* Re: [PATCH net-next 1/2] net: tap: replay while() loop with % operator in tap_get_queue()
From: Stephen Hemminger @ 2017-12-11 16:58 UTC (permalink / raw)
To: yuan linyu; +Cc: netdev, David S . Miller, yuan linyu
In-Reply-To: <1512998801-17852-1-git-send-email-cugyly@163.com>
On Mon, 11 Dec 2017 21:26:41 +0800
yuan linyu <cugyly@163.com> wrote:
> From: yuan linyu <Linyu.Yuan@alcatel-sbell.com.cn>
>
> Signed-off-by: yuan linyu <Linyu.Yuan@alcatel-sbell.com.cn>
> ---
> drivers/net/tap.c | 6 +-----
> 1 file changed, 1 insertion(+), 5 deletions(-)
>
> diff --git a/drivers/net/tap.c b/drivers/net/tap.c
> index 0a886fda..78900a0 100644
> --- a/drivers/net/tap.c
> +++ b/drivers/net/tap.c
> @@ -275,11 +275,7 @@ static struct tap_queue *tap_get_queue(struct tap_dev *tap,
>
> if (likely(skb_rx_queue_recorded(skb))) {
> rxq = skb_get_rx_queue(skb);
> -
> - while (unlikely(rxq >= numvtaps))
> - rxq -= numvtaps;
> -
> - queue = rcu_dereference(tap->taps[rxq]);
> + queue = rcu_dereference(tap->taps[rxq % numvtaps]);
> goto out;
> }
>
Modulus is slower than the loop.
^ permalink raw reply
* [PATCH net-next 0/2] hv_netvsc: Fix default and limit of recv buffe
From: Stephen Hemminger @ 2017-12-11 16:56 UTC (permalink / raw)
To: kys, haiyangz, sthemmin; +Cc: devel, netdev
The default for receive buffer descriptors is not correct, it should
match the default receive buffer size and the upper limit of receive
buffer size is too low. Also, for older versions of Window servers
hosts, different lower limit check is necessary, otherwise the buffer
request will be rejected by the host, resulting vNIC not come up.
This patch set corrects these problems.
Haiyang Zhang (2):
hv_netvsc: Fix the receive buffer size limit
hv_netvsc: Fix the TX/RX buffer default sizes
drivers/net/hyperv/hyperv_net.h | 19 ++++++++++++++++---
drivers/net/hyperv/netvsc.c | 5 +++++
drivers/net/hyperv/netvsc_drv.c | 4 ----
3 files changed, 21 insertions(+), 7 deletions(-)
--
2.11.0
^ permalink raw reply
* [PATCH net-next 2/2] hv_netvsc: Fix the TX/RX buffer default sizes
From: Stephen Hemminger @ 2017-12-11 16:56 UTC (permalink / raw)
To: kys, haiyangz, sthemmin; +Cc: devel, netdev
In-Reply-To: <20171211165658.14768-1-sthemmin@microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
The values were not computed correctly. There are no significant
visible impact, though.
The intended size of RX buffer is 16 MB, and the default slot size is 1728.
So, NETVSC_DEFAULT_RX should be 16*1024*1024 / 1728 = 9709.
The intended size of TX buffer is 1 MB, and the slot size is 6144.
So, NETVSC_DEFAULT_TX should be 1024*1024 / 6144 = 170.
The patch puts the formula directly into the macro, and moves them to
hyperv_net.h, together with related macros.
Fixes: 5023a6db73196 ("netvsc: increase default receive buffer size")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
---
drivers/net/hyperv/hyperv_net.h | 13 ++++++++++++-
drivers/net/hyperv/netvsc_drv.c | 4 ----
2 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 373455f216ce..845ddc7bba46 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -640,13 +640,24 @@ struct nvsp_message {
/* Max buffer sizes allowed by a host */
#define NETVSC_RECEIVE_BUFFER_SIZE (1024 * 1024 * 31) /* 31MB */
#define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY (1024 * 1024 * 15) /* 15MB */
-#define NETVSC_SEND_BUFFER_SIZE (1024 * 1024 * 15) /* 15MB */
+#define NETVSC_RECEIVE_BUFFER_DEFAULT (1024 * 1024 * 16)
+
+#define NETVSC_SEND_BUFFER_SIZE (1024 * 1024 * 15) /* 15MB */
+#define NETVSC_SEND_BUFFER_DEFAULT (1024 * 1024)
#define NETVSC_INVALID_INDEX -1
#define NETVSC_SEND_SECTION_SIZE 6144
#define NETVSC_RECV_SECTION_SIZE 1728
+/* Default size of TX buf: 1MB, RX buf: 16MB */
+#define NETVSC_MIN_TX_SECTIONS 10
+#define NETVSC_DEFAULT_TX (NETVSC_SEND_BUFFER_DEFAULT \
+ / NETVSC_SEND_SECTION_SIZE)
+#define NETVSC_MIN_RX_SECTIONS 10
+#define NETVSC_DEFAULT_RX (NETVSC_RECEIVE_BUFFER_DEFAULT \
+ / NETVSC_RECV_SECTION_SIZE)
+
#define NETVSC_RECEIVE_BUFFER_ID 0xcafe
#define NETVSC_SEND_BUFFER_ID 0
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index dc70de674ca9..b6a434ac64d3 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -47,10 +47,6 @@
#include "hyperv_net.h"
#define RING_SIZE_MIN 64
-#define NETVSC_MIN_TX_SECTIONS 10
-#define NETVSC_DEFAULT_TX 192 /* ~1M */
-#define NETVSC_MIN_RX_SECTIONS 10 /* ~64K */
-#define NETVSC_DEFAULT_RX 10485 /* Max ~16M */
#define LINKCHANGE_INT (2 * HZ)
#define VF_TAKEOVER_INT (HZ / 10)
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 1/2] hv_netvsc: Fix the receive buffer size limit
From: Stephen Hemminger @ 2017-12-11 16:56 UTC (permalink / raw)
To: kys, haiyangz, sthemmin; +Cc: devel, netdev
In-Reply-To: <20171211165658.14768-1-sthemmin@microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
The max should be 31 MB on host with NVSP version > 2.
On legacy hosts (NVSP version <=2) only 15 MB receive buffer is allowed,
otherwise the buffer request will be rejected by the host, resulting
vNIC not coming up.
The NVSP version is only available after negotiation. So, we add the
limit checking for legacy hosts in netvsc_init_buf().
Fixes: 5023a6db73196 ("netvsc: increase default receive buffer size")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
---
drivers/net/hyperv/hyperv_net.h | 6 ++++--
drivers/net/hyperv/netvsc.c | 5 +++++
2 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 3d940c67ea94..373455f216ce 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -637,9 +637,11 @@ struct nvsp_message {
#define NETVSC_MTU 65535
#define NETVSC_MTU_MIN ETH_MIN_MTU
-#define NETVSC_RECEIVE_BUFFER_SIZE (1024*1024*16) /* 16MB */
-#define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY (1024*1024*15) /* 15MB */
+/* Max buffer sizes allowed by a host */
+#define NETVSC_RECEIVE_BUFFER_SIZE (1024 * 1024 * 31) /* 31MB */
+#define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY (1024 * 1024 * 15) /* 15MB */
#define NETVSC_SEND_BUFFER_SIZE (1024 * 1024 * 15) /* 15MB */
+
#define NETVSC_INVALID_INDEX -1
#define NETVSC_SEND_SECTION_SIZE 6144
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index e4bcd202a56a..e5d16a8cf0d6 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -268,6 +268,11 @@ static int netvsc_init_buf(struct hv_device *device,
buf_size = device_info->recv_sections * device_info->recv_section_size;
buf_size = roundup(buf_size, PAGE_SIZE);
+ /* Legacy hosts only allow smaller receive buffer */
+ if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_2)
+ buf_size = min_t(unsigned int, buf_size,
+ NETVSC_RECEIVE_BUFFER_SIZE_LEGACY);
+
net_device->recv_buf = vzalloc(buf_size);
if (!net_device->recv_buf) {
netdev_err(ndev,
--
2.11.0
^ permalink raw reply related
* Re: [RFC PATCH 2/9] ethtool: introduce ethtool netlink interface
From: David Miller @ 2017-12-11 16:56 UTC (permalink / raw)
To: jiri; +Cc: mkubecek, netdev, linux-kernel
In-Reply-To: <20171211160221.GA1885@nanopsycho>
From: Jiri Pirko <jiri@resnulli.us>
Date: Mon, 11 Dec 2017 17:02:21 +0100
> Mon, Dec 11, 2017 at 02:53:31PM CET, mkubecek@suse.cz wrote:
>>No function implemented yet, only genetlink and module infrastructure.
>>Register/unregister genetlink family "ethtool" and allow the module to be
>>autoloaded by genetlink code (if built as a module, distributions would
>>probably prefer "y").
>>
>>Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
>
> [...]
>
>
>>+
>>+/* identifies the device to query/set
>>+ * - use either ifindex or ifname, not both
>>+ * - for dumps and messages not related to a particular devices, fill neither
>>+ * - info_mask is a bitfield, interpretation depends on the command
>>+ */
>>+struct ethnlmsghdr {
>>+ __u32 ifindex; /* device ifindex */
>>+ __u16 flags; /* request/response flags */
>>+ __u16 info_mask; /* request/response info mask */
>>+ char ifname[IFNAMSIZ]; /* device name */
>
> Why do you need this header? You can have 2 attrs:
> ETHTOOL_ATTR_IFINDEX and
> ETHTOOL_ATTR_IFNAME
>
> Why do you need per-command flags and info_mask? Could be bitfield
> attr if needed by specific command.
Jiri, we've had this discussion before :-)
For elements which are common to most, if not all, requests it makes
sense to define a base netlink message.
My opinion on this matter has not changed at all since the last time
we discussed this.
So unless you have new information to provide to me on this issue
which might change my mind, please accept the result of the previous
discussion which is that a base netlink message is not only
appropriate but desirable.
Thank you.
^ permalink raw reply
* Re: [PATCH v3] net: sh_eth: do not advertise Gigabit capabilities when not available
From: David Miller @ 2017-12-11 16:54 UTC (permalink / raw)
To: thomas.petazzoni
Cc: sergei.shtylyov, niklas.soderlund+renesas, geert+renesas,
horms+renesas, netdev, linux-renesas-soc
In-Reply-To: <20171208153540.3323-1-thomas.petazzoni@free-electrons.com>
From: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Date: Fri, 8 Dec 2017 16:35:40 +0100
> Not all variants of the sh_eth hardware have Gigabit
> support. Unfortunately, the current driver doesn't tell the PHY about
> the limited MAC capabilities. Due to this, if you have a Gigabit
> capable PHY, the PHY will advertise its Gigabit capability and
> establish a link at 1Gbit/s, even though the MAC doesn't support it.
>
> In order to avoid this, we use the recently introduced
> phy_set_max_speed() to tell the PHY to not advertise speed higher than
> 100 MBit/s.
>
> Tested on a SH7786 platform, with a Gigabit PHY.
>
> Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Applied, thanks.
^ permalink raw reply
* Re: RFC(v2): Audit Kernel Container IDs
From: Casey Schaufler @ 2017-12-11 16:52 UTC (permalink / raw)
To: Eric Paris, Mickaël Salaün, Richard Guy Briggs, cgroups,
Linux Containers, Linux API, Linux Audit, Linux FS Devel,
Linux Kernel, Linux Network Development
Cc: mszeredi, Eric W. Biederman, Simo Sorce, jlayton,
Carlos O'Donell, David Howells, Al Viro, Andy Lutomirski,
Eric Paris, trondmy, Michael Kerrisk
In-Reply-To: <1513009857.6310.337.camel@redhat.com>
On 12/11/2017 8:30 AM, Eric Paris wrote:
> On Sat, 2017-12-09 at 10:28 -0800, Casey Schaufler wrote:
>> Because a container doesn't have to use namespaces to be a container
>> you still need a mechanism for a process to declare that it is in
>> fact
>> in a container, and to identify the container.
> I like the idea but I'm still tossing it around in my head (and
> thinking about Casey's statement too). Lets say we have a 'docker-like'
> container with pid=100 netns=X,userns=Y,mountns=Z. If I'm on the host
> in all init namespaces and I run
> nsenter -t 100 -n ip link set eth0 promisc on
> How should this be logged? Did this command run in it's own 'container'
> unrelated to the 'docker-like' container?
Jose Bollo's PTAGS ( https://gitlab.com/jobol/ptags ) would be
prefect. Any time you declare something to be a container or
enter a namespace you slap a tag on it. Identifying nested
containers would be easy, you'd have multiple tags.
PTAGS unfortunately needs module stacking, but how hard could that be?
> -Eric
^ permalink raw reply
* [PATCH 27/45] net: remove duplicate includes
From: Pravin Shedge @ 2017-12-11 16:39 UTC (permalink / raw)
To: netdev, netfilter-devel, coreteam, davem, andrew, vivien.didelot,
f.fainelli, pablo, kadlec, fw, jhs, xiyou.wangcong, mingo,
rmk+kernel
Cc: pravin.shedge4linux, linux-kernel
These duplicate includes have been found with scripts/checkincludes.pl but
they have been removed manually to avoid removing false positives.
Signed-off-by: Pravin Shedge <pravin.shedge4linux@gmail.com>
---
net/core/netprio_cgroup.c | 1 -
net/dsa/slave.c | 1 -
net/netfilter/nf_conntrack_netlink.c | 1 -
net/sched/act_meta_mark.c | 1 -
net/sched/act_meta_skbtcindex.c | 1 -
net/sched/cls_api.c | 1 -
net/sched/cls_u32.c | 1 -
7 files changed, 7 deletions(-)
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 1c48109..b905747 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -14,7 +14,6 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
-#include <linux/module.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index d6e7a64..a95a55f 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -16,7 +16,6 @@
#include <linux/of_net.h>
#include <linux/of_mdio.h>
#include <linux/mdio.h>
-#include <linux/list.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
#include <net/tc_act/tc_mirred.h>
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 59c0899..332b518 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -45,7 +45,6 @@
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_timestamp.h>
#include <net/netfilter/nf_conntrack_labels.h>
-#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_synproxy.h>
#ifdef CONFIG_NF_NAT_NEEDED
#include <net/netfilter/nf_nat_core.h>
diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c
index 1e3f10e..6445184 100644
--- a/net/sched/act_meta_mark.c
+++ b/net/sched/act_meta_mark.c
@@ -22,7 +22,6 @@
#include <net/pkt_sched.h>
#include <uapi/linux/tc_act/tc_ife.h>
#include <net/tc_act/tc_ife.h>
-#include <linux/rtnetlink.h>
static int skbmark_encode(struct sk_buff *skb, void *skbdata,
struct tcf_meta_info *e)
diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c
index 2ea1f26..7221437 100644
--- a/net/sched/act_meta_skbtcindex.c
+++ b/net/sched/act_meta_skbtcindex.c
@@ -22,7 +22,6 @@
#include <net/pkt_sched.h>
#include <uapi/linux/tc_act/tc_ife.h>
#include <net/tc_act/tc_ife.h>
-#include <linux/rtnetlink.h>
static int skbtcindex_encode(struct sk_buff *skb, void *skbdata,
struct tcf_meta_info *e)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ddcf04b..f40256a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -23,7 +23,6 @@
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/kmod.h>
-#include <linux/err.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/sock.h>
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index ac152b4..507859c 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -45,7 +45,6 @@
#include <net/netlink.h>
#include <net/act_api.h>
#include <net/pkt_cls.h>
-#include <linux/netdevice.h>
#include <linux/idr.h>
struct tc_u_knode {
--
2.7.4
^ permalink raw reply related
* [PATCH v9 3/5] bpf: add a bpf_override_function helper
From: Josef Bacik @ 2017-12-11 16:36 UTC (permalink / raw)
To: rostedt, mingo, davem, netdev, linux-kernel, ast, kernel-team,
daniel, linux-btrfs
Cc: Josef Bacik
In-Reply-To: <1513010210-30594-1-git-send-email-josef@toxicpanda.com>
From: Josef Bacik <jbacik@fb.com>
Error injection is sloppy and very ad-hoc. BPF could fill this niche
perfectly with it's kprobe functionality. We could make sure errors are
only triggered in specific call chains that we care about with very
specific situations. Accomplish this with the bpf_override_funciton
helper. This will modify the probe'd callers return value to the
specified value and set the PC to an override function that simply
returns, bypassing the originally probed function. This gives us a nice
clean way to implement systematic error injection for all of our code
paths.
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
arch/Kconfig | 3 +++
arch/x86/Kconfig | 1 +
arch/x86/include/asm/kprobes.h | 4 +++
arch/x86/include/asm/ptrace.h | 5 ++++
arch/x86/kernel/kprobes/ftrace.c | 14 ++++++++++
include/linux/filter.h | 3 ++-
include/linux/trace_events.h | 1 +
include/uapi/linux/bpf.h | 7 ++++-
kernel/bpf/core.c | 3 +++
kernel/bpf/verifier.c | 2 ++
kernel/events/core.c | 7 +++++
kernel/trace/Kconfig | 11 ++++++++
kernel/trace/bpf_trace.c | 38 +++++++++++++++++++++++++++
kernel/trace/trace_kprobe.c | 55 +++++++++++++++++++++++++++++++++++-----
kernel/trace/trace_probe.h | 12 +++++++++
15 files changed, 157 insertions(+), 9 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 400b9e1b2f27..d3f4aaf9cb7a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -196,6 +196,9 @@ config HAVE_OPTPROBES
config HAVE_KPROBES_ON_FTRACE
bool
+config HAVE_KPROBE_OVERRIDE
+ bool
+
config HAVE_NMI
bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8eed3f94bfc7..04d66e6fa447 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -154,6 +154,7 @@ config X86
select HAVE_KERNEL_XZ
select HAVE_KPROBES
select HAVE_KPROBES_ON_FTRACE
+ select HAVE_KPROBE_OVERRIDE
select HAVE_KRETPROBES
select HAVE_KVM
select HAVE_LIVEPATCH if X86_64
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 9f2e3102e0bb..36abb23a7a35 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -67,6 +67,10 @@ extern const int kretprobe_blacklist_size;
void arch_remove_kprobe(struct kprobe *p);
asmlinkage void kretprobe_trampoline(void);
+#ifdef CONFIG_KPROBES_ON_FTRACE
+extern void arch_ftrace_kprobe_override_function(struct pt_regs *regs);
+#endif
+
/* Architecture specific copy of original instruction*/
struct arch_specific_insn {
/* copy of the original instruction */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 14131dd06b29..6de1fd3d0097 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -109,6 +109,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
return regs->ax;
}
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+ regs->ax = rc;
+}
+
/*
* user_mode(regs) determines whether a register set came from user
* mode. On x86_32, this is true if V8086 mode was enabled OR if the
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 8dc0161cec8f..1ea748d682fd 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -97,3 +97,17 @@ int arch_prepare_kprobe_ftrace(struct kprobe *p)
p->ainsn.boostable = false;
return 0;
}
+
+asmlinkage void override_func(void);
+asm(
+ ".type override_func, @function\n"
+ "override_func:\n"
+ " ret\n"
+ ".size override_func, .-override_func\n"
+);
+
+void arch_ftrace_kprobe_override_function(struct pt_regs *regs)
+{
+ regs->ip = (unsigned long)&override_func;
+}
+NOKPROBE_SYMBOL(arch_ftrace_kprobe_override_function);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0062302e1285..5feb441d3dd9 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -458,7 +458,8 @@ struct bpf_prog {
locked:1, /* Program image locked? */
gpl_compatible:1, /* Is filter GPL compatible? */
cb_access:1, /* Is control block accessed? */
- dst_needed:1; /* Do we need dst entry? */
+ dst_needed:1, /* Do we need dst entry? */
+ kprobe_override:1; /* Do we override a kprobe? */
enum bpf_prog_type type; /* Type of BPF program */
u32 len; /* Number of filter blocks */
u32 jited_len; /* Size of jited insns in bytes */
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index af44e7c2d577..5fea451f6e28 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -528,6 +528,7 @@ do { \
struct perf_event;
DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
+DECLARE_PER_CPU(int, bpf_kprobe_override);
extern int perf_trace_init(struct perf_event *event);
extern void perf_trace_destroy(struct perf_event *event);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 80d62e88590c..595bda120cfb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -677,6 +677,10 @@ union bpf_attr {
* @buf: buf to fill
* @buf_size: size of the buf
* Return : 0 on success or negative error code
+ *
+ * int bpf_override_return(pt_regs, rc)
+ * @pt_regs: pointer to struct pt_regs
+ * @rc: the return value to set
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -736,7 +740,8 @@ union bpf_attr {
FN(xdp_adjust_meta), \
FN(perf_event_read_value), \
FN(perf_prog_read_value), \
- FN(getsockopt),
+ FN(getsockopt), \
+ FN(override_return),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b9f8686a84cf..fc5a8ab4239a 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1320,6 +1320,9 @@ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
+ if (fp->kprobe_override)
+ return false;
+
if (!array->owner_prog_type) {
/* There's no owner yet where we could check for
* compatibility.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7afa92e9b409..e807bda7fe29 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4413,6 +4413,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
prog->dst_needed = 1;
if (insn->imm == BPF_FUNC_get_prandom_u32)
bpf_user_rnd_init_once();
+ if (insn->imm == BPF_FUNC_override_return)
+ prog->kprobe_override = 1;
if (insn->imm == BPF_FUNC_tail_call) {
/* If we tail call into other programs, we
* cannot make any assumptions since they can
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 16beab4767e1..6e3862bbe9c2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8077,6 +8077,13 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
return -EINVAL;
}
+ /* Kprobe override only works for kprobes, not uprobes. */
+ if (prog->kprobe_override &&
+ !(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) {
+ bpf_prog_put(prog);
+ return -EINVAL;
+ }
+
if (is_tracepoint || is_syscall_tp) {
int off = trace_event_get_offsets(event->tp_event);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index af7dad126c13..3e6fd580fe7f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -529,6 +529,17 @@ config FUNCTION_PROFILER
If in doubt, say N.
+config BPF_KPROBE_OVERRIDE
+ bool "Enable BPF programs to override a kprobed function"
+ depends on BPF_EVENTS
+ depends on KPROBES_ON_FTRACE
+ depends on HAVE_KPROBE_OVERRIDE
+ depends on DYNAMIC_FTRACE_WITH_REGS
+ default n
+ help
+ Allows BPF to override the execution of a probed function and
+ set a different return value. This is used for error injection.
+
config FTRACE_MCOUNT_RECORD
def_bool y
depends on DYNAMIC_FTRACE
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 27d1f4ffa3de..e4bfdbc5a905 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -13,6 +13,10 @@
#include <linux/filter.h>
#include <linux/uaccess.h>
#include <linux/ctype.h>
+#include <linux/kprobes.h>
+#include <asm/kprobes.h>
+
+#include "trace_probe.h"
#include "trace.h"
u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
@@ -76,6 +80,29 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
}
EXPORT_SYMBOL_GPL(trace_call_bpf);
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
+{
+ __this_cpu_write(bpf_kprobe_override, 1);
+ regs_set_return_value(regs, rc);
+ arch_ftrace_kprobe_override_function(regs);
+ return 0;
+}
+#else
+BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc)
+{
+ return -EINVAL;
+}
+#endif
+
+static const struct bpf_func_proto bpf_override_return_proto = {
+ .func = bpf_override_return,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+};
+
BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
{
int ret;
@@ -551,6 +578,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
return &bpf_get_stackid_proto;
case BPF_FUNC_perf_event_read_value:
return &bpf_perf_event_read_value_proto;
+ case BPF_FUNC_override_return:
+ return &bpf_override_return_proto;
default:
return tracing_func_proto(func_id);
}
@@ -766,6 +795,15 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
struct bpf_prog_array *new_array;
int ret = -EEXIST;
+ /*
+ * Kprobe override only works for ftrace based kprobes, and only if they
+ * are on the opt-in list.
+ */
+ if (prog->kprobe_override &&
+ (!trace_kprobe_ftrace(event->tp_event) ||
+ !trace_kprobe_error_injectable(event->tp_event)))
+ return -EINVAL;
+
mutex_lock(&bpf_event_mutex);
if (event->prog)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 492700c5fb4d..5db849809a56 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -42,6 +42,7 @@ struct trace_kprobe {
(offsetof(struct trace_kprobe, tp.args) + \
(sizeof(struct probe_arg) * (n)))
+DEFINE_PER_CPU(int, bpf_kprobe_override);
static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk)
{
@@ -87,6 +88,27 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk)
return nhit;
}
+int trace_kprobe_ftrace(struct trace_event_call *call)
+{
+ struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
+ return kprobe_ftrace(&tk->rp.kp);
+}
+
+int trace_kprobe_error_injectable(struct trace_event_call *call)
+{
+ struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
+ unsigned long addr;
+
+ if (tk->symbol) {
+ addr = (unsigned long)
+ kallsyms_lookup_name(trace_kprobe_symbol(tk));
+ addr += tk->rp.kp.offset;
+ } else {
+ addr = (unsigned long)tk->rp.kp.addr;
+ }
+ return within_kprobe_error_injection_list(addr);
+}
+
static int register_kprobe_event(struct trace_kprobe *tk);
static int unregister_kprobe_event(struct trace_kprobe *tk);
@@ -1170,7 +1192,7 @@ static int kretprobe_event_define_fields(struct trace_event_call *event_call)
#ifdef CONFIG_PERF_EVENTS
/* Kprobe profile handler */
-static void
+static int
kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
struct trace_event_call *call = &tk->tp.call;
@@ -1179,12 +1201,29 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
int size, __size, dsize;
int rctx;
- if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs))
- return;
+ if (bpf_prog_array_valid(call)) {
+ int ret;
+
+ ret = trace_call_bpf(call, regs);
+
+ /*
+ * We need to check and see if we modified the pc of the
+ * pt_regs, and if so clear the kprobe and return 1 so that we
+ * don't do the instruction skipping. Also reset our state so
+ * we are clean the next pass through.
+ */
+ if (__this_cpu_read(bpf_kprobe_override)) {
+ __this_cpu_write(bpf_kprobe_override, 0);
+ reset_current_kprobe();
+ return 1;
+ }
+ if (!ret)
+ return 0;
+ }
head = this_cpu_ptr(call->perf_events);
if (hlist_empty(head))
- return;
+ return 0;
dsize = __get_data_size(&tk->tp, regs);
__size = sizeof(*entry) + tk->tp.size + dsize;
@@ -1193,13 +1232,14 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
entry = perf_trace_buf_alloc(size, NULL, &rctx);
if (!entry)
- return;
+ return 0;
entry->ip = (unsigned long)tk->rp.kp.addr;
memset(&entry[1], 0, dsize);
store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
head, NULL);
+ return 0;
}
NOKPROBE_SYMBOL(kprobe_perf_func);
@@ -1275,6 +1315,7 @@ static int kprobe_register(struct trace_event_call *event,
static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
{
struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
+ int ret = 0;
raw_cpu_inc(*tk->nhit);
@@ -1282,9 +1323,9 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
kprobe_trace_func(tk, regs);
#ifdef CONFIG_PERF_EVENTS
if (tk->tp.flags & TP_FLAG_PROFILE)
- kprobe_perf_func(tk, regs);
+ ret = kprobe_perf_func(tk, regs);
#endif
- return 0; /* We don't tweek kernel, so just return 0 */
+ return ret;
}
NOKPROBE_SYMBOL(kprobe_dispatcher);
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index fb66e3eaa192..5e54d748c84c 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -252,6 +252,8 @@ struct symbol_cache;
unsigned long update_symbol_cache(struct symbol_cache *sc);
void free_symbol_cache(struct symbol_cache *sc);
struct symbol_cache *alloc_symbol_cache(const char *sym, long offset);
+int trace_kprobe_ftrace(struct trace_event_call *call);
+int trace_kprobe_error_injectable(struct trace_event_call *call);
#else
/* uprobes do not support symbol fetch methods */
#define fetch_symbol_u8 NULL
@@ -277,6 +279,16 @@ alloc_symbol_cache(const char *sym, long offset)
{
return NULL;
}
+
+static inline int trace_kprobe_ftrace(struct trace_event_call *call)
+{
+ return 0;
+}
+
+static inline int trace_kprobe_error_injectable(struct trace_event_call *call)
+{
+ return 0;
+}
#endif /* CONFIG_KPROBE_EVENTS */
struct probe_arg {
--
2.7.5
^ permalink raw reply related
* [PATCH v9 5/5] btrfs: allow us to inject errors at io_ctl_init
From: Josef Bacik @ 2017-12-11 16:36 UTC (permalink / raw)
To: rostedt, mingo, davem, netdev, linux-kernel, ast, kernel-team,
daniel, linux-btrfs
Cc: Josef Bacik
In-Reply-To: <1513010210-30594-1-git-send-email-josef@toxicpanda.com>
From: Josef Bacik <jbacik@fb.com>
This was instrumental in reproducing a space cache bug.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
fs/btrfs/free-space-cache.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 4426d1c73e50..fb1382893bfc 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -22,6 +22,7 @@
#include <linux/slab.h>
#include <linux/math64.h>
#include <linux/ratelimit.h>
+#include <linux/bpf.h>
#include "ctree.h"
#include "free-space-cache.h"
#include "transaction.h"
@@ -332,6 +333,7 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
return 0;
}
+BPF_ALLOW_ERROR_INJECTION(io_ctl_init);
static void io_ctl_free(struct btrfs_io_ctl *io_ctl)
{
--
2.7.5
^ permalink raw reply related
* [PATCH v9 4/5] samples/bpf: add a test for bpf_override_return
From: Josef Bacik @ 2017-12-11 16:36 UTC (permalink / raw)
To: rostedt, mingo, davem, netdev, linux-kernel, ast, kernel-team,
daniel, linux-btrfs
Cc: Josef Bacik
In-Reply-To: <1513010210-30594-1-git-send-email-josef@toxicpanda.com>
From: Josef Bacik <jbacik@fb.com>
This adds a basic test for bpf_override_return to verify it works. We
override the main function for mounting a btrfs fs so it'll return
-ENOMEM and then make sure that trying to mount a btrfs fs will fail.
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
samples/bpf/Makefile | 4 ++++
samples/bpf/test_override_return.sh | 15 +++++++++++++++
samples/bpf/tracex7_kern.c | 16 ++++++++++++++++
samples/bpf/tracex7_user.c | 28 ++++++++++++++++++++++++++++
tools/include/uapi/linux/bpf.h | 7 ++++++-
tools/testing/selftests/bpf/bpf_helpers.h | 3 ++-
6 files changed, 71 insertions(+), 2 deletions(-)
create mode 100755 samples/bpf/test_override_return.sh
create mode 100644 samples/bpf/tracex7_kern.c
create mode 100644 samples/bpf/tracex7_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index adeaa1302f34..4fb944a7ecf8 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -12,6 +12,7 @@ hostprogs-y += tracex3
hostprogs-y += tracex4
hostprogs-y += tracex5
hostprogs-y += tracex6
+hostprogs-y += tracex7
hostprogs-y += test_probe_write_user
hostprogs-y += trace_output
hostprogs-y += lathist
@@ -58,6 +59,7 @@ tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o
tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o
tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o
tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o
+tracex7-objs := bpf_load.o $(LIBBPF) tracex7_user.o
load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o
test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o
trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o
@@ -101,6 +103,7 @@ always += tracex3_kern.o
always += tracex4_kern.o
always += tracex5_kern.o
always += tracex6_kern.o
+always += tracex7_kern.o
always += sock_flags_kern.o
always += test_probe_write_user_kern.o
always += trace_output_kern.o
@@ -155,6 +158,7 @@ HOSTLOADLIBES_tracex3 += -lelf
HOSTLOADLIBES_tracex4 += -lelf -lrt
HOSTLOADLIBES_tracex5 += -lelf
HOSTLOADLIBES_tracex6 += -lelf
+HOSTLOADLIBES_tracex7 += -lelf
HOSTLOADLIBES_test_cgrp2_sock2 += -lelf
HOSTLOADLIBES_load_sock_ops += -lelf
HOSTLOADLIBES_test_probe_write_user += -lelf
diff --git a/samples/bpf/test_override_return.sh b/samples/bpf/test_override_return.sh
new file mode 100755
index 000000000000..e68b9ee6814b
--- /dev/null
+++ b/samples/bpf/test_override_return.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+
+rm -f testfile.img
+dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1
+DEVICE=$(losetup --show -f testfile.img)
+mkfs.btrfs -f $DEVICE
+mkdir tmpmnt
+./tracex7 $DEVICE
+if [ $? -eq 0 ]
+then
+ echo "SUCCESS!"
+else
+ echo "FAILED!"
+fi
+losetup -d $DEVICE
diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c
new file mode 100644
index 000000000000..1ab308a43e0f
--- /dev/null
+++ b/samples/bpf/tracex7_kern.c
@@ -0,0 +1,16 @@
+#include <uapi/linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <linux/version.h>
+#include "bpf_helpers.h"
+
+SEC("kprobe/open_ctree")
+int bpf_prog1(struct pt_regs *ctx)
+{
+ unsigned long rc = -12;
+
+ bpf_override_return(ctx, rc);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c
new file mode 100644
index 000000000000..8a52ac492e8b
--- /dev/null
+++ b/samples/bpf/tracex7_user.c
@@ -0,0 +1,28 @@
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <linux/bpf.h>
+#include <unistd.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+int main(int argc, char **argv)
+{
+ FILE *f;
+ char filename[256];
+ char command[256];
+ int ret;
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+
+ snprintf(command, 256, "mount %s tmpmnt/", argv[1]);
+ f = popen(command, "r");
+ ret = pclose(f);
+
+ return ret ? 0 : 1;
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4c223ab30293..cf446c25c0ec 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -677,6 +677,10 @@ union bpf_attr {
* @buf: buf to fill
* @buf_size: size of the buf
* Return : 0 on success or negative error code
+ *
+ * int bpf_override_return(pt_regs, rc)
+ * @pt_regs: pointer to struct pt_regs
+ * @rc: the return value to set
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -736,7 +740,8 @@ union bpf_attr {
FN(xdp_adjust_meta), \
FN(perf_event_read_value), \
FN(perf_prog_read_value), \
- FN(getsockopt),
+ FN(getsockopt), \
+ FN(override_return),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index fd9a17fa8a8b..33cb00e46c49 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -82,7 +82,8 @@ static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
unsigned int buf_size) =
(void *) BPF_FUNC_perf_prog_read_value;
-
+static int (*bpf_override_return)(void *ctx, unsigned long rc) =
+ (void *) BPF_FUNC_override_return;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
--
2.7.5
^ permalink raw reply related
* [PATCH v9 2/5] btrfs: make open_ctree error injectable
From: Josef Bacik @ 2017-12-11 16:36 UTC (permalink / raw)
To: rostedt, mingo, davem, netdev, linux-kernel, ast, kernel-team,
daniel, linux-btrfs
Cc: Josef Bacik
In-Reply-To: <1513010210-30594-1-git-send-email-josef@toxicpanda.com>
From: Josef Bacik <jbacik@fb.com>
This allows us to do error injection with BPF for open_ctree.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
fs/btrfs/disk-io.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 10a2a579cc7f..02b5f5667754 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -30,6 +30,7 @@
#include <linux/ratelimit.h>
#include <linux/uuid.h>
#include <linux/semaphore.h>
+#include <linux/bpf.h>
#include <asm/unaligned.h>
#include "ctree.h"
#include "disk-io.h"
@@ -3123,6 +3124,7 @@ int open_ctree(struct super_block *sb,
goto fail_block_groups;
goto retry_root_backup;
}
+BPF_ALLOW_ERROR_INJECTION(open_ctree);
static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
{
--
2.7.5
^ permalink raw reply related
* [PATCH v9 1/5] add infrastructure for tagging functions as error injectable
From: Josef Bacik @ 2017-12-11 16:36 UTC (permalink / raw)
To: rostedt, mingo, davem, netdev, linux-kernel, ast, kernel-team,
daniel, linux-btrfs
Cc: Josef Bacik
In-Reply-To: <1513010210-30594-1-git-send-email-josef@toxicpanda.com>
From: Josef Bacik <jbacik@fb.com>
Using BPF we can override kprob'ed functions and return arbitrary
values. Obviously this can be a bit unsafe, so make this feature opt-in
for functions. Simply tag a function with KPROBE_ERROR_INJECT_SYMBOL in
order to give BPF access to that function for error injection purposes.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
include/asm-generic/vmlinux.lds.h | 10 +++
include/linux/bpf.h | 11 +++
include/linux/kprobes.h | 1 +
include/linux/module.h | 5 ++
kernel/kprobes.c | 163 ++++++++++++++++++++++++++++++++++++++
kernel/module.c | 6 +-
6 files changed, 195 insertions(+), 1 deletion(-)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index ee8b707d9fa9..a2e8582d094a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -136,6 +136,15 @@
#define KPROBE_BLACKLIST()
#endif
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+#define ERROR_INJECT_LIST() . = ALIGN(8); \
+ VMLINUX_SYMBOL(__start_kprobe_error_inject_list) = .; \
+ KEEP(*(_kprobe_error_inject_list)) \
+ VMLINUX_SYMBOL(__stop_kprobe_error_inject_list) = .;
+#else
+#define ERROR_INJECT_LIST()
+#endif
+
#ifdef CONFIG_EVENT_TRACING
#define FTRACE_EVENTS() . = ALIGN(8); \
VMLINUX_SYMBOL(__start_ftrace_events) = .; \
@@ -564,6 +573,7 @@
FTRACE_EVENTS() \
TRACE_SYSCALLS() \
KPROBE_BLACKLIST() \
+ ERROR_INJECT_LIST() \
MEM_DISCARD(init.rodata) \
CLK_OF_TABLES() \
RESERVEDMEM_OF_TABLES() \
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e55e4255a210..7f4d2a953173 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -576,4 +576,15 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto;
void bpf_user_rnd_init_once(void);
u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+#define BPF_ALLOW_ERROR_INJECTION(fname) \
+static unsigned long __used \
+ __attribute__((__section__("_kprobe_error_inject_list"))) \
+ _eil_addr_##fname = (unsigned long)fname;
+#else
+#define BPF_ALLOW_ERROR_INJECTION(fname)
+#endif
+#endif
+
#endif /* _LINUX_BPF_H */
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9440a2fc8893..963fd364f3d6 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -271,6 +271,7 @@ extern bool arch_kprobe_on_func_entry(unsigned long offset);
extern bool kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
extern bool within_kprobe_blacklist(unsigned long addr);
+extern bool within_kprobe_error_injection_list(unsigned long addr);
struct kprobe_insn_cache {
struct mutex mutex;
diff --git a/include/linux/module.h b/include/linux/module.h
index c69b49abe877..548fa09fa806 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -475,6 +475,11 @@ struct module {
ctor_fn_t *ctors;
unsigned int num_ctors;
#endif
+
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+ unsigned int num_kprobe_ei_funcs;
+ unsigned long *kprobe_ei_funcs;
+#endif
} ____cacheline_aligned __randomize_layout;
#ifndef MODULE_ARCH_INIT
#define MODULE_ARCH_INIT {}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index da2ccf142358..b4aab48ad258 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -83,6 +83,16 @@ static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
return &(kretprobe_table_locks[hash].lock);
}
+/* List of symbols that can be overriden for error injection. */
+static LIST_HEAD(kprobe_error_injection_list);
+static DEFINE_MUTEX(kprobe_ei_mutex);
+struct kprobe_ei_entry {
+ struct list_head list;
+ unsigned long start_addr;
+ unsigned long end_addr;
+ void *priv;
+};
+
/* Blacklist -- list of struct kprobe_blacklist_entry */
static LIST_HEAD(kprobe_blacklist);
@@ -1394,6 +1404,17 @@ bool within_kprobe_blacklist(unsigned long addr)
return false;
}
+bool within_kprobe_error_injection_list(unsigned long addr)
+{
+ struct kprobe_ei_entry *ent;
+
+ list_for_each_entry(ent, &kprobe_error_injection_list, list) {
+ if (addr >= ent->start_addr && addr < ent->end_addr)
+ return true;
+ }
+ return false;
+}
+
/*
* If we have a symbol_name argument, look it up and add the offset field
* to it. This way, we can specify a relative address to a symbol.
@@ -2168,6 +2189,86 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
return 0;
}
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+/* Markers of the _kprobe_error_inject_list section */
+extern unsigned long __start_kprobe_error_inject_list[];
+extern unsigned long __stop_kprobe_error_inject_list[];
+
+/*
+ * Lookup and populate the kprobe_error_injection_list.
+ *
+ * For safety reasons we only allow certain functions to be overriden with
+ * bpf_error_injection, so we need to populate the list of the symbols that have
+ * been marked as safe for overriding.
+ */
+static void populate_kprobe_error_injection_list(unsigned long *start,
+ unsigned long *end,
+ void *priv)
+{
+ unsigned long *iter;
+ struct kprobe_ei_entry *ent;
+ unsigned long entry, offset = 0, size = 0;
+
+ mutex_lock(&kprobe_ei_mutex);
+ for (iter = start; iter < end; iter++) {
+ entry = arch_deref_entry_point((void *)*iter);
+
+ if (!kernel_text_address(entry) ||
+ !kallsyms_lookup_size_offset(entry, &size, &offset)) {
+ pr_err("Failed to find error inject entry at %p\n",
+ (void *)entry);
+ continue;
+ }
+
+ ent = kmalloc(sizeof(*ent), GFP_KERNEL);
+ if (!ent)
+ break;
+ ent->start_addr = entry;
+ ent->end_addr = entry + size;
+ ent->priv = priv;
+ INIT_LIST_HEAD(&ent->list);
+ list_add_tail(&ent->list, &kprobe_error_injection_list);
+ }
+ mutex_unlock(&kprobe_ei_mutex);
+}
+
+static void __init populate_kernel_kprobe_ei_list(void)
+{
+ populate_kprobe_error_injection_list(__start_kprobe_error_inject_list,
+ __stop_kprobe_error_inject_list,
+ NULL);
+}
+
+static void module_load_kprobe_ei_list(struct module *mod)
+{
+ if (!mod->num_kprobe_ei_funcs)
+ return;
+ populate_kprobe_error_injection_list(mod->kprobe_ei_funcs,
+ mod->kprobe_ei_funcs +
+ mod->num_kprobe_ei_funcs, mod);
+}
+
+static void module_unload_kprobe_ei_list(struct module *mod)
+{
+ struct kprobe_ei_entry *ent, *n;
+ if (!mod->num_kprobe_ei_funcs)
+ return;
+
+ mutex_lock(&kprobe_ei_mutex);
+ list_for_each_entry_safe(ent, n, &kprobe_error_injection_list, list) {
+ if (ent->priv == mod) {
+ list_del_init(&ent->list);
+ kfree(ent);
+ }
+ }
+ mutex_unlock(&kprobe_ei_mutex);
+}
+#else
+static inline void __init populate_kernel_kprobe_ei_list(void) {}
+static inline void module_load_kprobe_ei_list(struct module *m) {}
+static inline void module_unload_kprobe_ei_list(struct module *m) {}
+#endif
+
/* Module notifier call back, checking kprobes on the module */
static int kprobes_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
@@ -2178,6 +2279,11 @@ static int kprobes_module_callback(struct notifier_block *nb,
unsigned int i;
int checkcore = (val == MODULE_STATE_GOING);
+ if (val == MODULE_STATE_COMING)
+ module_load_kprobe_ei_list(mod);
+ else if (val == MODULE_STATE_GOING)
+ module_unload_kprobe_ei_list(mod);
+
if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE)
return NOTIFY_DONE;
@@ -2240,6 +2346,8 @@ static int __init init_kprobes(void)
pr_err("Please take care of using kprobes.\n");
}
+ populate_kernel_kprobe_ei_list();
+
if (kretprobe_blacklist_size) {
/* lookup the function address from its name */
for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
@@ -2407,6 +2515,56 @@ static const struct file_operations debugfs_kprobe_blacklist_ops = {
.release = seq_release,
};
+/*
+ * kprobes/error_injection_list -- shows which functions can be overriden for
+ * error injection.
+ * */
+static void *kprobe_ei_seq_start(struct seq_file *m, loff_t *pos)
+{
+ mutex_lock(&kprobe_ei_mutex);
+ return seq_list_start(&kprobe_error_injection_list, *pos);
+}
+
+static void kprobe_ei_seq_stop(struct seq_file *m, void *v)
+{
+ mutex_unlock(&kprobe_ei_mutex);
+}
+
+static void *kprobe_ei_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ return seq_list_next(v, &kprobe_error_injection_list, pos);
+}
+
+static int kprobe_ei_seq_show(struct seq_file *m, void *v)
+{
+ char buffer[KSYM_SYMBOL_LEN];
+ struct kprobe_ei_entry *ent =
+ list_entry(v, struct kprobe_ei_entry, list);
+
+ sprint_symbol(buffer, ent->start_addr);
+ seq_printf(m, "%s\n", buffer);
+ return 0;
+}
+
+static const struct seq_operations kprobe_ei_seq_ops = {
+ .start = kprobe_ei_seq_start,
+ .next = kprobe_ei_seq_next,
+ .stop = kprobe_ei_seq_stop,
+ .show = kprobe_ei_seq_show,
+};
+
+static int kprobe_ei_open(struct inode *inode, struct file *filp)
+{
+ return seq_open(filp, &kprobe_ei_seq_ops);
+}
+
+static const struct file_operations debugfs_kprobe_ei_ops = {
+ .open = kprobe_ei_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
static void arm_all_kprobes(void)
{
struct hlist_head *head;
@@ -2548,6 +2706,11 @@ static int __init debugfs_kprobe_init(void)
if (!file)
goto error;
+ file = debugfs_create_file("error_injection_list", 0444, dir, NULL,
+ &debugfs_kprobe_ei_ops);
+ if (!file)
+ goto error;
+
return 0;
error:
diff --git a/kernel/module.c b/kernel/module.c
index dea01ac9cb74..bd695bfdc5c4 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3118,7 +3118,11 @@ static int find_module_sections(struct module *mod, struct load_info *info)
sizeof(*mod->ftrace_callsites),
&mod->num_ftrace_callsites);
#endif
-
+#ifdef CONFIG_BPF_KPROBE_OVERRIDE
+ mod->kprobe_ei_funcs = section_objs(info, "_kprobe_error_inject_list",
+ sizeof(*mod->kprobe_ei_funcs),
+ &mod->num_kprobe_ei_funcs);
+#endif
mod->extable = section_objs(info, "__ex_table",
sizeof(*mod->extable), &mod->num_exentries);
--
2.7.5
^ permalink raw reply related
* [PATCH v9 0/5] Add the ability to do BPF directed error injection
From: Josef Bacik @ 2017-12-11 16:36 UTC (permalink / raw)
To: rostedt, mingo, davem, netdev, linux-kernel, ast, kernel-team,
daniel, linux-btrfs
This is the same as v8, just rebased onto the bpf tree.
v8->v9:
- rebased onto the bpf tree.
v7->v8:
- removed the _ASM_KPROBE_ERROR_INJECT since it was not needed.
v6->v7:
- moved the opt-in macro to bpf.h out of kprobes.h.
v5->v6:
- add BPF_ALLOW_ERROR_INJECTION() tagging for functions that will support this
feature. This way only functions that opt-in will be allowed to be
overridden.
- added a btrfs patch to allow error injection for open_ctree() so that the bpf
sample actually works.
v4->v5:
- disallow kprobe_override programs from being put in the prog map array so we
don't tail call into something we didn't check. This allows us to make the
normal path still fast without a bunch of percpu operations.
v3->v4:
- fix a build error found by kbuild test bot (I didn't wait long enough
apparently.)
- Added a warning message as per Daniels suggestion.
v2->v3:
- added a ->kprobe_override flag to bpf_prog.
- added some sanity checks to disallow attaching bpf progs that have
->kprobe_override set that aren't for ftrace kprobes.
- added the trace_kprobe_ftrace helper to check if the trace_event_call is a
ftrace kprobe.
- renamed bpf_kprobe_state to bpf_kprobe_override, fixed it so we only read this
value in the kprobe path, and thus only write to it if we're overriding or
clearing the override.
v1->v2:
- moved things around to make sure that bpf_override_return could really only be
used for an ftrace kprobe.
- killed the special return values from trace_call_bpf.
- renamed pc_modified to bpf_kprobe_state so bpf_override_return could tell if
it was being called from an ftrace kprobe context.
- reworked the logic in kprobe_perf_func to take advantage of bpf_kprobe_state.
- updated the test as per Alexei's review.
- Original message -
A lot of our error paths are not well tested because we have no good way of
injecting errors generically. Some subystems (block, memory) have ways to
inject errors, but they are random so it's hard to get reproduceable results.
With BPF we can add determinism to our error injection. We can use kprobes and
other things to verify we are injecting errors at the exact case we are trying
to test. This patch gives us the tool to actual do the error injection part.
It is very simple, we just set the return value of the pt_regs we're given to
whatever we provide, and then override the PC with a dummy function that simply
returns.
Right now this only works on x86, but it would be simple enough to expand to
other architectures. Thanks,
Josef
^ permalink raw reply
* Re: Waiting for the PHY to complete auto-negotiation
From: Måns Rullgård @ 2017-12-11 16:32 UTC (permalink / raw)
To: Mason; +Cc: Florian Fainelli, Andrew Lunn, netdev, David Miller
In-Reply-To: <e968c0cf-f69f-7f1d-a0db-b856f4c50755@free.fr>
Mason <slash.tmp@free.fr> writes:
> On 11/12/2017 15:36, Måns Rullgård wrote:
>
>> Mason writes:
>>
>>> I suppose I should test forcefully setting the enable bit to 0 in
>>> the driver, and see if hell breaks loose.
>>
>> You can't. When the enable bit is 1, writes to that register are
>> ignored. It goes back to 0 automatically when the hw runs out of
>> descriptors.
>
> I don't think they are ignored, because toggling the control flow
> bit actually breaks RX.
Oh, then it's even worse than the docs suggest.
--
Måns Rullgård
^ permalink raw reply
* Re: [RFC PATCH 0/9] ethtool netlink interface (WiP)
From: Jiri Pirko @ 2017-12-11 16:32 UTC (permalink / raw)
To: Michal Kubecek; +Cc: netdev, linux-kernel
In-Reply-To: <cover.1513000306.git.mkubecek@suse.cz>
Mon, Dec 11, 2017 at 02:53:11PM CET, mkubecek@suse.cz wrote:
>This is still work in progress and only a very small part of the ioctl
>interface is reimplemented but I would like to get some comments before
>the patchset becomes too big and changing things becomes too tedious.
>
>The interface used for communication between ethtool and kernel is based on
>ioctl() and suffers from many problems. The most pressing seems the be the
>lack of extensibility. While some of the newer commands use structures
>designed to allow future extensions (e.g. GFEATURES or TEST), most either
>allow no extension at all (GPAUSEPARAM, GCOALESCE) or only limited set of
>reserved fields (GDRVINFO, GEEE). Even most of those which support future
>extensions limit the data types that can be used.
>
>This series aims to provide an alternative interface based on netlink which
>is what other network configuration utilities use. In particular, it uses
>generic netlink (family "ethtool"). The goal is to provide an interface
>which would be extensible, flexible and practical both for ethtool and for
>other network configuration tools (e.g. wicked or systemd-networkd).
>
>The interface is documented in Documentation/networking/ethtool-netlink.txt
>
>I'll post RFC patch series for ethtool in a few days, it still needs some
>more polishing.
First of all, thank you Michale for taking a stab at this!
I think that it does not make sense to convert ethtool->netlink_ethtool
1:1 feature wise. Now we have devlink, ritch switch representation
model, tc offload and many others. Lot of things that are in
ethtool, should be done in devlink. Also, there are couple of things
that should just die - nice example is ethtool --config-ntuple - we
should use tc for that.
So I believe that it would be better to introduce new iterface called
differently, to avoid confusion, like "ethlink" and start to migrate
things there, without existing baggage. In kernel the existing ethtool
would just call compat layer inside ethlink code. Similarly with devlink.
ethtool api would freeze. Similar scenario to rtnetlink and legacy ioctl.
Also, this new netlink iface should have userspace notification
support from day 1.
^ permalink raw reply
* Re: RFC(v2): Audit Kernel Container IDs
From: Eric Paris @ 2017-12-11 16:30 UTC (permalink / raw)
To: Casey Schaufler, Mickaël Salaün, Richard Guy Briggs,
cgroups, Linux Containers, Linux API, Linux Audit, Linux FS Devel,
Linux Kernel, Linux Network Development
Cc: mszeredi, Eric W. Biederman, Simo Sorce, jlayton,
Carlos O'Donell, David Howells, Al Viro, Andy Lutomirski,
Eric Paris, trondmy, Michael Kerrisk
In-Reply-To: <f8ea78be-9bbf-2967-7b12-ac93bb85b0bc@schaufler-ca.com>
On Sat, 2017-12-09 at 10:28 -0800, Casey Schaufler wrote:
> On 12/9/2017 2:20 AM, Micka�l Sala�n wrote:
> > What about automatically create
> > and assign an ID to a process when it enters a namespace different
> > than
> > one of its parent process? This delegates the (permission)
> > responsibility to the use of namespaces (e.g. /proc/sys/user/max_*
> > limit).
>
> That gets ugly when you have a container that uses user, filesystem,
> network and whatever else namespaces. If all containers used the same
> set of namespaces I think this would be a fine idea, but they don't.
>
> > One interesting side effect of this approach would be to be able to
> > identify which processes are in the same set of namespaces, even if
> > not
> > spawn from the container but entered after its creation (i.e. using
> > setns), by creating container IDs as a (deterministic) checksum
> > from the
> > /proc/self/ns/* IDs.
> >
> > Since the concern is to identify a container, I think the ability
> > to
> > audit the switch from one container ID to another is enough. I
> > don't
> > think we need nested IDs.
>
> Because a container doesn't have to use namespaces to be a container
> you still need a mechanism for a process to declare that it is in
> fact
> in a container, and to identify the container.
I like the idea but I'm still tossing it around in my head (and
thinking about Casey's statement too). Lets say we have a 'docker-like'
container with pid=100 netns=X,userns=Y,mountns=Z. If I'm on the host
in all init namespaces and I run
nsenter -t 100 -n ip link set eth0 promisc on
How should this be logged? Did this command run in it's own 'container'
unrelated to the 'docker-like' container?
-Eric
^ permalink raw reply
* Re: [PATCH] dt-bindings: fec: Make the phy-reset-gpio polarity explicit
From: David Miller @ 2017-12-11 16:27 UTC (permalink / raw)
To: festevam; +Cc: fugang.duan, robh+dt, netdev, fabio.estevam
In-Reply-To: <1512742293-14572-1-git-send-email-festevam@gmail.com>
From: Fabio Estevam <festevam@gmail.com>
Date: Fri, 8 Dec 2017 12:11:33 -0200
> From: Fabio Estevam <fabio.estevam@nxp.com>
>
> The GPIO polarity passed to phy-reset-gpio is ignored by the FEC
> driver and it is assumed to be active low.
>
> It can be active high only when the 'phy-reset-active-high' property
> is present.
>
> The current examples pass active high polarity and work fine, but
> in order to improve the documentation make it explicit what the real
> polarity is.
>
> Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Applied to net-next.
^ permalink raw reply
* Re: [PATCHv2 net-next 00/12] sctp: Implement Stream Interleave: The I-DATA Chunk Supporting User Message Interleaving
From: David Miller @ 2017-12-11 16:23 UTC (permalink / raw)
To: lucien.xin; +Cc: netdev, linux-sctp, marcelo.leitner, nhorman
In-Reply-To: <cover.1512738021.git.lucien.xin@gmail.com>
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 8 Dec 2017 21:03:57 +0800
> Stream Interleave would be Implemented in two Parts:
>
> 1. The I-DATA Chunk Supporting User Message Interleaving
> 2. Interaction with Other SCTP Extensions
...
> As the 1st part of Stream Interleave Implementation, this patchset adds
> an ops framework named sctp_stream_interleave with a bunch of stuff that
> does lots of things needed somewhere.
>
> Then it defines sctp_stream_interleave_0 to work for normal DATA chunks
> and sctp_stream_interleave_1 for I-DATA chunks.
>
> With these functions, hundreds of if-else checks for the different process
> on I-DATA chunks would be avoided. Besides, very few codes could be shared
> in these two function sets.
>
> In this patchset, it adds some basic variables, structures and socket
> options firstly, then implement these functions one by one to add the
> procedures for ordered idata gradually, at last adjusts some codes to
> make them work for unordered idata.
>
> To make it safe to be implemented and also not break the normal data
> chunk process, this feature can't be enabled to use until all stream
> interleave codes are completely accomplished.
>
> v1 -> v2:
> - fixed a checkpatch warning that a blank line was missed.
> - avoided a kbuild warning reported from gcc-4.9.
Series applied, thanks Xin.
^ permalink raw reply
* Re: [PATCH net v3] net: phy: meson-gxl: detect LPA corruption
From: David Miller @ 2017-12-11 16:19 UTC (permalink / raw)
To: jbrunet
Cc: andrew, f.fainelli, khilman, netdev, linux-arm-kernel,
linux-amlogic, linux-kernel
In-Reply-To: <20171208110811.30789-1-jbrunet@baylibre.com>
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Fri, 8 Dec 2017 12:08:11 +0100
> I suppose this patch probably seems a bit hacky, especially the part
> about the link partner acknowledge. I'm trying to figure out if the
> value in MII_LPA makes sense but I don't have such a deep knowledge
> of the ethernet spec.
Yeah it's not the prettiest thing in the world, but if this is what you
need to check to detect this situation then there isn't much else you
can do.
Applied, thanks.
^ permalink raw reply
* Re: [RFC PATCH 5/9] ethtool: implement GET_DRVINFO message
From: Jiri Pirko @ 2017-12-11 16:16 UTC (permalink / raw)
To: Michal Kubecek; +Cc: netdev, linux-kernel
In-Reply-To: <219f457821c4cbca64ead6a8f8a92246ed7f32a3.1513000306.git.mkubecek@suse.cz>
Mon, Dec 11, 2017 at 02:54:01PM CET, mkubecek@suse.cz wrote:
>Request the same information as ETHTOOL_GDRVINFO. This is read-only so that
>corresponding SET_DRVINFO exists but is only used in kernel replies. Rip
>the code to query the driver out of the legacy interface and move it to
>a new file ethtool_common.c so that both interfaces can use it.
>
>Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
>---
> Documentation/networking/ethtool-netlink.txt | 30 ++++++++++-
> include/uapi/linux/ethtool_netlink.h | 21 ++++++++
> net/core/Makefile | 2 +-
> net/core/ethtool.c | 42 +++-------------
> net/core/ethtool_common.c | 46 +++++++++++++++++
> net/core/ethtool_common.h | 11 ++++
> net/core/ethtool_netlink.c | 75 ++++++++++++++++++++++++++++
> 7 files changed, 189 insertions(+), 38 deletions(-)
> create mode 100644 net/core/ethtool_common.c
> create mode 100644 net/core/ethtool_common.h
>
>diff --git a/Documentation/networking/ethtool-netlink.txt b/Documentation/networking/ethtool-netlink.txt
>index 893e5156f6a7..cb992180b211 100644
>--- a/Documentation/networking/ethtool-netlink.txt
>+++ b/Documentation/networking/ethtool-netlink.txt
>@@ -107,6 +107,9 @@ which the request applies.
> List of message types
> ---------------------
>
>+ ETHTOOL_CMD_GET_DRVINFO
>+ ETHTOOL_CMD_SET_DRVINFO response only
>+
> All constants use ETHTOOL_CMD_ prefix followed by "GET", "SET" or "ACT" to
> indicate the type.
>
>@@ -119,6 +122,31 @@ messages marked as "response only" in the table above.
> Later sections describe the format and semantics of these request messages.
>
>
>+GET_DRVINFO
>+-----------
>+
>+GET_DRVINFO request corresponds to ETHTOOL_GDRVINFO ioctl command and provides
>+basic driver information. The request doesn't use any attributes and flags,
>+info_mask and index field in request header are ignored. Kernel response
>+contents:
>+
>+ ETHA_DRVINFO_DRIVER (string) driver name
>+ ETHA_DRVINFO_VERSION (string) driver version
You use 3 prefixes:
ETHTOOL_ for cmd
ETHA_ for attrs
ethnl_ for function
I suggest to sync this, perhaps to:
ETHNL_CMD_*
ETHNL_ATTR_*
ethnl_*
?
>+ ETHA_DRVINFO_FWVERSION (string) firmware version
>+ ETHA_DRVINFO_BUSINFO (string) device bus address
>+ ETHA_DRVINFO_EROM_VER (string) expansion ROM version
>+ ETHA_DRVINFO_N_PRIV_FLAGS (u32) number of private flags
>+ ETHA_DRVINFO_N_STATS (u32) number of device stats
>+ ETHA_DRVINFO_TESTINFO_LEN (u32) number of test results
>+ ETHA_DRVINFO_EEDUMP_LEN (u32) EEPROM dump size
>+ ETHA_DRVINFO_REGDUMP_LEN (u32) register dump size
We are now working on providing various fw memory regions dump in
devlink. It makes sense to have it in devlink for couple of reasons:
1) per-asic, not netdev specific, therefore does not really make sense
to have netdev as handle, but rather devlink handle.
2) snapshot support - we need to provide support for getting snapshot
(for example on failure), transferring to user and deleting it
(remove from driver memory).
Also, driver name, version, fwversion, etc is per-asic. Would make sense
to have it in devlink as well.
I think this is great opprotunity to move things where they should be to
be alligned with the current world and kernel infrastructure.
^ permalink raw reply
* Re: [PATCH next] ipvlan: add L2 check for packets arriving via virtual devices
From: David Miller @ 2017-12-11 16:15 UTC (permalink / raw)
To: mahesh; +Cc: netdev, edumazet, amit.sikka, maheshb
In-Reply-To: <20171207231543.7637-1-mahesh@bandewar.net>
From: Mahesh Bandewar <mahesh@bandewar.net>
Date: Thu, 7 Dec 2017 15:15:43 -0800
> From: Mahesh Bandewar <maheshb@google.com>
>
> Packets that don't have dest mac as the mac of the master device should
> not be entertained by the IPvlan rx-handler. This is mostly true as the
> packet path mostly takes care of that, except when the master device is
> a virtual device. As demonstrated in the following case -
...
> This patch adds that missing check in the IPvlan rx-handler.
>
> Reported-by: Amit Sikka <amit.sikka@ericsson.com>
> Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Applied, but it's a shame that the data plane takes on this new MAC
compare operation.
^ permalink raw reply
* Re: [PATCH V2] netlink: Add netns check on taps
From: Michal Kubecek @ 2017-12-11 16:13 UTC (permalink / raw)
To: David Miller
Cc: cernekee, johannes.berg, netdev, linux-kernel, daniel, dsahern
In-Reply-To: <20171206.155714.908446002721815545.davem@davemloft.net>
On Wed, Dec 06, 2017 at 03:57:14PM -0500, David Miller wrote:
> From: Kevin Cernekee <cernekee@chromium.org>
> Date: Wed, 6 Dec 2017 12:12:27 -0800
>
> > Currently, a nlmon link inside a child namespace can observe systemwide
> > netlink activity. Filter the traffic so that nlmon can only sniff
> > netlink messages from its own netns.
> >
> > Test case:
> >
> > vpnns -- bash -c "ip link add nlmon0 type nlmon; \
> > ip link set nlmon0 up; \
> > tcpdump -i nlmon0 -q -w /tmp/nlmon.pcap -U" &
> > sudo ip xfrm state add src 10.1.1.1 dst 10.1.1.2 proto esp \
> > spi 0x1 mode transport \
> > auth sha1 0x6162633132330000000000000000000000000000 \
> > enc aes 0x00000000000000000000000000000000
> > grep --binary abc123 /tmp/nlmon.pcap
> >
> > Signed-off-by: Kevin Cernekee <cernekee@chromium.org>
>
> Applied and queued up for -stable, thanks Kevin.
David,
this patch is marked as accepted in patchworks and listed in
http://patchwork.ozlabs.org/bundle/davem/stable/?state=*
but it's not in the net tree. Is there a problem with it?
Michal Kubecek
^ permalink raw reply
* RE: [PATCH V2 net-next 2/8] net: hns3: Add mailbox support to VF driver
From: Salil Mehta @ 2017-12-11 16:04 UTC (permalink / raw)
To: Philippe Ombredanne
Cc: David S. Miller, Zhuangyuzeng (Yisen), lipeng (Y),
mehta.salil.lnk@gmail.com, netdev@vger.kernel.org, LKML,
linux-rdma@vger.kernel.org, Linuxarm
In-Reply-To: <CAOFm3uH0G7hA0kpiH+SivdLQ6hH_Prq7_gHg6O-hoaO94dPoTQ@mail.gmail.com>
Hi Philippe,
> -----Original Message-----
> From: Philippe Ombredanne [mailto:pombredanne@nexb.com]
> Sent: Saturday, December 09, 2017 12:17 AM
> To: Salil Mehta <salil.mehta@huawei.com>
> Cc: David S. Miller <davem@davemloft.net>; Zhuangyuzeng (Yisen)
> <yisen.zhuang@huawei.com>; lipeng (Y) <lipeng321@huawei.com>;
> mehta.salil.lnk@gmail.com; netdev@vger.kernel.org; LKML <linux-
> kernel@vger.kernel.org>; linux-rdma@vger.kernel.org; Linuxarm
> <linuxarm@huawei.com>
> Subject: Re: [PATCH V2 net-next 2/8] net: hns3: Add mailbox support to
> VF driver
>
> Sali,
Sali ---> Salil
Thanks
>
> On Fri, Dec 8, 2017 at 10:16 PM, Salil Mehta <salil.mehta@huawei.com>
> wrote:
> > This patch adds the support of the mailbox to the VF driver. The
> > mailbox shall be used as an interface to communicate with the
> > PF driver for various purposes like {set|get} MAC related
> > operations, reset, link status etc. The mailbox supports both
> > synchronous and asynchronous command send to PF driver.
> >
> > Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
> > Signed-off-by: lipeng <lipeng321@huawei.com>
> [...]
> > --- /dev/null
> > +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
> > @@ -0,0 +1,94 @@
> > +/*
> > + * Copyright (c) 2016-2017 Hisilicon Limited.
> > + *
> > + * This program is free software; you can redistribute it and/or
> modify
> > + * it under the terms of the GNU General Public License as published
> by
> > + * the Free Software Foundation; either version 2 of the License, or
> > + * (at your option) any later version.
> > + */
>
> Why not use the new SPDX ids?
We can. I will change the headers for files [.c .h Makefile] part of HNS3
VF driver change in next V3 patch submit.
> e.g.
> > +/* SPDX-License-Identifier: GPL-2.0+ */
> > +/* Copyright (c) 2016-2017 Hisilicon Limited. */
>
> See Linus posts and Thomas doc patches for details.
Sure.
Thanks!
>
> --
> Cordially
> Philippe Ombredanne
^ permalink raw reply
* Re: [RFC PATCH 2/9] ethtool: introduce ethtool netlink interface
From: Jiri Pirko @ 2017-12-11 16:02 UTC (permalink / raw)
To: Michal Kubecek; +Cc: netdev, linux-kernel
In-Reply-To: <37174026f818dd1a61ca1b37bef2f1b114198de2.1513000306.git.mkubecek@suse.cz>
Mon, Dec 11, 2017 at 02:53:31PM CET, mkubecek@suse.cz wrote:
>No function implemented yet, only genetlink and module infrastructure.
>Register/unregister genetlink family "ethtool" and allow the module to be
>autoloaded by genetlink code (if built as a module, distributions would
>probably prefer "y").
>
>Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
[...]
>+
>+/* identifies the device to query/set
>+ * - use either ifindex or ifname, not both
>+ * - for dumps and messages not related to a particular devices, fill neither
>+ * - info_mask is a bitfield, interpretation depends on the command
>+ */
>+struct ethnlmsghdr {
>+ __u32 ifindex; /* device ifindex */
>+ __u16 flags; /* request/response flags */
>+ __u16 info_mask; /* request/response info mask */
>+ char ifname[IFNAMSIZ]; /* device name */
Why do you need this header? You can have 2 attrs:
ETHTOOL_ATTR_IFINDEX and
ETHTOOL_ATTR_IFNAME
Why do you need per-command flags and info_mask? Could be bitfield
attr if needed by specific command.
>+};
>+
>+#define ETHNL_HDRLEN NLMSG_ALIGN(sizeof(struct ethnlmsghdr))
>+
>+enum {
>+ ETHTOOL_CMD_NOOP,
>+
>+ __ETHTOOL_CMD_MAX,
>+ ETHTOOL_CMD_MAX = (__ETHTOOL_CMD_MAX - 1),
>+};
>+
>+/* generic netlink info */
>+#define ETHTOOL_GENL_NAME "ethtool"
>+#define ETHTOOL_GENL_VERSION 1
>+
>+#endif /* _UAPI_LINUX_ETHTOOL_NETLINK_H_ */
>diff --git a/net/Kconfig b/net/Kconfig
>index 9dba2715919d..a5e3c89a2495 100644
>--- a/net/Kconfig
>+++ b/net/Kconfig
>@@ -440,6 +440,13 @@ config MAY_USE_DEVLINK
> on MAY_USE_DEVLINK to ensure they do not cause link errors when
> devlink is a loadable module and the driver using it is built-in.
>
>+config ETHTOOL_NETLINK
>+ tristate "Netlink interface for ethtool"
>+ default m
>+ help
>+ New netlink based interface for ethtool which is going to obsolete
>+ the old ioctl based one once it provides all features.
>+
> endif # if NET
>
> # Used by archs to tell that they support BPF JIT compiler plus which flavour.
>diff --git a/net/core/Makefile b/net/core/Makefile
>index 1fd0a9c88b1b..617ab2abecdf 100644
>--- a/net/core/Makefile
>+++ b/net/core/Makefile
>@@ -30,3 +30,4 @@ obj-$(CONFIG_DST_CACHE) += dst_cache.o
> obj-$(CONFIG_HWBM) += hwbm.o
> obj-$(CONFIG_NET_DEVLINK) += devlink.o
> obj-$(CONFIG_GRO_CELLS) += gro_cells.o
>+obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_netlink.o
>diff --git a/net/core/ethtool_netlink.c b/net/core/ethtool_netlink.c
>new file mode 100644
>index 000000000000..46a226bb9a2c
>--- /dev/null
>+++ b/net/core/ethtool_netlink.c
>@@ -0,0 +1,46 @@
>+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
>+
>+#include <linux/module.h>
>+#include <linux/ethtool_netlink.h>
>+#include <linux/netdevice.h>
>+#include <net/genetlink.h>
>+#include "ethtool_common.h"
>+
>+static struct genl_family ethtool_genl_family;
>+
>+/* genetlink paperwork */
What "paperwork"? :)
>+
>+static const struct genl_ops ethtool_genl_ops[] = {
>+};
>+
>+static struct genl_family ethtool_genl_family = {
>+ .hdrsize = ETHNL_HDRLEN,
>+ .name = ETHTOOL_GENL_NAME,
>+ .version = ETHTOOL_GENL_VERSION,
>+ .netnsok = true,
>+ .ops = ethtool_genl_ops,
>+ .n_ops = ARRAY_SIZE(ethtool_genl_ops),
>+};
>+
>+/* module paperwork */
>+
>+static int __init ethtool_nl_init(void)
>+{
>+ return genl_register_family(ðtool_genl_family);
>+}
>+
>+static void __exit ethtool_nl_exit(void)
>+{
>+ genl_unregister_family(ðtool_genl_family);
>+}
>+
>+module_init(ethtool_nl_init);
>+module_exit(ethtool_nl_exit);
>+
>+/* this alias is for autoload */
>+MODULE_ALIAS("net-pf-" __stringify(PF_NETLINK)
>+ "-proto-" __stringify(NETLINK_GENERIC)
>+ "-family-" ETHTOOL_GENL_NAME);
You can use MODULE_ALIAS_GENL_FAMILY instead.
>+MODULE_AUTHOR("Michal Kubecek <mkubecek@suse.cz>");
>+MODULE_DESCRIPTION("Netlink interface for ethtool");
>+MODULE_LICENSE("GPL");
"GPL v2"?
>--
>2.15.1
>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox