angle: by teaching the MAC driver to manipulate
the GPIO in question; that solution, when applied to the device trees, led
to adding the PHY reset GPIO properties to the MAC device node, with one
exception: Cadence MACB driver which could handle the "reset-gpios" prop
in a PHY device subnode. I believe that the correct approach is to teach
the 'phylib' to get the MDIO device reset GPIO from the device tree node
corresponding to this device -- which this patch is doing...
Note that I had to modify the AT803x PHY driver as it would stop working
otherwise -- it made use of the reset GPIO for its own purposes...
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Acked-by: Rob Herring <robh@kernel.org>
[geert: Propagate actual errors from fwnode_get_named_gpiod()]
[geert: Avoid destroying initial setup]
[geert: Consolidate GPIO descriptor acquiring code]
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
v4:
- Remove Florian's Acked-by,
- Add missing #include <linux/gpio/consumer.h>,
- Re-add the gpiod check, as the dummy gpiod_set_value() for !GPIOLIB
does not ignore NULL, and calls WARN_ON(1),
- Do not reassert the reset signal if {mdio,phy}_probe() or
phy_device_register() succeeded, as that may destroy initial setup,
- Do not deassert the reset signal in {mdio,phy}_remove(), as it
should already be deasserted,
- Bring the PHY back into reset state in phy_device_remove(),
- Move/consolidate GPIO descriptor acquiring code from
of_mdiobus_register_phy() and of_mdiobus_register_device() to
mdiobus_register_device().
Note that this changes behavior slightly, in that the reset signal
is now also asserted when called from of_mdiobus_register_device().
v3:
- Fix fwnode_get_named_gpiod() call due to added parameters (which
allowed to eliminate the gpiod_direction_output() call),
- Undelete one blank line in the AT803x driver,
- Resolve rejects, refresh patch,
- Reword/reformat changelog,
- Take over from Sergei,
- Add Acked-by,
- Remove unneeded gpiod check, as gpiod_set_value() handles NULL fine,
- Handle fwnode_get_named_gpiod() errors correctly:
- -ENOENT is ignored (the GPIO is optional), and turned into NULL,
which allowed to remove all later !IS_ERR() checks,
- Other errors (incl. -EPROBE_DEFER) are propagated [*],
v2:
- Reformat changelog,
- Resolve rejects, refresh patch.
---
Documentation/devicetree/bindings/net/phy.txt | 2 ++
drivers/net/phy/at803x.c | 18 +++------------
drivers/net/phy/mdio_bus.c | 21 ++++++++++++++++++
drivers/net/phy/mdio_device.c | 25 +++++++++++++++++++--
drivers/net/phy/phy_device.c | 32 +++++++++++++++++++++++++--
include/linux/mdio.h | 3 +++
include/linux/phy.h | 5 +++++
7 files changed, 87 insertions(+), 19 deletions(-)
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index 77d0b2a61ffa96fc..c05479f5ac7cc837 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -53,6 +53,8 @@ Optional Properties:
to ensure the integrated PHY is used. The absence of this property indicates
the muxers should be configured so that the external PHY is used.
+- reset-gpios: The GPIO phandle and specifier for the PHY reset signal.
+
Example:
ethernet-phy@0 {
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index de7dd6566df7a364..29da7a3c7a3761c0 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -71,7 +71,6 @@ MODULE_LICENSE("GPL");
struct at803x_priv {
bool phy_reset:1;
- struct gpio_desc *gpiod_reset;
};
struct at803x_context {
@@ -254,22 +253,11 @@ static int at803x_probe(struct phy_device *phydev)
{
struct device *dev = &phydev->mdio.dev;
struct at803x_priv *priv;
- struct gpio_desc *gpiod_reset;
priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
- if (phydev->drv->phy_id != ATH8030_PHY_ID)
- goto does_not_require_reset_workaround;
-
- gpiod_reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
- if (IS_ERR(gpiod_reset))
- return PTR_ERR(gpiod_reset);
-
- priv->gpiod_reset = gpiod_reset;
-
-does_not_require_reset_workaround:
phydev->priv = priv;
return 0;
@@ -343,14 +331,14 @@ static void at803x_link_change_notify(struct phy_device *phydev)
* cannot recover from by software.
*/
if (phydev->state == PHY_NOLINK) {
- if (priv->gpiod_reset && !priv->phy_reset) {
+ if (phydev->mdio.reset && !priv->phy_reset) {
struct at803x_context context;
at803x_context_save(phydev, &context);
- gpiod_set_value(priv->gpiod_reset, 1);
+ phy_device_reset(phydev, 1);
msleep(1);
- gpiod_set_value(priv->gpiod_reset, 0);
+ phy_device_reset(phydev, 0);
msleep(1);
at803x_context_restore(phydev, &context);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 2df7b62c1a36811e..c97d55cd6679412e 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -38,6 +38,7 @@
#include <linux/phy.h>
#include <linux/io.h>
#include <linux/uaccess.h>
+#include <linux/gpio/consumer.h>
#include <asm/irq.h>
@@ -48,9 +49,26 @@
int mdiobus_register_device(struct mdio_device *mdiodev)
{
+ struct gpio_desc *gpiod;
+
if (mdiodev->bus->mdio_map[mdiodev->addr])
return -EBUSY;
+ /* Deassert the optional reset signal */
+ if (mdiodev->dev.of_node)
+ gpiod = fwnode_get_named_gpiod(&mdiodev->dev.of_node->fwnode,
+ "reset-gpios", 0, GPIOD_OUT_LOW,
+ "PHY reset");
+ if (PTR_ERR(gpiod) == -ENOENT)
+ gpiod = NULL;
+ else if (IS_ERR(gpiod))
+ return PTR_ERR(gpiod);
+
+ mdiodev->reset = gpiod;
+
+ /* Assert the reset signal again */
+ mdio_device_reset(mdiodev, 1);
+
mdiodev->bus->mdio_map[mdiodev->addr] = mdiodev;
return 0;
@@ -420,6 +438,9 @@ void mdiobus_unregister(struct mii_bus *bus)
if (!mdiodev)
continue;
+ if (mdiodev->reset)
+ gpiod_put(mdiodev->reset);
+
mdiodev->device_remove(mdiodev);
mdiodev->device_free(mdiodev);
}
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index e24f28924af8953d..75d97dd9fb281704 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -12,6 +12,8 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/errno.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
@@ -114,6 +116,13 @@ void mdio_device_remove(struct mdio_device *mdiodev)
}
EXPORT_SYMBOL(mdio_device_remove);
+void mdio_device_reset(struct mdio_device *mdiodev, int value)
+{
+ if (mdiodev->reset)
+ gpiod_set_value(mdiodev->reset, value);
+}
+EXPORT_SYMBOL(mdio_device_reset);
+
/**
* mdio_probe - probe an MDIO device
* @dev: device to probe
@@ -128,8 +137,16 @@ static int mdio_probe(struct device *dev)
struct mdio_driver *mdiodrv = to_mdio_driver(drv);
int err = 0;
- if (mdiodrv->probe)
+ if (mdiodrv->probe) {
+ /* Deassert the reset signal */
+ mdio_device_reset(mdiodev, 0);
+
err = mdiodrv->probe(mdiodev);
+ if (err) {
+ /* Assert the reset signal */
+ mdio_device_reset(mdiodev, 1);
+ }
+ }
return err;
}
@@ -140,9 +157,13 @@ static int mdio_remove(struct device *dev)
struct device_driver *drv = mdiodev->dev.driver;
struct mdio_driver *mdiodrv = to_mdio_driver(drv);
- if (mdiodrv->remove)
+ if (mdiodrv->remove) {
mdiodrv->remove(mdiodev);
+ /* Assert the reset signal */
+ mdio_device_reset(mdiodev, 1);
+ }
+
return 0;
}
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 8154fb706751e8ad..1de5e242b8b4cda3 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -632,6 +632,9 @@ int phy_device_register(struct phy_device *phydev)
if (err)
return err;
+ /* Deassert the reset signal */
+ phy_device_reset(phydev, 0);
+
/* Run all of the fixups for this PHY */
err = phy_scan_fixups(phydev);
if (err) {
@@ -650,6 +653,9 @@ int phy_device_register(struct phy_device *phydev)
return 0;
out:
+ /* Assert the reset signal */
+ phy_device_reset(phydev, 1);
+
mdiobus_unregister_device(&phydev->mdio);
return err;
}
@@ -666,6 +672,10 @@ EXPORT_SYMBOL(phy_device_register);
void phy_device_remove(struct phy_device *phydev)
{
device_del(&phydev->mdio.dev);
+
+ /* Assert the reset signal */
+ phy_device_reset(phydev, 1);
+
mdiobus_unregister_device(&phydev->mdio);
}
EXPORT_SYMBOL(phy_device_remove);
@@ -849,6 +859,9 @@ int phy_init_hw(struct phy_device *phydev)
{
int ret = 0;
+ /* Deassert the reset signal */
+ phy_device_reset(phydev, 0);
+
if (!phydev->drv || !phydev->drv->config_init)
return 0;
@@ -1126,6 +1139,9 @@ void phy_detach(struct phy_device *phydev)
put_device(&phydev->mdio.dev);
if (ndev_owner != bus->owner)
module_put(bus->owner);
+
+ /* Assert the reset signal */
+ phy_device_reset(phydev, 1);
}
EXPORT_SYMBOL(phy_detach);
@@ -1811,8 +1827,16 @@ static int phy_probe(struct device *dev)
/* Set the state to READY by default */
phydev->state = PHY_READY;
- if (phydev->drv->probe)
+ if (phydev->drv->probe) {
+ /* Deassert the reset signal */
+ phy_device_reset(phydev, 0);
+
err = phydev->drv->probe(phydev);
+ if (err) {
+ /* Assert the reset signal */
+ phy_device_reset(phydev, 1);
+ }
+ }
mutex_unlock(&phydev->lock);
@@ -1829,8 +1853,12 @@ static int phy_remove(struct device *dev)
phydev->state = PHY_DOWN;
mutex_unlock(&phydev->lock);
- if (phydev->drv && phydev->drv->remove)
+ if (phydev->drv && phydev->drv->remove) {
phydev->drv->remove(phydev);
+
+ /* Assert the reset signal */
+ phy_device_reset(phydev, 1);
+ }
phydev->drv = NULL;
return 0;
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index ca08ab16ecdc9b78..92d4e55ffe675637 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -12,6 +12,7 @@
#include <uapi/linux/mdio.h>
#include <linux/mod_devicetable.h>
+struct gpio_desc;
struct mii_bus;
/* Multiple levels of nesting are possible. However typically this is
@@ -39,6 +40,7 @@ struct mdio_device {
/* Bus address of the MDIO device (0-31) */
int addr;
int flags;
+ struct gpio_desc *reset;
};
#define to_mdio_device(d) container_of(d, struct mdio_device, dev)
@@ -71,6 +73,7 @@ void mdio_device_free(struct mdio_device *mdiodev);
struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr);
int mdio_device_register(struct mdio_device *mdiodev);
void mdio_device_remove(struct mdio_device *mdiodev);
+void mdio_device_reset(struct mdio_device *mdiodev, int value);
int mdio_driver_register(struct mdio_driver *drv);
void mdio_driver_unregister(struct mdio_driver *drv);
int mdio_device_bus_match(struct device *dev, struct device_driver *drv);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4962af37722ac2ea..6106ed915841c97e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -841,6 +841,11 @@ int phy_aneg_done(struct phy_device *phydev);
int phy_stop_interrupts(struct phy_device *phydev);
int phy_restart_aneg(struct phy_device *phydev);
+static inline void phy_device_reset(struct phy_device *phydev, int value)
+{
+ mdio_device_reset(&phydev->mdio, value);
+}
+
#define phydev_err(_phydev, format, args...) \
dev_err(&_phydev->mdio.dev, format, ##args)
--
2.7.4
^ permalink raw reply related
* [PATCH v4 4/4] arm64: dts: renesas: ulcb: Add EthernetAVB PHY reset
From: Geert Uytterhoeven @ 2017-12-04 10:34 UTC (permalink / raw)
To: David S . Miller, Andrew Lunn, Florian Fainelli, Simon Horman,
Magnus Damm
Cc: Sergei Shtylyov, Rob Herring, Mark Rutland, Nicolas Ferre,
Richard Leitner, netdev-u79uwXL29TY76Z2rM5mHXA,
devicetree-u79uwXL29TY76Z2rM5mHXA,
linux-renesas-soc-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Geert Uytterhoeven
In-Reply-To: <1512383692-14009-1-git-send-email-geert+renesas-gXvu3+zWzMSzQB+pC5nmwQ@public.gmane.org>
Describe the GPIO used to reset the Ethernet PHY for EthernetAVB.
This allows the driver to reset the PHY during probe and after system
resume.
On ULCB, the enable pin of the regulator providing PHY power is always
pulled high, but the driver may still need to reset the PHY if this
wasn't done by the bootloader before.
Inspired by patches in the BSP for the individual Salvator-X/XS boards
by Kazuya Mizuguchi.
Signed-off-by: Geert Uytterhoeven <geert+renesas-gXvu3+zWzMSzQB+pC5nmwQ@public.gmane.org>
---
Compile-tested only.
v4:
- No changes,
v3:
- Extract from series "[PATCH 0/4] ravb: Add PHY reset support", and
incorporate in this series,
- Move reset-gpios from the ethernet to the ethernet-phy node.
---
arch/arm64/boot/dts/renesas/ulcb.dtsi | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi
index 0d85b315ce711c8f..be91016e0b48f196 100644
--- a/arch/arm64/boot/dts/renesas/ulcb.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi
@@ -154,6 +154,7 @@
reg = <0>;
interrupt-parent = <&gpio2>;
interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
+ reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>;
};
};
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH v4 3/4] arm64: dts: renesas: salvator-common: Add EthernetAVB PHY reset
From: Geert Uytterhoeven @ 2017-12-04 10:34 UTC (permalink / raw)
To: David S . Miller, Andrew Lunn, Florian Fainelli, Simon Horman,
Magnus Damm
Cc: Sergei Shtylyov, Rob Herring, Mark Rutland, Nicolas Ferre,
Richard Leitner, netdev, devicetree, linux-renesas-soc,
linux-kernel, Geert Uytterhoeven
In-Reply-To: <1512383692-14009-1-git-send-email-geert+renesas@glider.be>
Describe the GPIO used to reset the Ethernet PHY for EthernetAVB.
This allows the driver to reset the PHY during probe and after system
resume.
This fixes Ethernet operation after resume from s2ram on Salvator-XS,
where the enable pin of the regulator providing PHY power is connected
to PRESETn, and PSCI powers down the SoC during system suspend.
On Salvator-X, the enable pin is always pulled high, but the driver may
still need to reset the PHY if this wasn't done by the bootloader
before.
Inspired by patches in the BSP for the individual Salvator-X/XS boards
by Kazuya Mizuguchi.
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
For proper PHY reset operation during system resume, this depends on
"[PATCH v4 1/4] phylib: Add device reset GPIO support".
However, this patch can be applied independently.
v4:
- No changes,
v3:
- Extract from series "[PATCH 0/4] ravb: Add PHY reset support", and
incorporate in this series,
- Move reset-gpios from the ethernet to the ethernet-phy node.
---
arch/arm64/boot/dts/renesas/salvator-common.dtsi | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index a298df74ca6c037f..6a9524ff881306cf 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -264,6 +264,7 @@
reg = <0>;
interrupt-parent = <&gpio2>;
interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
+ reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>;
};
};
--
2.7.4
^ permalink raw reply related
* [PATCH v4 2/4] macb: Kill PHY reset code
From: Geert Uytterhoeven @ 2017-12-04 10:34 UTC (permalink / raw)
To: David S . Miller, Andrew Lunn, Florian Fainelli, Simon Horman,
Magnus Damm
Cc: Sergei Shtylyov, Rob Herring, Mark Rutland, Nicolas Ferre,
Richard Leitner, netdev, devicetree, linux-renesas-soc,
linux-kernel, Geert Uytterhoeven
In-Reply-To: <1512383692-14009-1-git-send-email-geert+renesas@glider.be>
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
With the phylib now being aware of the "reset-gpios" PHY node property,
there should be no need to frob the PHY reset in this driver anymore...
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
v4:
- Add Reviewed-by,
v3:
- Resolve rejects due to the file being renamed, refresh the patch,
- Add code to reset PHY on probe error,
- Edit patch description,
- Take over from Sergei,
- Add Acked-by,
v2:
- No changes.
---
drivers/net/ethernet/cadence/macb.h | 1 -
drivers/net/ethernet/cadence/macb_main.c | 21 ---------------------
2 files changed, 22 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 3165c2ba58f97744..c50c5ec49b1dc585 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -1171,7 +1171,6 @@ struct macb {
unsigned int dma_burst_length;
phy_interface_t phy_interface;
- struct gpio_desc *reset_gpio;
/* AT91RM9200 transmit */
struct sk_buff *skb; /* holds skb until xmit interrupt completes */
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index c5fa87cdc6c401a7..3f0dfb20fdbcf936 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3803,7 +3803,6 @@ static int macb_probe(struct platform_device *pdev)
= macb_config->clk_init;
int (*init)(struct platform_device *) = macb_config->init;
struct device_node *np = pdev->dev.of_node;
- struct device_node *phy_node;
struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL;
unsigned int queue_mask, num_queues;
struct macb_platform_data *pdata;
@@ -3909,18 +3908,6 @@ static int macb_probe(struct platform_device *pdev)
else
macb_get_hwaddr(bp);
- /* Power up the PHY if there is a GPIO reset */
- phy_node = of_get_next_available_child(np, NULL);
- if (phy_node) {
- int gpio = of_get_named_gpio(phy_node, "reset-gpios", 0);
-
- if (gpio_is_valid(gpio)) {
- bp->reset_gpio = gpio_to_desc(gpio);
- gpiod_direction_output(bp->reset_gpio, 1);
- }
- }
- of_node_put(phy_node);
-
err = of_get_phy_mode(np);
if (err < 0) {
pdata = dev_get_platdata(&pdev->dev);
@@ -3967,10 +3954,6 @@ static int macb_probe(struct platform_device *pdev)
of_phy_deregister_fixed_link(np);
mdiobus_free(bp->mii_bus);
- /* Shutdown the PHY if there is a GPIO reset */
- if (bp->reset_gpio)
- gpiod_set_value(bp->reset_gpio, 0);
-
err_out_free_netdev:
free_netdev(dev);
@@ -4001,10 +3984,6 @@ static int macb_remove(struct platform_device *pdev)
dev->phydev = NULL;
mdiobus_free(bp->mii_bus);
- /* Shutdown the PHY if there is a GPIO reset */
- if (bp->reset_gpio)
- gpiod_set_value(bp->reset_gpio, 0);
-
unregister_netdev(dev);
clk_disable_unprepare(bp->tx_clk);
clk_disable_unprepare(bp->hclk);
--
2.7.4
^ permalink raw reply related
* [PATCH v4 0/4] Teach phylib hard-resetting devices
From: Geert Uytterhoeven @ 2017-12-04 10:34 UTC (permalink / raw)
To: David S . Miller, Andrew Lunn, Florian Fainelli, Simon Horman,
Magnus Damm
Cc: Sergei Shtylyov, Rob Herring, Mark Rutland, Nicolas Ferre,
Richard Leitner, netdev, devicetree, linux-renesas-soc,
linux-kernel, Geert Uytterhoeven
Hi David, Andrew, Florian, Simon, Magnus,
This patch series adds optional PHY reset support to phylib.
The first two patches are destined for David's net-next tree. They add
core PHY reset code, and update a driver that currently uses its own
reset code.
The last two patches are destined for Simon's renesas tree. They add
properties to describe the EthernetAVB PHY reset topology to the common
Salvator-X/XS and ULCB DTS files, which solves two issues:
1. On Salvator-XS, the enable pin of the regulator providing PHY power
is connected to PRESETn, and PSCI powers down the SoC during system
suspend. Hence a PHY reset is needed to restore network
functionality after system resume.
2. Linux should not rely on the boot loader having reset the PHY, but
should reset the PHY during driver probe.
Changes compared to v3:
- Remove Florian's Acked-by,
- Add missing #include <linux/gpio/consumer.h>,
- Re-add the gpiod check, as the dummy gpiod_set_value() for !GPIOLIB
does not ignore NULL, and calls WARN_ON(1),
- Do not reassert the reset signal if {mdio,phy}_probe() or
phy_device_register() succeeded, as that may destroy initial setup,
- Do not deassert the reset signal in {mdio,phy}_remove(), as it
should already be deasserted,
- Bring the PHY back into reset state in phy_device_remove(),
- Move/consolidate GPIO descriptor acquiring code from
of_mdiobus_register_phy() and of_mdiobus_register_device() to
mdiobus_register_device().
Note that this changes behavior slightly, in that the reset signal
is now also asserted when called from of_mdiobus_register_device().
- Add Reviewed-by,
Changes compared to v2, as sent by Sergei Shtylyov:
- Fix fwnode_get_named_gpiod() call due to added parameters (which
allowed to eliminate the gpiod_direction_output() call),
- Rebased, refreshed, reworded,
- Take over from Sergei,
- Add Acked-by,
- Remove unneeded gpiod check, as gpiod_set_value() handles NULL fine,
- Handle fwnode_get_named_gpiod() errors correctly:
- -ENOENT is ignored (the GPIO is optional), and turned into NULL,
which allowed to remove all later !IS_ERR() checks,
- Other errors (incl. -EPROBE_DEFER) are propagated,
- Extract DTS patches from series "[PATCH 0/4] ravb: Add PHY reset
support" (https://www.spinics.net/lists/netdev/msg457308.html), and
incorporate in this series, after moving reset-gpios from the
ethernet to the ethernet-phy node.
Given (1) the new reset-gpios DT property in the PHY node follows
established practises, (2) the DT binding change in the first patch has
been acked by Rob, and (3) the DTS patch does not cause any regressions
if it is applied before the PHY driver patches, the DTS patches can be
applied independently.
Thanks!
Geert Uytterhoeven (2):
arm64: dts: renesas: salvator-common: Add EthernetAVB PHY reset
arm64: dts: renesas: ulcb: Add EthernetAVB PHY reset
Sergei Shtylyov (2):
phylib: Add device reset GPIO support
macb: Kill PHY reset code
Documentation/devicetree/bindings/net/phy.txt | 2 ++
arch/arm64/boot/dts/renesas/salvator-common.dtsi | 1 +
arch/arm64/boot/dts/renesas/ulcb.dtsi | 1 +
drivers/net/ethernet/cadence/macb.h | 1 -
drivers/net/ethernet/cadence/macb_main.c | 21 ----------------
drivers/net/phy/at803x.c | 18 +++----------
drivers/net/phy/mdio_bus.c | 21 ++++++++++++++++
drivers/net/phy/mdio_device.c | 25 ++++++++++++++++--
drivers/net/phy/phy_device.c | 32 ++++++++++++++++++++++--
include/linux/mdio.h | 3 +++
include/linux/phy.h | 5 ++++
11 files changed, 89 insertions(+), 41 deletions(-)
--
2.7.4
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
^ permalink raw reply
* [PATCH net-next] flow_dissector: dissect tunnel info outside __skb_flow_dissect()
From: Simon Horman @ 2017-12-04 10:31 UTC (permalink / raw)
To: David Miller, Jiri Pirko
Cc: Jamal Hadi Salim, Cong Wang, netdev, oss-drivers, Tom Herbert,
Willem de Bruijn, Simon Horman
Move dissection of tunnel info to outside of the main flow dissection
function, __skb_flow_dissect(). The sole user of this feature, the flower
classifier, is updated to call tunnel info dissection directly, using
skb_flow_dissect_tunnel_info().
This results in a slightly less complex implementation of
__skb_flow_dissect(), in particular removing logic from that call path
which is not used by the majority of users. The expense of this is borne by
the flower classifier which now has to make an extra call for tunnel info
dissection.
This patch should not result in any behavioural change.
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
include/linux/skbuff.h | 5 +++++
net/core/flow_dissector.c | 12 +++++-------
net/sched/cls_flower.c | 1 +
3 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bc486ef23f20..7d053bbaa5d1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1211,6 +1211,11 @@ static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow,
data, proto, nhoff, hlen, flags);
}
+void
+skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container);
+
static inline __u32 skb_get_hash(struct sk_buff *skb)
{
if (!skb->l4_hash && !skb->sw_hash)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 15ce30063765..cc75488d3653 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -133,10 +133,10 @@ skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type,
ctrl->addr_type = type;
}
-static void
-__skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
- struct flow_dissector *flow_dissector,
- void *target_container)
+void
+skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
+ struct flow_dissector *flow_dissector,
+ void *target_container)
{
struct ip_tunnel_info *info;
struct ip_tunnel_key *key;
@@ -212,6 +212,7 @@ __skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
tp->dst = key->tp_dst;
}
}
+EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
static enum flow_dissect_ret
__skb_flow_dissect_mpls(const struct sk_buff *skb,
@@ -576,9 +577,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
FLOW_DISSECTOR_KEY_BASIC,
target_container);
- __skb_flow_dissect_tunnel_info(skb, flow_dissector,
- target_container);
-
if (dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
struct ethhdr *eth = eth_hdr(skb);
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 543a3e875d05..6132a7317efa 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -166,6 +166,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
* so do it rather here.
*/
skb_key.basic.n_proto = skb->protocol;
+ skb_flow_dissect_tunnel_info(skb, &head->dissector, &skb_key);
skb_flow_dissect(skb, &head->dissector, &skb_key, 0);
fl_set_masked_key(&skb_mkey, &skb_key, &head->mask);
--
2.11.0
^ permalink raw reply related
* Re: [Bridge] [PATCH net-next] bridge: ebtables: Avoid resetting limit rule state
From: Pablo Neira Ayuso @ 2017-12-04 10:13 UTC (permalink / raw)
To: Linus Lüssing
Cc: netdev, bridge, Florian Westphal, linux-kernel, coreteam,
netfilter-devel, Jozsef Kadlecsik, David S . Miller
In-Reply-To: <20171204052006.GF3307@otheros>
On Mon, Dec 04, 2017 at 06:20:06AM +0100, Linus Lüssing wrote:
> On Mon, Dec 04, 2017 at 05:53:35AM +0100, Linus Lüssing wrote:
> > And so, no I do not have this patch. I looked at it now, but it
> > does not seem to have any relation with .matchinfo, does it?
>
> Relation between .usersize and .checkentry I ment, not
> .usersize and .matchinfo.
In your patch, info->prev comes set to a value from userspace, right?
commit 324318f0248c31be8a08984146e7e4dd7cdd091d
Author: Willem de Bruijn <willemb@google.com>
Date: Tue May 9 16:17:37 2017 -0400
netfilter: xtables: zero padding in data_to_user
Since that patch above, the data area is zero'ed before dumped to
userspace, so we would get a null info->prev, hence defeating the
trick your patch relies on.
Am I missing anything?
^ permalink raw reply
* Re: [RFC PATCH] net_sched: bulk free tcf_block
From: Paolo Abeni @ 2017-12-04 10:12 UTC (permalink / raw)
To: Cong Wang
Cc: Linux Kernel Network Developers, Jamal Hadi Salim, Jiri Pirko,
David S. Miller
In-Reply-To: <CAM_iQpU7rXqE0iXQzr5kJx2ab_v6OXmL1drt+VJYJAGoL5dyug@mail.gmail.com>
Hi,
On Fri, 2017-12-01 at 14:07 -0800, Cong Wang wrote:
> On Fri, Dec 1, 2017 at 3:05 AM, Paolo Abeni <pabeni@redhat.com> wrote:
> >
> > Thank you for the feedback.
> >
> > I tested your patch and in the above scenario I measure:
> >
> > real 0m0.017s
> > user 0m0.000s
> > sys 0m0.017s
> >
> > so it apparently works well for this case.
>
> Thanks a lot for testing it! I will test it further. If it goes well I will
> send a formal patch with your Tested-by unless you object it.
I'm in late, but I was fine with the above ;)
> > We could still have a storm of rtnl lock/unlock operations while
> > deleting a large tc tree with lot of filters, and I think we can reduce
> > them with bulk free, evenutally applying it to filters, too.
> >
> > That will also reduce the pressure on the rtnl lock when e.g. OVS H/W
> > offload pushes a lot of rules/sec.
> >
> > WDYT?
> >
>
> Why this is specific to tc filter? From what you are saying, we need to
> batch all TC operations (qdisc, filter and action) rather than just filter?
Exactly, the idea would be to batch all the delayed works. I started
with blocks, to somewhat tackle the issue seen on qdisc removal.
> In short term, I think batching rtnl lock/unlock is a good optimization,
> so I have no objection. For long term, I think we need to revise RTNL
> lock and probably move it down to each layer, but clearly it requires
> much more work.
Agreed!
Paolo
^ permalink raw reply
* Re: [PATCH 1/3] dt-bindings: Add optional nvmem MAC address bindings to ti,wlink-st
From: Sergei Shtylyov @ 2017-12-04 10:09 UTC (permalink / raw)
To: David Lechner, devicetree-u79uwXL29TY76Z2rM5mHXA,
linux-bluetooth-u79uwXL29TY76Z2rM5mHXA
Cc: Rob Herring, Mark Rutland, Marcel Holtmann, Gustavo Padovan,
Johan Hedberg, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <2dfb7130-e229-7429-0f30-11d7df553fdf-M4DtvfQ/ZS1MRgGoP+s0PdBPR1lH4CV8@public.gmane.org>
On 12/4/2017 12:54 PM, Sergei Shtylyov wrote:
>> This adds optional nvmem consumer properties to the ti,wlink-st device tree
>> bindings to allow specifying the Bluetooth MAC address.
>>
>> Signed-off-by: David Lechner <david-nq/r/kbU++upp/zk7JDF2g@public.gmane.org>
>> ---
>> Documentation/devicetree/bindings/net/ti,wilink-st.txt | 4 ++++
>> 1 file changed, 4 insertions(+)
>>
>> diff --git a/Documentation/devicetree/bindings/net/ti,wilink-st.txt
>> b/Documentation/devicetree/bindings/net/ti,wilink-st.txt
>> index 1649c1f..24eb897 100644
>> --- a/Documentation/devicetree/bindings/net/ti,wilink-st.txt
>> +++ b/Documentation/devicetree/bindings/net/ti,wilink-st.txt
>> @@ -32,6 +32,8 @@ Optional properties:
>> See ../clocks/clock-bindings.txt for details.
>> - clock-names : Must include the following entry:
>> "ext_clock" (External clock provided to the TI combo chip).
>> + - nvmem-cells: phandle to nvmem data cell that contains a MAC address
>> + - nvmem-cell-names: "mac-address" (required when nvmem-cells is specified)
>> Example:
>> @@ -43,5 +45,7 @@ Example:
>> enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
>> clocks = <&clk32k_wl18xx>;
>> clock-names = "ext_clock";
>> + nvmem-cells: <&mac_address>
>
> s/:/ = /?
>
>> + nvmem-cell-names "mac-address"
>
> Where's =?
And ;? :-)
[...]
MBR, Sergei
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'
From: Daniel Borkmann @ 2017-12-04 9:57 UTC (permalink / raw)
To: Al Viro
Cc: Kees Cook, Shmulik Ladkani, Willem de Bruijn, Pablo Neira Ayuso,
Linus Torvalds, David Miller, LKML, Network Development,
Christoph Hellwig, Thomas Garnier, Jann Horn
In-Reply-To: <20171202184850.GQ21978@ZenIV.linux.org.uk>
On 12/02/2017 07:48 PM, Al Viro wrote:
> On Fri, Dec 01, 2017 at 09:47:00PM +0100, Daniel Borkmann wrote:
>>> Might want to replace security_path_mknod() with something saner, while we are
>>> at it.
>>>
>>> Objections?
>>
>> No, thanks for looking into this, and sorry for this fugly hack! :( Not
>> that this doesn't make it any better, but I think back then I took it
>> over from mqueue implementation ... should have known better and looking
>> into making this generic instead, sigh. The above looks good to me, so
>> no objections from my side and thanks for working on it!
>>
>>> PS: mqueue.c would also benefit from such primitive - do_create() there would
>>> simply pass attr as callback's argument into vfs_mkobj(), with callback being
>>> the guts of mqueue_create()...
>
> OK... See vfs.git#untested.mkobj; it really needs testing, though - mq_open(2)
> passes LTP tests, but that's not saying much, and BPF side is completely
> untested.
I pulled vfs.git#untested.mkobj into my local tree and ran tests for both
progs and maps on it, all went fine and the patch looks good to me.
For 'bpf_obj_do_pin(): switch to vfs_mkobj(), quit abusing ->mknod()' when
you push the fix to Linus, feel free to add:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Thanks for your help, Al!
^ permalink raw reply
* [PATCH v2 6/6] perf s390: add regs_query_register_offset()
From: Hendrik Brueckner @ 2017-12-04 9:56 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Alexei Starovoitov, Daniel Borkmann,
Martin Schwidefsky, Will Deacon, Ingo Molnar
Cc: Arnd Bergmann, Peter Zijlstra, David S. Miller, linux-kernel,
linux-s390, netdev
In-Reply-To: <1512381409-19775-1-git-send-email-brueckner@linux.vnet.ibm.com>
The regs_query_register_offset() helper function converts
register name like "%r0" to an offset of a register in user_pt_regs
It is required by the BPF prologue generator.
The user_pt_regs structure was recently added to "asm/ptrace.h".
Hence, update tools/perf/check-headers.sh to keep the header file
in sync with kernel changes.
Suggested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-and-tested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
---
tools/perf/arch/s390/Makefile | 1 +
tools/perf/arch/s390/util/dwarf-regs.c | 32 +++++++++++++++++++++++++++++---
| 1 +
3 files changed, 31 insertions(+), 3 deletions(-)
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 21322e0..09ba923 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
endif
HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
index f47576c..a8ace5c 100644
--- a/tools/perf/arch/s390/util/dwarf-regs.c
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -2,17 +2,43 @@
/*
* Mapping of DWARF debug register numbers into register names.
*
- * Copyright IBM Corp. 2010
- * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ * Copyright IBM Corp. 2010, 2017
+ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ * Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
*
*/
+#include <errno.h>
#include <stddef.h>
-#include <dwarf-regs.h>
+#include <stdlib.h>
#include <linux/kernel.h>
+#include <asm/ptrace.h>
+#include <string.h>
+#include <dwarf-regs.h>
#include "dwarf-regs-table.h"
const char *get_arch_regstr(unsigned int n)
{
return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n];
}
+
+/*
+ * Convert the register name into an offset to struct pt_regs (kernel).
+ * This is required by the BPF prologue generator. The BPF
+ * program is called in the BPF overflow handler in the perf
+ * core.
+ */
+int regs_query_register_offset(const char *name)
+{
+ unsigned long gpr;
+
+ if (!name || strncmp(name, "%r", 2))
+ return -EINVAL;
+
+ errno = 0;
+ gpr = strtoul(name + 2, NULL, 10);
+ if (errno || gpr >= 16)
+ return -EINVAL;
+
+ return offsetof(user_pt_regs, gprs) + 8 * gpr;
+}
--git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 77406d2..6db9d80 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -30,6 +30,7 @@ arch/x86/include/uapi/asm/vmx.h
arch/powerpc/include/uapi/asm/kvm.h
arch/s390/include/uapi/asm/kvm.h
arch/s390/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/ptrace.h
arch/s390/include/uapi/asm/sie.h
arch/arm/include/uapi/asm/kvm.h
arch/arm64/include/uapi/asm/kvm.h
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 5/6] selftests/bpf: sync kernel headers and introduce arch support in Makefile
From: Hendrik Brueckner @ 2017-12-04 9:56 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Alexei Starovoitov, Daniel Borkmann,
Martin Schwidefsky, Will Deacon, Ingo Molnar
Cc: Arnd Bergmann, Peter Zijlstra, David S. Miller, linux-kernel,
linux-s390, netdev
In-Reply-To: <1512381409-19775-1-git-send-email-brueckner@linux.vnet.ibm.com>
Synchronize the uapi kernel header files which solves the broken
uapi export of pt_regs. Because of arch-specific uapi headers,
extended the include path in the Makefile.
With this change, the test_verifier program compiles and runs successfully
on s390.
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-and-tested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Shuah Khan <shuah@kernel.org>
---
tools/arch/arm64/include/uapi/asm/bpf_perf_event.h | 9 +
tools/arch/s390/include/uapi/asm/bpf_perf_event.h | 9 +
tools/arch/s390/include/uapi/asm/ptrace.h | 457 +++++++++++++++++++++
tools/include/uapi/asm-generic/bpf_perf_event.h | 9 +
tools/include/uapi/linux/bpf_perf_event.h | 6 +-
tools/testing/selftests/bpf/Makefile | 14 +-
6 files changed, 500 insertions(+), 4 deletions(-)
create mode 100644 tools/arch/arm64/include/uapi/asm/bpf_perf_event.h
create mode 100644 tools/arch/s390/include/uapi/asm/bpf_perf_event.h
create mode 100644 tools/arch/s390/include/uapi/asm/ptrace.h
create mode 100644 tools/include/uapi/asm-generic/bpf_perf_event.h
diff --git a/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h b/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 0000000..b551b74
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/tools/arch/s390/include/uapi/asm/bpf_perf_event.h b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 0000000..cefe7c7
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/tools/arch/s390/include/uapi/asm/ptrace.h b/tools/arch/s390/include/uapi/asm/ptrace.h
new file mode 100644
index 0000000..543dd70
--- /dev/null
+++ b/tools/arch/s390/include/uapi/asm/ptrace.h
@@ -0,0 +1,457 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * S390 version
+ * Copyright IBM Corp. 1999, 2000
+ * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ */
+
+#ifndef _UAPI_S390_PTRACE_H
+#define _UAPI_S390_PTRACE_H
+
+/*
+ * Offsets in the user_regs_struct. They are used for the ptrace
+ * system call and in entry.S
+ */
+#ifndef __s390x__
+
+#define PT_PSWMASK 0x00
+#define PT_PSWADDR 0x04
+#define PT_GPR0 0x08
+#define PT_GPR1 0x0C
+#define PT_GPR2 0x10
+#define PT_GPR3 0x14
+#define PT_GPR4 0x18
+#define PT_GPR5 0x1C
+#define PT_GPR6 0x20
+#define PT_GPR7 0x24
+#define PT_GPR8 0x28
+#define PT_GPR9 0x2C
+#define PT_GPR10 0x30
+#define PT_GPR11 0x34
+#define PT_GPR12 0x38
+#define PT_GPR13 0x3C
+#define PT_GPR14 0x40
+#define PT_GPR15 0x44
+#define PT_ACR0 0x48
+#define PT_ACR1 0x4C
+#define PT_ACR2 0x50
+#define PT_ACR3 0x54
+#define PT_ACR4 0x58
+#define PT_ACR5 0x5C
+#define PT_ACR6 0x60
+#define PT_ACR7 0x64
+#define PT_ACR8 0x68
+#define PT_ACR9 0x6C
+#define PT_ACR10 0x70
+#define PT_ACR11 0x74
+#define PT_ACR12 0x78
+#define PT_ACR13 0x7C
+#define PT_ACR14 0x80
+#define PT_ACR15 0x84
+#define PT_ORIGGPR2 0x88
+#define PT_FPC 0x90
+/*
+ * A nasty fact of life that the ptrace api
+ * only supports passing of longs.
+ */
+#define PT_FPR0_HI 0x98
+#define PT_FPR0_LO 0x9C
+#define PT_FPR1_HI 0xA0
+#define PT_FPR1_LO 0xA4
+#define PT_FPR2_HI 0xA8
+#define PT_FPR2_LO 0xAC
+#define PT_FPR3_HI 0xB0
+#define PT_FPR3_LO 0xB4
+#define PT_FPR4_HI 0xB8
+#define PT_FPR4_LO 0xBC
+#define PT_FPR5_HI 0xC0
+#define PT_FPR5_LO 0xC4
+#define PT_FPR6_HI 0xC8
+#define PT_FPR6_LO 0xCC
+#define PT_FPR7_HI 0xD0
+#define PT_FPR7_LO 0xD4
+#define PT_FPR8_HI 0xD8
+#define PT_FPR8_LO 0XDC
+#define PT_FPR9_HI 0xE0
+#define PT_FPR9_LO 0xE4
+#define PT_FPR10_HI 0xE8
+#define PT_FPR10_LO 0xEC
+#define PT_FPR11_HI 0xF0
+#define PT_FPR11_LO 0xF4
+#define PT_FPR12_HI 0xF8
+#define PT_FPR12_LO 0xFC
+#define PT_FPR13_HI 0x100
+#define PT_FPR13_LO 0x104
+#define PT_FPR14_HI 0x108
+#define PT_FPR14_LO 0x10C
+#define PT_FPR15_HI 0x110
+#define PT_FPR15_LO 0x114
+#define PT_CR_9 0x118
+#define PT_CR_10 0x11C
+#define PT_CR_11 0x120
+#define PT_IEEE_IP 0x13C
+#define PT_LASTOFF PT_IEEE_IP
+#define PT_ENDREGS 0x140-1
+
+#define GPR_SIZE 4
+#define CR_SIZE 4
+
+#define STACK_FRAME_OVERHEAD 96 /* size of minimum stack frame */
+
+#else /* __s390x__ */
+
+#define PT_PSWMASK 0x00
+#define PT_PSWADDR 0x08
+#define PT_GPR0 0x10
+#define PT_GPR1 0x18
+#define PT_GPR2 0x20
+#define PT_GPR3 0x28
+#define PT_GPR4 0x30
+#define PT_GPR5 0x38
+#define PT_GPR6 0x40
+#define PT_GPR7 0x48
+#define PT_GPR8 0x50
+#define PT_GPR9 0x58
+#define PT_GPR10 0x60
+#define PT_GPR11 0x68
+#define PT_GPR12 0x70
+#define PT_GPR13 0x78
+#define PT_GPR14 0x80
+#define PT_GPR15 0x88
+#define PT_ACR0 0x90
+#define PT_ACR1 0x94
+#define PT_ACR2 0x98
+#define PT_ACR3 0x9C
+#define PT_ACR4 0xA0
+#define PT_ACR5 0xA4
+#define PT_ACR6 0xA8
+#define PT_ACR7 0xAC
+#define PT_ACR8 0xB0
+#define PT_ACR9 0xB4
+#define PT_ACR10 0xB8
+#define PT_ACR11 0xBC
+#define PT_ACR12 0xC0
+#define PT_ACR13 0xC4
+#define PT_ACR14 0xC8
+#define PT_ACR15 0xCC
+#define PT_ORIGGPR2 0xD0
+#define PT_FPC 0xD8
+#define PT_FPR0 0xE0
+#define PT_FPR1 0xE8
+#define PT_FPR2 0xF0
+#define PT_FPR3 0xF8
+#define PT_FPR4 0x100
+#define PT_FPR5 0x108
+#define PT_FPR6 0x110
+#define PT_FPR7 0x118
+#define PT_FPR8 0x120
+#define PT_FPR9 0x128
+#define PT_FPR10 0x130
+#define PT_FPR11 0x138
+#define PT_FPR12 0x140
+#define PT_FPR13 0x148
+#define PT_FPR14 0x150
+#define PT_FPR15 0x158
+#define PT_CR_9 0x160
+#define PT_CR_10 0x168
+#define PT_CR_11 0x170
+#define PT_IEEE_IP 0x1A8
+#define PT_LASTOFF PT_IEEE_IP
+#define PT_ENDREGS 0x1B0-1
+
+#define GPR_SIZE 8
+#define CR_SIZE 8
+
+#define STACK_FRAME_OVERHEAD 160 /* size of minimum stack frame */
+
+#endif /* __s390x__ */
+
+#define NUM_GPRS 16
+#define NUM_FPRS 16
+#define NUM_CRS 16
+#define NUM_ACRS 16
+
+#define NUM_CR_WORDS 3
+
+#define FPR_SIZE 8
+#define FPC_SIZE 4
+#define FPC_PAD_SIZE 4 /* gcc insists on aligning the fpregs */
+#define ACR_SIZE 4
+
+
+#define PTRACE_OLDSETOPTIONS 21
+
+#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+typedef union {
+ float f;
+ double d;
+ __u64 ui;
+ struct
+ {
+ __u32 hi;
+ __u32 lo;
+ } fp;
+} freg_t;
+
+typedef struct {
+ __u32 fpc;
+ __u32 pad;
+ freg_t fprs[NUM_FPRS];
+} s390_fp_regs;
+
+#define FPC_EXCEPTION_MASK 0xF8000000
+#define FPC_FLAGS_MASK 0x00F80000
+#define FPC_DXC_MASK 0x0000FF00
+#define FPC_RM_MASK 0x00000003
+
+/* this typedef defines how a Program Status Word looks like */
+typedef struct {
+ unsigned long mask;
+ unsigned long addr;
+} __attribute__ ((aligned(8))) psw_t;
+
+#ifndef __s390x__
+
+#define PSW_MASK_PER 0x40000000UL
+#define PSW_MASK_DAT 0x04000000UL
+#define PSW_MASK_IO 0x02000000UL
+#define PSW_MASK_EXT 0x01000000UL
+#define PSW_MASK_KEY 0x00F00000UL
+#define PSW_MASK_BASE 0x00080000UL /* always one */
+#define PSW_MASK_MCHECK 0x00040000UL
+#define PSW_MASK_WAIT 0x00020000UL
+#define PSW_MASK_PSTATE 0x00010000UL
+#define PSW_MASK_ASC 0x0000C000UL
+#define PSW_MASK_CC 0x00003000UL
+#define PSW_MASK_PM 0x00000F00UL
+#define PSW_MASK_RI 0x00000000UL
+#define PSW_MASK_EA 0x00000000UL
+#define PSW_MASK_BA 0x00000000UL
+
+#define PSW_MASK_USER 0x0000FF00UL
+
+#define PSW_ADDR_AMODE 0x80000000UL
+#define PSW_ADDR_INSN 0x7FFFFFFFUL
+
+#define PSW_DEFAULT_KEY (((unsigned long) PAGE_DEFAULT_ACC) << 20)
+
+#define PSW_ASC_PRIMARY 0x00000000UL
+#define PSW_ASC_ACCREG 0x00004000UL
+#define PSW_ASC_SECONDARY 0x00008000UL
+#define PSW_ASC_HOME 0x0000C000UL
+
+#else /* __s390x__ */
+
+#define PSW_MASK_PER 0x4000000000000000UL
+#define PSW_MASK_DAT 0x0400000000000000UL
+#define PSW_MASK_IO 0x0200000000000000UL
+#define PSW_MASK_EXT 0x0100000000000000UL
+#define PSW_MASK_BASE 0x0000000000000000UL
+#define PSW_MASK_KEY 0x00F0000000000000UL
+#define PSW_MASK_MCHECK 0x0004000000000000UL
+#define PSW_MASK_WAIT 0x0002000000000000UL
+#define PSW_MASK_PSTATE 0x0001000000000000UL
+#define PSW_MASK_ASC 0x0000C00000000000UL
+#define PSW_MASK_CC 0x0000300000000000UL
+#define PSW_MASK_PM 0x00000F0000000000UL
+#define PSW_MASK_RI 0x0000008000000000UL
+#define PSW_MASK_EA 0x0000000100000000UL
+#define PSW_MASK_BA 0x0000000080000000UL
+
+#define PSW_MASK_USER 0x0000FF0180000000UL
+
+#define PSW_ADDR_AMODE 0x0000000000000000UL
+#define PSW_ADDR_INSN 0xFFFFFFFFFFFFFFFFUL
+
+#define PSW_DEFAULT_KEY (((unsigned long) PAGE_DEFAULT_ACC) << 52)
+
+#define PSW_ASC_PRIMARY 0x0000000000000000UL
+#define PSW_ASC_ACCREG 0x0000400000000000UL
+#define PSW_ASC_SECONDARY 0x0000800000000000UL
+#define PSW_ASC_HOME 0x0000C00000000000UL
+
+#endif /* __s390x__ */
+
+
+/*
+ * The s390_regs structure is used to define the elf_gregset_t.
+ */
+typedef struct {
+ psw_t psw;
+ unsigned long gprs[NUM_GPRS];
+ unsigned int acrs[NUM_ACRS];
+ unsigned long orig_gpr2;
+} s390_regs;
+
+/*
+ * The user_pt_regs structure exports the beginning of
+ * the in-kernel pt_regs structure to user space.
+ */
+typedef struct {
+ unsigned long args[1];
+ psw_t psw;
+ unsigned long gprs[NUM_GPRS];
+} user_pt_regs;
+
+/*
+ * Now for the user space program event recording (trace) definitions.
+ * The following structures are used only for the ptrace interface, don't
+ * touch or even look at it if you don't want to modify the user-space
+ * ptrace interface. In particular stay away from it for in-kernel PER.
+ */
+typedef struct {
+ unsigned long cr[NUM_CR_WORDS];
+} per_cr_words;
+
+#define PER_EM_MASK 0xE8000000UL
+
+typedef struct {
+#ifdef __s390x__
+ unsigned : 32;
+#endif /* __s390x__ */
+ unsigned em_branching : 1;
+ unsigned em_instruction_fetch : 1;
+ /*
+ * Switching on storage alteration automatically fixes
+ * the storage alteration event bit in the users std.
+ */
+ unsigned em_storage_alteration : 1;
+ unsigned em_gpr_alt_unused : 1;
+ unsigned em_store_real_address : 1;
+ unsigned : 3;
+ unsigned branch_addr_ctl : 1;
+ unsigned : 1;
+ unsigned storage_alt_space_ctl : 1;
+ unsigned : 21;
+ unsigned long starting_addr;
+ unsigned long ending_addr;
+} per_cr_bits;
+
+typedef struct {
+ unsigned short perc_atmid;
+ unsigned long address;
+ unsigned char access_id;
+} per_lowcore_words;
+
+typedef struct {
+ unsigned perc_branching : 1;
+ unsigned perc_instruction_fetch : 1;
+ unsigned perc_storage_alteration : 1;
+ unsigned perc_gpr_alt_unused : 1;
+ unsigned perc_store_real_address : 1;
+ unsigned : 3;
+ unsigned atmid_psw_bit_31 : 1;
+ unsigned atmid_validity_bit : 1;
+ unsigned atmid_psw_bit_32 : 1;
+ unsigned atmid_psw_bit_5 : 1;
+ unsigned atmid_psw_bit_16 : 1;
+ unsigned atmid_psw_bit_17 : 1;
+ unsigned si : 2;
+ unsigned long address;
+ unsigned : 4;
+ unsigned access_id : 4;
+} per_lowcore_bits;
+
+typedef struct {
+ union {
+ per_cr_words words;
+ per_cr_bits bits;
+ } control_regs;
+ /*
+ * The single_step and instruction_fetch bits are obsolete,
+ * the kernel always sets them to zero. To enable single
+ * stepping use ptrace(PTRACE_SINGLESTEP) instead.
+ */
+ unsigned single_step : 1;
+ unsigned instruction_fetch : 1;
+ unsigned : 30;
+ /*
+ * These addresses are copied into cr10 & cr11 if single
+ * stepping is switched off
+ */
+ unsigned long starting_addr;
+ unsigned long ending_addr;
+ union {
+ per_lowcore_words words;
+ per_lowcore_bits bits;
+ } lowcore;
+} per_struct;
+
+typedef struct {
+ unsigned int len;
+ unsigned long kernel_addr;
+ unsigned long process_addr;
+} ptrace_area;
+
+/*
+ * S/390 specific non posix ptrace requests. I chose unusual values so
+ * they are unlikely to clash with future ptrace definitions.
+ */
+#define PTRACE_PEEKUSR_AREA 0x5000
+#define PTRACE_POKEUSR_AREA 0x5001
+#define PTRACE_PEEKTEXT_AREA 0x5002
+#define PTRACE_PEEKDATA_AREA 0x5003
+#define PTRACE_POKETEXT_AREA 0x5004
+#define PTRACE_POKEDATA_AREA 0x5005
+#define PTRACE_GET_LAST_BREAK 0x5006
+#define PTRACE_PEEK_SYSTEM_CALL 0x5007
+#define PTRACE_POKE_SYSTEM_CALL 0x5008
+#define PTRACE_ENABLE_TE 0x5009
+#define PTRACE_DISABLE_TE 0x5010
+#define PTRACE_TE_ABORT_RAND 0x5011
+
+/*
+ * The numbers chosen here are somewhat arbitrary but absolutely MUST
+ * not overlap with any of the number assigned in <linux/ptrace.h>.
+ */
+#define PTRACE_SINGLEBLOCK 12 /* resume execution until next branch */
+
+/*
+ * PT_PROT definition is loosely based on hppa bsd definition in
+ * gdb/hppab-nat.c
+ */
+#define PTRACE_PROT 21
+
+typedef enum {
+ ptprot_set_access_watchpoint,
+ ptprot_set_write_watchpoint,
+ ptprot_disable_watchpoint
+} ptprot_flags;
+
+typedef struct {
+ unsigned long lowaddr;
+ unsigned long hiaddr;
+ ptprot_flags prot;
+} ptprot_area;
+
+/* Sequence of bytes for breakpoint illegal instruction. */
+#define S390_BREAKPOINT {0x0,0x1}
+#define S390_BREAKPOINT_U16 ((__u16)0x0001)
+#define S390_SYSCALL_OPCODE ((__u16)0x0a00)
+#define S390_SYSCALL_SIZE 2
+
+/*
+ * The user_regs_struct defines the way the user registers are
+ * store on the stack for signal handling.
+ */
+struct user_regs_struct {
+ psw_t psw;
+ unsigned long gprs[NUM_GPRS];
+ unsigned int acrs[NUM_ACRS];
+ unsigned long orig_gpr2;
+ s390_fp_regs fp_regs;
+ /*
+ * These per registers are in here so that gdb can modify them
+ * itself as there is no "official" ptrace interface for hardware
+ * watchpoints. This is the way intel does it.
+ */
+ per_struct per_info;
+ unsigned long ieee_instruction_pointer; /* obsolete, always 0 */
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_S390_PTRACE_H */
diff --git a/tools/include/uapi/asm-generic/bpf_perf_event.h b/tools/include/uapi/asm-generic/bpf_perf_event.h
new file mode 100644
index 0000000..53815d2
--- /dev/null
+++ b/tools/include/uapi/asm-generic/bpf_perf_event.h
@@ -0,0 +1,9 @@
+#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+
+#include <linux/ptrace.h>
+
+/* Export kernel pt_regs structure */
+typedef struct pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */
diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h
index 0674272..8f95303 100644
--- a/tools/include/uapi/linux/bpf_perf_event.h
+++ b/tools/include/uapi/linux/bpf_perf_event.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/* Copyright (c) 2016 Facebook
*
* This program is free software; you can redistribute it and/or
@@ -7,11 +8,10 @@
#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
#define _UAPI__LINUX_BPF_PERF_EVENT_H__
-#include <linux/types.h>
-#include <linux/ptrace.h>
+#include <asm/bpf_perf_event.h>
struct bpf_perf_event_data {
- struct pt_regs regs;
+ bpf_user_pt_regs_t regs;
__u64 sample_period;
};
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 333a486..21a2d76 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,7 +1,19 @@
# SPDX-License-Identifier: GPL-2.0
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+include $(srctree)/tools/scripts/Makefile.arch
+
+$(call detected_var,SRCARCH)
+
LIBDIR := ../../../lib
BPFDIR := $(LIBDIR)/bpf
APIDIR := ../../../include/uapi
+ASMDIR:= ../../../arch/$(ARCH)/include/uapi
GENDIR := ../../../../include/generated
GENHDR := $(GENDIR)/autoconf.h
@@ -9,7 +21,7 @@ ifneq ($(wildcard $(GENHDR)),)
GENFLAGS := -DHAVE_GENHDR
endif
-CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(ASMDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
LDLIBS += -lcap -lelf
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 2/6] s390/bpf: correct broken uapi for BPF_PROG_TYPE_PERF_EVENT program type
From: Hendrik Brueckner @ 2017-12-04 9:56 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Alexei Starovoitov, Daniel Borkmann,
Martin Schwidefsky, Will Deacon, Ingo Molnar
Cc: Arnd Bergmann, Peter Zijlstra, David S. Miller, linux-kernel,
linux-s390, netdev
In-Reply-To: <1512381409-19775-1-git-send-email-brueckner@linux.vnet.ibm.com>
To mitigate and correct the broken uapi for the BPF_PROG_TYPE_PERF_EVENT
program type, introduce a user_pt_regs structure (similar to arm64) that
exports parts from the beginnig of the pt_regs structure.
The export must start with the beginning of the pt_regs structure because
to correctly calculate BPF prologues for perf (regs_query_register_offset()).
For BPF_PROG_TYPE_PERF_EVENT program types, the BPF program is then passed
a user_pt_regs structure.
Note: Depending on future changes to the s390 pt_regs structure, consider
the user_pt_regs structure to be stable for a particular kernel version
only. (Of course, s390 tries to ensure keep it stable as much as possible.)
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-and-tested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
---
arch/s390/include/asm/perf_event.h | 1 +
arch/s390/include/asm/ptrace.h | 11 ++++++++---
arch/s390/include/uapi/asm/bpf_perf_event.h | 9 +++++++++
arch/s390/include/uapi/asm/ptrace.h | 11 +++++++++++
4 files changed, 29 insertions(+), 3 deletions(-)
create mode 100644 arch/s390/include/uapi/asm/bpf_perf_event.h
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index d6c9d1e..b9c0e36 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -40,6 +40,7 @@ extern ssize_t cpumf_events_sysfs_show(struct device *dev,
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
+#define perf_arch_bpf_user_pt_regs(regs) ®s->user_regs
/* Perf pt_regs extension for sample-data-entry indicators */
struct perf_sf_sde_regs {
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index a3788da..6f70d81 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -74,9 +74,14 @@ enum {
*/
struct pt_regs
{
- unsigned long args[1];
- psw_t psw;
- unsigned long gprs[NUM_GPRS];
+ union {
+ user_pt_regs user_regs;
+ struct {
+ unsigned long args[1];
+ psw_t psw;
+ unsigned long gprs[NUM_GPRS];
+ };
+ };
unsigned long orig_gpr2;
unsigned int int_code;
unsigned int int_parm;
diff --git a/arch/s390/include/uapi/asm/bpf_perf_event.h b/arch/s390/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 0000000..cefe7c7
--- /dev/null
+++ b/arch/s390/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 0d23c8f..70f7cb2 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -291,6 +291,17 @@
} s390_regs;
/*
+ * The user_pt_regs structure exports the beginning of
+ * the in-kernel pt_regs structure to user space.
+ */
+typedef struct
+{
+ unsigned long args[1];
+ psw_t psw;
+ unsigned long gprs[NUM_GPRS];
+} user_pt_regs;
+
+/*
* Now for the user space program event recording (trace) definitions.
* The following structures are used only for the ptrace interface, don't
* touch or even look at it if you don't want to modify the user-space
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 1/6] bpf: correct broken uapi for BPF_PROG_TYPE_PERF_EVENT program type
From: Hendrik Brueckner @ 2017-12-04 9:56 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Alexei Starovoitov, Daniel Borkmann,
Martin Schwidefsky, Will Deacon, Ingo Molnar
Cc: Arnd Bergmann, Peter Zijlstra, David S. Miller, linux-kernel,
linux-s390, netdev
In-Reply-To: <1512381409-19775-1-git-send-email-brueckner@linux.vnet.ibm.com>
Commit 0515e5999a466dfe ("bpf: introduce BPF_PROG_TYPE_PERF_EVENT
program type") introduced the bpf_perf_event_data structure which
exports the pt_regs structure. This is OK for multiple architectures
but fail for s390 and arm64 which do not export pt_regs. Programs
using them, for example, the bpf selftest fail to compile on these
architectures.
For s390, exporting the pt_regs is not an option because s390 wants
to allow changes to it. For arm64, there is a user_pt_regs structure
that covers parts of the pt_regs structure for use by user space.
To solve the broken uapi for s390 and arm64, introduce an abstract
type for pt_regs and add an asm/bpf_perf_event.h file that concretes
the type. An asm-generic header file covers the architectures that
export pt_regs today.
The arch-specific enablement for s390 and arm64 follows in separate
commits.
Reported-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Fixes: 0515e5999a466dfe ("bpf: introduce BPF_PROG_TYPE_PERF_EVENT program type")
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-and-tested-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Daniel Borkmann <daniel@iogearbox.net>
---
arch/alpha/include/uapi/asm/Kbuild | 2 ++
arch/arc/include/uapi/asm/Kbuild | 1 +
arch/arm/include/uapi/asm/Kbuild | 1 +
arch/blackfin/include/uapi/asm/Kbuild | 1 +
arch/c6x/include/uapi/asm/Kbuild | 1 +
arch/cris/include/uapi/asm/Kbuild | 1 +
arch/frv/include/uapi/asm/Kbuild | 2 ++
arch/h8300/include/uapi/asm/Kbuild | 1 +
arch/hexagon/include/uapi/asm/Kbuild | 1 +
arch/ia64/include/uapi/asm/Kbuild | 1 +
arch/m32r/include/uapi/asm/Kbuild | 1 +
arch/m68k/include/uapi/asm/Kbuild | 1 +
arch/metag/include/uapi/asm/Kbuild | 1 +
arch/microblaze/include/uapi/asm/Kbuild | 1 +
arch/mips/include/uapi/asm/Kbuild | 1 +
arch/mn10300/include/uapi/asm/Kbuild | 1 +
arch/nios2/include/uapi/asm/Kbuild | 1 +
arch/openrisc/include/uapi/asm/Kbuild | 1 +
arch/parisc/include/uapi/asm/Kbuild | 1 +
arch/powerpc/include/uapi/asm/Kbuild | 1 +
arch/riscv/include/uapi/asm/Kbuild | 1 +
arch/score/include/uapi/asm/Kbuild | 1 +
arch/sh/include/uapi/asm/Kbuild | 1 +
arch/sparc/include/uapi/asm/Kbuild | 1 +
arch/tile/include/uapi/asm/Kbuild | 1 +
arch/unicore32/include/uapi/asm/Kbuild | 1 +
arch/x86/include/uapi/asm/Kbuild | 1 +
arch/xtensa/include/uapi/asm/Kbuild | 1 +
include/linux/perf_event.h | 6 +++++-
include/uapi/asm-generic/bpf_perf_event.h | 9 +++++++++
include/uapi/linux/bpf_perf_event.h | 5 ++---
kernel/events/core.c | 2 +-
32 files changed, 47 insertions(+), 5 deletions(-)
create mode 100644 include/uapi/asm-generic/bpf_perf_event.h
diff --git a/arch/alpha/include/uapi/asm/Kbuild b/arch/alpha/include/uapi/asm/Kbuild
index b15bf6b..14a2e9a 100644
--- a/arch/alpha/include/uapi/asm/Kbuild
+++ b/arch/alpha/include/uapi/asm/Kbuild
@@ -1,2 +1,4 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += bpf_perf_event.h
diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild
index fa6d0ff..170b5db 100644
--- a/arch/arc/include/uapi/asm/Kbuild
+++ b/arch/arc/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild
index 4d53de3..4d1cc18 100644
--- a/arch/arm/include/uapi/asm/Kbuild
+++ b/arch/arm/include/uapi/asm/Kbuild
@@ -7,6 +7,7 @@ generated-y += unistd-oabi.h
generated-y += unistd-eabi.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += ioctl.h
generic-y += ipcbuf.h
diff --git a/arch/blackfin/include/uapi/asm/Kbuild b/arch/blackfin/include/uapi/asm/Kbuild
index aa624b4..2240b38 100644
--- a/arch/blackfin/include/uapi/asm/Kbuild
+++ b/arch/blackfin/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += ioctl.h
generic-y += ipcbuf.h
diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild
index 67ee896..26644e1 100644
--- a/arch/c6x/include/uapi/asm/Kbuild
+++ b/arch/c6x/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/cris/include/uapi/asm/Kbuild b/arch/cris/include/uapi/asm/Kbuild
index 3687b54..3470c6e 100644
--- a/arch/cris/include/uapi/asm/Kbuild
+++ b/arch/cris/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/frv/include/uapi/asm/Kbuild b/arch/frv/include/uapi/asm/Kbuild
index b15bf6b..14a2e9a 100644
--- a/arch/frv/include/uapi/asm/Kbuild
+++ b/arch/frv/include/uapi/asm/Kbuild
@@ -1,2 +1,4 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += bpf_perf_event.h
diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild
index 187aed8..2f65f78 100644
--- a/arch/h8300/include/uapi/asm/Kbuild
+++ b/arch/h8300/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild
index cb5df3a..41a176d 100644
--- a/arch/hexagon/include/uapi/asm/Kbuild
+++ b/arch/hexagon/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild
index 13a97aa..f5c6967 100644
--- a/arch/ia64/include/uapi/asm/Kbuild
+++ b/arch/ia64/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += kvm_para.h
diff --git a/arch/m32r/include/uapi/asm/Kbuild b/arch/m32r/include/uapi/asm/Kbuild
index 1c44d3b..451bf60 100644
--- a/arch/m32r/include/uapi/asm/Kbuild
+++ b/arch/m32r/include/uapi/asm/Kbuild
@@ -1,5 +1,6 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += kvm_para.h
generic-y += siginfo.h
diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild
index 3717b64..c2e26a4 100644
--- a/arch/m68k/include/uapi/asm/Kbuild
+++ b/arch/m68k/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += ioctl.h
generic-y += ipcbuf.h
diff --git a/arch/metag/include/uapi/asm/Kbuild b/arch/metag/include/uapi/asm/Kbuild
index 6ac763d..f9eaf07 100644
--- a/arch/metag/include/uapi/asm/Kbuild
+++ b/arch/metag/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild
index 06609ca..2c6a6bf 100644
--- a/arch/microblaze/include/uapi/asm/Kbuild
+++ b/arch/microblaze/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild
index a0266fe..7a4becd 100644
--- a/arch/mips/include/uapi/asm/Kbuild
+++ b/arch/mips/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += ipcbuf.h
diff --git a/arch/mn10300/include/uapi/asm/Kbuild b/arch/mn10300/include/uapi/asm/Kbuild
index c94ee54..81271d3 100644
--- a/arch/mn10300/include/uapi/asm/Kbuild
+++ b/arch/mn10300/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += siginfo.h
diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild
index ffca24d..13a3d77 100644
--- a/arch/nios2/include/uapi/asm/Kbuild
+++ b/arch/nios2/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild
index 62286db..130c16c 100644
--- a/arch/openrisc/include/uapi/asm/Kbuild
+++ b/arch/openrisc/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild
index 196d2a4..286ef5a 100644
--- a/arch/parisc/include/uapi/asm/Kbuild
+++ b/arch/parisc/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
+generic-y += bpf_perf_event.h
generic-y += kvm_para.h
generic-y += param.h
generic-y += poll.h
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 0d960ef..1a6ed59 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += param.h
generic-y += poll.h
generic-y += resource.h
diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild
index 5ded96b..7e91f48 100644
--- a/arch/riscv/include/uapi/asm/Kbuild
+++ b/arch/riscv/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += setup.h
generic-y += unistd.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/score/include/uapi/asm/Kbuild b/arch/score/include/uapi/asm/Kbuild
index c94ee54..81271d3 100644
--- a/arch/score/include/uapi/asm/Kbuild
+++ b/arch/score/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += siginfo.h
diff --git a/arch/sh/include/uapi/asm/Kbuild b/arch/sh/include/uapi/asm/Kbuild
index e285313..ba4d39c 100644
--- a/arch/sh/include/uapi/asm/Kbuild
+++ b/arch/sh/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild
index 2178c78..4680ba2 100644
--- a/arch/sparc/include/uapi/asm/Kbuild
+++ b/arch/sparc/include/uapi/asm/Kbuild
@@ -1,4 +1,5 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += types.h
diff --git a/arch/tile/include/uapi/asm/Kbuild b/arch/tile/include/uapi/asm/Kbuild
index 5711de0..cc43961 100644
--- a/arch/tile/include/uapi/asm/Kbuild
+++ b/arch/tile/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild
index 759a714..8611ef9 100644
--- a/arch/unicore32/include/uapi/asm/Kbuild
+++ b/arch/unicore32/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
generic-y += auxvec.h
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index da1489c..1e901e4 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
+generic-y += bpf_perf_event.h
generated-y += unistd_32.h
generated-y += unistd_64.h
generated-y += unistd_x32.h
diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild
index a5bcdfb..837d4dd 100644
--- a/arch/xtensa/include/uapi/asm/Kbuild
+++ b/arch/xtensa/include/uapi/asm/Kbuild
@@ -2,6 +2,7 @@
include include/uapi/asm-generic/Kbuild.asm
generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
generic-y += errno.h
generic-y += fcntl.h
generic-y += ioctl.h
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2c9c87d..7546822 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -15,6 +15,7 @@
#define _LINUX_PERF_EVENT_H
#include <uapi/linux/perf_event.h>
+#include <uapi/linux/bpf_perf_event.h>
/*
* Kernel-internal data types and definitions:
@@ -787,7 +788,7 @@ struct perf_output_handle {
};
struct bpf_perf_event_data_kern {
- struct pt_regs *regs;
+ bpf_user_pt_regs_t *regs;
struct perf_sample_data *data;
struct perf_event *event;
};
@@ -1177,6 +1178,9 @@ extern void perf_tp_event(u16 event_type, u64 count, void *record,
(user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL)
# define perf_instruction_pointer(regs) instruction_pointer(regs)
#endif
+#ifndef perf_arch_bpf_user_pt_regs
+# define perf_arch_bpf_user_pt_regs(regs) regs
+#endif
static inline bool has_branch_stack(struct perf_event *event)
{
diff --git a/include/uapi/asm-generic/bpf_perf_event.h b/include/uapi/asm-generic/bpf_perf_event.h
new file mode 100644
index 0000000..53815d2
--- /dev/null
+++ b/include/uapi/asm-generic/bpf_perf_event.h
@@ -0,0 +1,9 @@
+#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+
+#include <linux/ptrace.h>
+
+/* Export kernel pt_regs structure */
+typedef struct pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */
diff --git a/include/uapi/linux/bpf_perf_event.h b/include/uapi/linux/bpf_perf_event.h
index af549d4..8f95303 100644
--- a/include/uapi/linux/bpf_perf_event.h
+++ b/include/uapi/linux/bpf_perf_event.h
@@ -8,11 +8,10 @@
#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
#define _UAPI__LINUX_BPF_PERF_EVENT_H__
-#include <linux/types.h>
-#include <linux/ptrace.h>
+#include <asm/bpf_perf_event.h>
struct bpf_perf_event_data {
- struct pt_regs regs;
+ bpf_user_pt_regs_t regs;
__u64 sample_period;
};
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 16beab4..ba957b9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7987,11 +7987,11 @@ static void bpf_overflow_handler(struct perf_event *event,
{
struct bpf_perf_event_data_kern ctx = {
.data = data,
- .regs = regs,
.event = event,
};
int ret = 0;
+ ctx.regs = perf_arch_bpf_user_pt_regs(regs);
preempt_disable();
if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
goto out;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 4/6] s390/uapi: correct whitespace & coding style in asm/ptrace.h
From: Hendrik Brueckner @ 2017-12-04 9:56 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Alexei Starovoitov, Daniel Borkmann,
Martin Schwidefsky, Will Deacon, Ingo Molnar
Cc: Arnd Bergmann, Peter Zijlstra, David S. Miller, linux-kernel,
linux-s390, netdev
In-Reply-To: <1512381409-19775-1-git-send-email-brueckner@linux.vnet.ibm.com>
Correct whitespace and coding style issues in the s390 asm/ptrace.h
uapi header file. This is preparatory work to copy it to the tools/
directory for inclusion by selftests and perf.
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
---
arch/s390/include/uapi/asm/ptrace.h | 118 ++++++++++++++++--------------------
1 file changed, 52 insertions(+), 66 deletions(-)
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 70f7cb2..543dd70 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -162,7 +162,7 @@
#define GPR_SIZE 8
#define CR_SIZE 8
-#define STACK_FRAME_OVERHEAD 160 /* size of minimum stack frame */
+#define STACK_FRAME_OVERHEAD 160 /* size of minimum stack frame */
#endif /* __s390x__ */
@@ -179,17 +179,16 @@
#define ACR_SIZE 4
-#define PTRACE_OLDSETOPTIONS 21
+#define PTRACE_OLDSETOPTIONS 21
#ifndef __ASSEMBLY__
#include <linux/stddef.h>
#include <linux/types.h>
-typedef union
-{
- float f;
- double d;
- __u64 ui;
+typedef union {
+ float f;
+ double d;
+ __u64 ui;
struct
{
__u32 hi;
@@ -197,23 +196,21 @@
} fp;
} freg_t;
-typedef struct
-{
- __u32 fpc;
+typedef struct {
+ __u32 fpc;
__u32 pad;
- freg_t fprs[NUM_FPRS];
+ freg_t fprs[NUM_FPRS];
} s390_fp_regs;
-#define FPC_EXCEPTION_MASK 0xF8000000
-#define FPC_FLAGS_MASK 0x00F80000
-#define FPC_DXC_MASK 0x0000FF00
-#define FPC_RM_MASK 0x00000003
+#define FPC_EXCEPTION_MASK 0xF8000000
+#define FPC_FLAGS_MASK 0x00F80000
+#define FPC_DXC_MASK 0x0000FF00
+#define FPC_RM_MASK 0x00000003
/* this typedef defines how a Program Status Word looks like */
-typedef struct
-{
- unsigned long mask;
- unsigned long addr;
+typedef struct {
+ unsigned long mask;
+ unsigned long addr;
} __attribute__ ((aligned(8))) psw_t;
#ifndef __s390x__
@@ -282,8 +279,7 @@
/*
* The s390_regs structure is used to define the elf_gregset_t.
*/
-typedef struct
-{
+typedef struct {
psw_t psw;
unsigned long gprs[NUM_GPRS];
unsigned int acrs[NUM_ACRS];
@@ -294,8 +290,7 @@
* The user_pt_regs structure exports the beginning of
* the in-kernel pt_regs structure to user space.
*/
-typedef struct
-{
+typedef struct {
unsigned long args[1];
psw_t psw;
unsigned long gprs[NUM_GPRS];
@@ -307,19 +302,17 @@
* touch or even look at it if you don't want to modify the user-space
* ptrace interface. In particular stay away from it for in-kernel PER.
*/
-typedef struct
-{
+typedef struct {
unsigned long cr[NUM_CR_WORDS];
} per_cr_words;
#define PER_EM_MASK 0xE8000000UL
-typedef struct
-{
+typedef struct {
#ifdef __s390x__
- unsigned : 32;
+ unsigned : 32;
#endif /* __s390x__ */
- unsigned em_branching : 1;
+ unsigned em_branching : 1;
unsigned em_instruction_fetch : 1;
/*
* Switching on storage alteration automatically fixes
@@ -328,44 +321,41 @@
unsigned em_storage_alteration : 1;
unsigned em_gpr_alt_unused : 1;
unsigned em_store_real_address : 1;
- unsigned : 3;
+ unsigned : 3;
unsigned branch_addr_ctl : 1;
- unsigned : 1;
+ unsigned : 1;
unsigned storage_alt_space_ctl : 1;
- unsigned : 21;
+ unsigned : 21;
unsigned long starting_addr;
unsigned long ending_addr;
} per_cr_bits;
-typedef struct
-{
+typedef struct {
unsigned short perc_atmid;
unsigned long address;
unsigned char access_id;
} per_lowcore_words;
-typedef struct
-{
- unsigned perc_branching : 1;
+typedef struct {
+ unsigned perc_branching : 1;
unsigned perc_instruction_fetch : 1;
unsigned perc_storage_alteration : 1;
- unsigned perc_gpr_alt_unused : 1;
+ unsigned perc_gpr_alt_unused : 1;
unsigned perc_store_real_address : 1;
- unsigned : 3;
- unsigned atmid_psw_bit_31 : 1;
- unsigned atmid_validity_bit : 1;
- unsigned atmid_psw_bit_32 : 1;
- unsigned atmid_psw_bit_5 : 1;
- unsigned atmid_psw_bit_16 : 1;
- unsigned atmid_psw_bit_17 : 1;
- unsigned si : 2;
+ unsigned : 3;
+ unsigned atmid_psw_bit_31 : 1;
+ unsigned atmid_validity_bit : 1;
+ unsigned atmid_psw_bit_32 : 1;
+ unsigned atmid_psw_bit_5 : 1;
+ unsigned atmid_psw_bit_16 : 1;
+ unsigned atmid_psw_bit_17 : 1;
+ unsigned si : 2;
unsigned long address;
- unsigned : 4;
- unsigned access_id : 4;
+ unsigned : 4;
+ unsigned access_id : 4;
} per_lowcore_bits;
-typedef struct
-{
+typedef struct {
union {
per_cr_words words;
per_cr_bits bits;
@@ -375,9 +365,9 @@
* the kernel always sets them to zero. To enable single
* stepping use ptrace(PTRACE_SINGLESTEP) instead.
*/
- unsigned single_step : 1;
+ unsigned single_step : 1;
unsigned instruction_fetch : 1;
- unsigned : 30;
+ unsigned : 30;
/*
* These addresses are copied into cr10 & cr11 if single
* stepping is switched off
@@ -387,11 +377,10 @@
union {
per_lowcore_words words;
per_lowcore_bits bits;
- } lowcore;
+ } lowcore;
} per_struct;
-typedef struct
-{
+typedef struct {
unsigned int len;
unsigned long kernel_addr;
unsigned long process_addr;
@@ -401,12 +390,12 @@
* S/390 specific non posix ptrace requests. I chose unusual values so
* they are unlikely to clash with future ptrace definitions.
*/
-#define PTRACE_PEEKUSR_AREA 0x5000
-#define PTRACE_POKEUSR_AREA 0x5001
+#define PTRACE_PEEKUSR_AREA 0x5000
+#define PTRACE_POKEUSR_AREA 0x5001
#define PTRACE_PEEKTEXT_AREA 0x5002
#define PTRACE_PEEKDATA_AREA 0x5003
#define PTRACE_POKETEXT_AREA 0x5004
-#define PTRACE_POKEDATA_AREA 0x5005
+#define PTRACE_POKEDATA_AREA 0x5005
#define PTRACE_GET_LAST_BREAK 0x5006
#define PTRACE_PEEK_SYSTEM_CALL 0x5007
#define PTRACE_POKE_SYSTEM_CALL 0x5008
@@ -424,21 +413,19 @@
* PT_PROT definition is loosely based on hppa bsd definition in
* gdb/hppab-nat.c
*/
-#define PTRACE_PROT 21
+#define PTRACE_PROT 21
-typedef enum
-{
+typedef enum {
ptprot_set_access_watchpoint,
ptprot_set_write_watchpoint,
ptprot_disable_watchpoint
} ptprot_flags;
-typedef struct
-{
+typedef struct {
unsigned long lowaddr;
unsigned long hiaddr;
ptprot_flags prot;
-} ptprot_area;
+} ptprot_area;
/* Sequence of bytes for breakpoint illegal instruction. */
#define S390_BREAKPOINT {0x0,0x1}
@@ -450,8 +437,7 @@
* The user_regs_struct defines the way the user registers are
* store on the stack for signal handling.
*/
-struct user_regs_struct
-{
+struct user_regs_struct {
psw_t psw;
unsigned long gprs[NUM_GPRS];
unsigned int acrs[NUM_ACRS];
--
1.8.3.1
^ permalink raw reply related
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