* [PATCH bpf-next 0/4] bpf: per program stats
From: Alexei Starovoitov @ 2019-02-22 23:36 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, bpf, kernel-team
Introduce per program stats to monitor the usage BPF
Alexei Starovoitov (4):
bpf: enable program stats
bpf: expose program stats via bpf_prog_info
tools/bpf: sync bpf.h into tools
tools/bpftool: recognize bpf_prog_info runtime and runcnt
include/linux/bpf.h | 7 ++++
include/linux/filter.h | 16 ++++++++-
include/uapi/linux/bpf.h | 2 ++
kernel/bpf/core.c | 13 +++++++
kernel/bpf/syscall.c | 29 ++++++++++++++--
kernel/bpf/verifier.c | 5 +++
kernel/sysctl.c | 34 +++++++++++++++++++
.../bpftool/Documentation/bpftool-prog.rst | 4 ++-
tools/bpf/bpftool/prog.c | 7 ++++
tools/include/uapi/linux/bpf.h | 2 ++
10 files changed, 115 insertions(+), 4 deletions(-)
--
2.20.0
^ permalink raw reply
* [PATCH bpf-next 2/4] bpf: expose program stats via bpf_prog_info
From: Alexei Starovoitov @ 2019-02-22 23:36 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, bpf, kernel-team
In-Reply-To: <20190222233644.1487087-1-ast@kernel.org>
Return bpf program runtime and runcnt via bpf_prog_info
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/uapi/linux/bpf.h | 2 ++
kernel/bpf/syscall.c | 5 +++++
2 files changed, 7 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index bcdd2474eee7..d2cb85d85b39 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2813,6 +2813,8 @@ struct bpf_prog_info {
__u32 jited_line_info_rec_size;
__u32 nr_prog_tags;
__aligned_u64 prog_tags;
+ __u64 runtime;
+ __u64 runcnt;
} __attribute__((aligned(8)));
struct bpf_map_info {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 079e7fa14f39..6c55aeb2e1b7 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2142,6 +2142,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
struct bpf_prog_info info = {};
u32 info_len = attr->info.info_len;
+ struct bpf_prog_stats stats;
char __user *uinsns;
u32 ulen;
int err;
@@ -2181,6 +2182,10 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
if (err)
return err;
+ bpf_prog_get_stats(prog, &stats);
+ info.runtime = stats.nsecs;
+ info.runcnt = stats.cnt;
+
if (!capable(CAP_SYS_ADMIN)) {
info.jited_prog_len = 0;
info.xlated_prog_len = 0;
--
2.20.0
^ permalink raw reply related
* [PATCH bpf-next 3/4] tools/bpf: sync bpf.h into tools
From: Alexei Starovoitov @ 2019-02-22 23:36 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, bpf, kernel-team
In-Reply-To: <20190222233644.1487087-1-ast@kernel.org>
sync bpf.h into tools directory
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/include/uapi/linux/bpf.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bcdd2474eee7..d2cb85d85b39 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2813,6 +2813,8 @@ struct bpf_prog_info {
__u32 jited_line_info_rec_size;
__u32 nr_prog_tags;
__aligned_u64 prog_tags;
+ __u64 runtime;
+ __u64 runcnt;
} __attribute__((aligned(8)));
struct bpf_map_info {
--
2.20.0
^ permalink raw reply related
* [PATCH bpf-next 1/4] bpf: enable program stats
From: Alexei Starovoitov @ 2019-02-22 23:36 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, bpf, kernel-team
In-Reply-To: <20190222233644.1487087-1-ast@kernel.org>
JITed BPF programs are indistinguishable from kernel functions, but unlike
kernel code BPF code can be changed often.
Typical approach of "perf record" + "perf report" profiling and tunning of
kernel code works just as well for BPF programs, but kernel code doesn't
need to be monitored whereas BPF programs do.
Users load and run large amount of BPF programs.
These BPF stats allow tools monitor the usage of BPF on the server.
The monitoring tools will turn sysctl kernel.bpf_stats_enabled
on and off for few seconds to sample average cost of the programs.
Aggregated data over hours and days will provide an insight into cost of BPF
and alarms can trigger in case given program suddenly gets more expensive.
The cost of two sched_clock() per program invocation adds ~20 nsec.
Fast BPF progs (like selftests/bpf/progs/test_pkt_access.c) will slow down
from ~40 nsec to ~60 nsec.
static_key minimizes the cost of the stats collection.
There is no measurable difference before/after this patch
with kernel.bpf_stats_enabled=0
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf.h | 7 +++++++
include/linux/filter.h | 16 +++++++++++++++-
kernel/bpf/core.c | 13 +++++++++++++
kernel/bpf/syscall.c | 24 ++++++++++++++++++++++--
kernel/bpf/verifier.c | 5 +++++
kernel/sysctl.c | 34 ++++++++++++++++++++++++++++++++++
6 files changed, 96 insertions(+), 3 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index de18227b3d95..14260674bc57 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -340,6 +340,11 @@ enum bpf_cgroup_storage_type {
#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
+struct bpf_prog_stats {
+ u64 cnt;
+ u64 nsecs;
+};
+
struct bpf_prog_aux {
atomic_t refcnt;
u32 used_map_cnt;
@@ -389,6 +394,7 @@ struct bpf_prog_aux {
* main prog always has linfo_idx == 0
*/
u32 linfo_idx;
+ struct bpf_prog_stats __percpu *stats;
union {
struct work_struct work;
struct rcu_head rcu;
@@ -559,6 +565,7 @@ void bpf_map_area_free(void *base);
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
extern int sysctl_unprivileged_bpf_disabled;
+extern int sysctl_bpf_stats_enabled;
int bpf_map_new_fd(struct bpf_map *map, int flags);
int bpf_prog_new_fd(struct bpf_prog *prog);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f32b3eca5a04..7b14235b6f7d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -533,7 +533,21 @@ struct sk_filter {
struct bpf_prog *prog;
};
-#define BPF_PROG_RUN(filter, ctx) ({ cant_sleep(); (*(filter)->bpf_func)(ctx, (filter)->insnsi); })
+DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
+
+#define BPF_PROG_RUN(prog, ctx) ({ \
+ u32 ret; \
+ cant_sleep(); \
+ if (static_branch_unlikely(&bpf_stats_enabled_key)) { \
+ u64 start = sched_clock(); \
+ ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi); \
+ this_cpu_inc(prog->aux->stats->cnt); \
+ this_cpu_add(prog->aux->stats->nsecs, \
+ sched_clock() - start); \
+ } else { \
+ ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi); \
+ } \
+ ret; })
#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ef88b167959d..574747f98d44 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -95,6 +95,13 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
return NULL;
}
+ aux->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags);
+ if (!aux->stats) {
+ kfree(aux);
+ vfree(fp);
+ return NULL;
+ }
+
fp->pages = size / PAGE_SIZE;
fp->aux = aux;
fp->aux->prog = fp;
@@ -231,6 +238,8 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
void __bpf_prog_free(struct bpf_prog *fp)
{
+ if (fp->aux && !fp->is_func)
+ free_percpu(fp->aux->stats);
kfree(fp->aux);
vfree(fp);
}
@@ -2069,6 +2078,10 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
return -EFAULT;
}
+DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
+EXPORT_SYMBOL(bpf_stats_enabled_key);
+int sysctl_bpf_stats_enabled __read_mostly;
+
/* All definitions of tracepoints related to BPF. */
#define CREATE_TRACE_POINTS
#include <linux/bpf_trace.h>
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ec7c552af76b..079e7fa14f39 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1283,24 +1283,44 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
return 0;
}
+static void bpf_prog_get_stats(const struct bpf_prog *prog,
+ struct bpf_prog_stats *stats)
+{
+ u64 nsecs = 0, cnt = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ nsecs += per_cpu(prog->aux->stats->nsecs, cpu);
+ cnt += per_cpu(prog->aux->stats->cnt, cpu);
+ }
+ stats->nsecs = nsecs;
+ stats->cnt = cnt;
+}
+
#ifdef CONFIG_PROC_FS
static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_prog *prog = filp->private_data;
char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
+ struct bpf_prog_stats stats;
+ bpf_prog_get_stats(prog, &stats);
bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
seq_printf(m,
"prog_type:\t%u\n"
"prog_jited:\t%u\n"
"prog_tag:\t%s\n"
"memlock:\t%llu\n"
- "prog_id:\t%u\n",
+ "prog_id:\t%u\n"
+ "runtime:\t%llu\n"
+ "runcnt:\t%llu\n",
prog->type,
prog->jited,
prog_tag,
prog->pages * 1ULL << PAGE_SHIFT,
- prog->aux->id);
+ prog->aux->id,
+ stats.nsecs,
+ stats.cnt);
}
#endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1b9496c41383..dff61920a316 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7330,6 +7330,11 @@ static int jit_subprogs(struct bpf_verifier_env *env)
if (bpf_prog_calc_tag(func[i]))
goto out_free;
func[i]->is_func = 1;
+ /* BPF_PROG_RUN doesn't call subprogs directly,
+ * hence stats are reused from main prog
+ */
+ free_percpu(func[i]->aux->stats);
+ func[i]->aux->stats = prog->aux->stats;
func[i]->aux->func_idx = i;
/* the btf and func_info will be freed only at prog->aux */
func[i]->aux->btf = prog->aux->btf;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ba4d9e85feb8..86e0771352f2 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -224,6 +224,9 @@ static int proc_dostring_coredump(struct ctl_table *table, int write,
#endif
static int proc_dopipe_max_size(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
+static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
#ifdef CONFIG_MAGIC_SYSRQ
/* Note: sysrq code uses its own private copy */
@@ -1230,6 +1233,15 @@ static struct ctl_table kern_table[] = {
.extra2 = &one,
},
#endif
+ {
+ .procname = "bpf_stats_enabled",
+ .data = &sysctl_bpf_stats_enabled,
+ .maxlen = sizeof(sysctl_bpf_stats_enabled),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax_bpf_stats,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
{
.procname = "panic_on_rcu_stall",
@@ -3260,6 +3272,28 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
#endif /* CONFIG_PROC_SYSCTL */
+static int proc_dointvec_minmax_bpf_stats(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret, bpf_stats = *(int *)table->data;
+ struct ctl_table tmp = *table;
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ tmp.data = &bpf_stats;
+ ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ if (write && !ret) {
+ *(int *)table->data = bpf_stats;
+ if (bpf_stats)
+ static_branch_enable(&bpf_stats_enabled_key);
+ else
+ static_branch_disable(&bpf_stats_enabled_key);
+ }
+ return ret;
+}
+
/*
* No sense putting this after each symbol definition, twice,
* exception granted :-)
--
2.20.0
^ permalink raw reply related
* [PATCH bpf-next 4/4] tools/bpftool: recognize bpf_prog_info runtime and runcnt
From: Alexei Starovoitov @ 2019-02-22 23:36 UTC (permalink / raw)
To: davem; +Cc: daniel, netdev, bpf, kernel-team
In-Reply-To: <20190222233644.1487087-1-ast@kernel.org>
$ bpftool p s
1: kprobe tag a56587d488d216c9 gpl runtime 79786 runcnt 8
loaded_at 2019-02-22T12:22:51-0800 uid 0
xlated 352B not jited memlock 4096B
$ bpftool --json --pretty p s
[{
"id": 1,
"type": "kprobe",
"tag": "a56587d488d216c9",
"gpl_compatible": true,
"runtime": 79786,
"runcnt": 8,
"loaded_at": 1550866971,
"uid": 0,
"bytes_xlated": 352,
"jited": false,
"bytes_memlock": 4096
}
]
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/bpf/bpftool/Documentation/bpftool-prog.rst | 4 +++-
tools/bpf/bpftool/prog.c | 7 +++++++
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 12bc1e2d4b46..102b180d3add 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -171,7 +171,7 @@ EXAMPLES
::
- 10: xdp name some_prog tag 005a3d2123620c8b gpl
+ 10: xdp name some_prog tag 005a3d2123620c8b gpl runtime 81632 runcnt 10
loaded_at 2017-09-29T20:11:00+0000 uid 0
xlated 528B jited 370B memlock 4096B map_ids 10
@@ -184,6 +184,8 @@ EXAMPLES
"type": "xdp",
"tag": "005a3d2123620c8b",
"gpl_compatible": true,
+ "runtime": 81632,
+ "runcnt": 10,
"loaded_at": 1506715860,
"uid": 0,
"bytes_xlated": 528,
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index db978c8d76a8..8065ba11b9d5 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -214,6 +214,10 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible);
+ if (info->runtime) {
+ jsonw_uint_field(json_wtr, "runtime", info->runtime);
+ jsonw_uint_field(json_wtr, "runcnt", info->runcnt);
+ }
print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
@@ -277,6 +281,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino);
printf("%s", info->gpl_compatible ? " gpl" : "");
+ if (info->runtime)
+ printf(" runtime %lld runcnt %lld",
+ info->runtime, info->runcnt);
printf("\n");
if (info->load_time) {
--
2.20.0
^ permalink raw reply related
* Re: [PATCH net-next v3 4/4] dt-bindings: net: freescale: enetc: Add connection bindings for ENETC ethernet nodes
From: Rob Herring @ 2019-02-22 23:37 UTC (permalink / raw)
To: Claudiu Manoil
Cc: Shawn Guo, Li Yang, David S . Miller, alexandru.marginean,
linux-arm-kernel, devicetree, netdev, linux-kernel
In-Reply-To: <1550847859-17346-5-git-send-email-claudiu.manoil@nxp.com>
On Fri, Feb 22, 2019 at 05:04:19PM +0200, Claudiu Manoil wrote:
> Define connection bindings (external PHY connections and internal links)
> for the ENETC on-chip ethernet controllers.
>
> Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
> ---
> v3 - added this patch to the set
>
> .../devicetree/bindings/net/fsl-enetc.txt | 109 +++++++++++++++++++++
> 1 file changed, 109 insertions(+)
> create mode 100644 Documentation/devicetree/bindings/net/fsl-enetc.txt
>
> diff --git a/Documentation/devicetree/bindings/net/fsl-enetc.txt b/Documentation/devicetree/bindings/net/fsl-enetc.txt
> new file mode 100644
> index 0000000..2fbb998
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/net/fsl-enetc.txt
> @@ -0,0 +1,109 @@
> +* ENETC ethernet nodes - external connection bindings
> +
> +The ENETC ethernet controllers are PCIe integrated endpoints
> +(IEPs), on-chip devices discoverable as standard PCIe endpoints,
> +integrated into Freescale SoCs. The ENETC devices are self
> +contained, the information needed for device initialization
> +is available in hardware (PCIe ECAM area). However, depending
> +on board design, their external connections are configurable.
> +As usual for SoCs, device tree nodes may be used to define these
> +external connections. The rest of the document specifies how
> +external connections for ENETC ethernet controllers may be
> +defined via device tree nodes.
> +
> +Silicon (SoC) availability (<SoC name>: <SoC DT path/name>)
> + - LS1028A: [arch/arm64] [...]freescale/fsl-ls1028a.dtsi
This doesn't belong in bindings.
> +
> +
> +* ENETC nodes
> +
> +Defined in the SoC device tree as "pci" child nodes of the
> +"pci-host-ecam-generic" compatible "pcie" parent node also known
> +as the Integrated Endpoint Root Complex (IERC) SoC node.
The host controller attachment is also outside the scope of this
binding.
> +
> +Structure - example (LS1028A):
> +
> + pcie@1f0000000 {
> + compatible = "pci-host-ecam-generic";
> + device_type = "pci";
> + ...
> + enetc_port0: pci@0,0 {
The node name 'pci' is reserved for bridges. This should match the
device class if possible (ethernet).
> + reg = <0x000000 0 0 0 0>;
> + };
> + enetc_port1: pci@0,1 {
> + reg = <0x000100 0 0 0 0>;
> + };
> + ...
> + }
> +
> +Each ENETC node has a device number and a function number (expressed
> +by its "reg" property and pci node name, i.e. "pci@0,1" represents
> +device number 0 and functions number 1). Only the standard pci "reg"
> +property is needed here.
There should be a compatible too.
> +For easy reference, each ENETC node is tagged by a handle having the
> +following format:
> +
> + "enetc_port<idx>" where, idx = 0 .. n-1;
> + n - #of available ENETC nodes (Ports) on
> + the given SoC.
These are just source labels, so really they can be anything.
> +
> +NOTES
> +i. The SoC H/W Reference Manual provides a mapping of the ENETC Port
> +numbers to the PCIe Device Number/ Function Number.
> +Example (LS1028):
> + All ENETC PFs (PCIe Physical Functions) have Device Number 0.
> + Port 0 - PF0 (pci@0,0)
> + Port 1 - PF1 (pci@0,1)
> + Port 2 - PF2 (pci@0,2)
> + Port 3 - PF6 (pci@0,6)
> +
> +ii. The SoC H/W Reference Manual also defines which ENETC Ports may have
> +external connections (external ports) and which ones are internally
> +connected to a on-chip L2 switch for instance (internal ports).
> +
> +
> +* Defining connections for ENETC nodes
> +
> +To define external connections for the external ENETC Ports on a given
> +board/platform, the board device tree should include the SoC device tree
> +and reference the external ports by their "enetc_port<idx>" handle.
SoC vs. board files are convention, but not really part of the binding
ABI.
> +
> +Following cases arise, defining all possible connection bindings:
> +
> +1) The ENETC Port is connected to a MDIO configurable PHY:
> +
> + In this case, the ENETC node should include a "mdio" sub-node
> + that in turn should contain the "phy" node describing the
> + external phy. ENETC Port node structure (example):
> +
> + &enetc_port0 {
Please just show the full DT example, not separate chunks.
> + phy-handle = <&sgmii_phy0>;
> + phy-connection-type = "sgmii";
> +
> + mdio {
> + #address-cells = <1>;
> + #size-cells = <0>;
> + sgmii_phy0: ethernet-phy@2 {
> + reg = <0x2>;
> + };
> + };
> + };
> +
> + All properties are mandatory for this case, their bindings already
> + defined (see ethernet.txt and phy.txt).
> +
> +2) The ENETC Port has a fixed-link connection:
> +
> + In this case, the ENETC Port node defines a fixed link connection,
> + with the following structure (example):
> +
> + &enetc_port2 {
> + fixed-link {
> + speed = <1000>;
> + full-duplex;
> + };
> + };
> +
> + The "fixed-link" node properties are standard (as defined in
> + fixed-link.txt).
> + This connection type also applies to the internal ENETC Ports.
> --
> 2.7.4
>
^ permalink raw reply
* [PATCH net-next v2 0/7] net: phy: marvell10g: Add 2.5GBaseT support
From: Maxime Chevallier @ 2019-02-22 23:37 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Andrew Lunn,
Florian Fainelli, Heiner Kallweit, Russell King, linux-arm-kernel,
Antoine Tenart, thomas.petazzoni, gregory.clement, miquel.raynal,
nadavh, stefanc, mw
This series adds the missing bits necessary to fully support 2.5GBaseT
in the Marvell Alaska PHYs.
The main points for that support are :
- Making use of the .get_features call, recently introduced by Heiner
and Andrew, that allows having a fully populated list of supported
modes, including 2500BaseT.
- Configuring the MII to 2500BaseX when establishing a link at 2.5G
- Adding a small quirk to take into account the fact that some PHYs in
the family won't report the correct supported abilities
The rest of the series consists of small cosmetic improvements such as
using the correct helper to set a linkmode bit and adding macros for the
PHY ids.
We also add support for the 88E2110 PHY, which doesn't require the
quirk, and support for 2500BaseT in the PPv2 driver, in order to have a
fully working setup on the MacchiatoBin board.
Changes since V1 : Fixed formatting issue in patch 01, rebased.
Maxime Chevallier (7):
net: phy: marvell10g: Use get_features to get the PHY abilities
net: phy: marvell10g: Use linkmode_set_bit helper instead of __set_bit
net: phy: marvell10g: Use 2500BASEX when using 2.5GBASET
net: phy: marvell10g: Use a #define for 88X3310 family id
net: phy: marvell10g: Force reading of 2.5/5G
net: mvpp2: Add 2.5GBaseT support
net: phy: marvell10g: add support for the 88x2110 PHY
.../net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 +
drivers/net/phy/marvell10g.c | 93 ++++++++++++++++---
include/linux/marvell_phy.h | 2 +
3 files changed, 82 insertions(+), 14 deletions(-)
--
2.19.2
^ permalink raw reply
* [PATCH net-next v2 1/7] net: phy: marvell10g: Use get_features to get the PHY abilities
From: Maxime Chevallier @ 2019-02-22 23:37 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Andrew Lunn,
Florian Fainelli, Heiner Kallweit, Russell King, linux-arm-kernel,
Antoine Tenart, thomas.petazzoni, gregory.clement, miquel.raynal,
nadavh, stefanc, mw
In-Reply-To: <20190222233744.25735-1-maxime.chevallier@bootlin.com>
The Alaska family of 10G PHYs has more abilities than the ones listed in
PHY_10GBIT_FULL_FEATURES, the exact list depending on the model.
Make use of the newly introduced .get_features call to build this list,
using genphy_c45_pma_read_abilities to build the list of supported
linkmodes, and adding autoneg ability based on what's reported by the AN
MMD.
.config_init is still used to validate the interface_mode.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
V2: Added missing blank line
drivers/net/phy/marvell10g.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 586ae1bc5a50..89920b10d75b 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -233,8 +233,6 @@ static int mv3310_resume(struct phy_device *phydev)
static int mv3310_config_init(struct phy_device *phydev)
{
- int ret, val;
-
/* Check that the PHY interface type is compatible */
if (phydev->interface != PHY_INTERFACE_MODE_SGMII &&
phydev->interface != PHY_INTERFACE_MODE_XAUI &&
@@ -242,6 +240,13 @@ static int mv3310_config_init(struct phy_device *phydev)
phydev->interface != PHY_INTERFACE_MODE_10GKR)
return -ENODEV;
+ return 0;
+}
+
+static int mv3310_get_features(struct phy_device *phydev)
+{
+ int ret, val;
+
if (phydev->c45_ids.devices_in_package & MDIO_DEVS_AN) {
val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
if (val < 0)
@@ -416,7 +421,7 @@ static struct phy_driver mv3310_drivers[] = {
.phy_id = 0x002b09aa,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "mv88x3310",
- .features = PHY_10GBIT_FEATURES,
+ .get_features = mv3310_get_features,
.soft_reset = gen10g_no_soft_reset,
.config_init = mv3310_config_init,
.probe = mv3310_probe,
--
2.19.2
^ permalink raw reply related
* [PATCH net-next v2 2/7] net: phy: marvell10g: Use linkmode_set_bit helper instead of __set_bit
From: Maxime Chevallier @ 2019-02-22 23:37 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Andrew Lunn,
Florian Fainelli, Heiner Kallweit, Russell King, linux-arm-kernel,
Antoine Tenart, thomas.petazzoni, gregory.clement, miquel.raynal,
nadavh, stefanc, mw
In-Reply-To: <20190222233744.25735-1-maxime.chevallier@bootlin.com>
Cosmetic patch making use of helpers dedicated to linkmodes handling.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/phy/marvell10g.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 89920b10d75b..821ef1b2f8cc 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -253,8 +253,8 @@ static int mv3310_get_features(struct phy_device *phydev)
return val;
if (val & MDIO_AN_STAT1_ABLE)
- __set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
- phydev->supported);
+ linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+ phydev->supported);
}
ret = genphy_c45_pma_read_abilities(phydev);
--
2.19.2
^ permalink raw reply related
* [PATCH net-next v2 3/7] net: phy: marvell10g: Use 2500BASEX when using 2.5GBASET
From: Maxime Chevallier @ 2019-02-22 23:37 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Andrew Lunn,
Florian Fainelli, Heiner Kallweit, Russell King, linux-arm-kernel,
Antoine Tenart, thomas.petazzoni, gregory.clement, miquel.raynal,
nadavh, stefanc, mw
In-Reply-To: <20190222233744.25735-1-maxime.chevallier@bootlin.com>
The Marvell Alaska family of PHYs supports 2.5GBaseT and 5GBaseT modes,
as defined in the 802.3bz specification.
Upon establishing a 2.5GBASET link, the PHY will reconfigure it's MII
interface to 2500BASEX.
At 5G, the PHY will reconfigure it's interface to 5GBASE-R, but this
mode isn't supported by any MAC for now.
This was tested with :
- The 88X3310, which is on the MacchiatoBin
- The 88E2010, an Alaska PHY that has no fiber interfaces, and is
limited to 5G maximum speed.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/phy/marvell10g.c | 26 +++++++++++++++++++-------
1 file changed, 19 insertions(+), 7 deletions(-)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 821ef1b2f8cc..9342d8c2ff7f 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -235,6 +235,7 @@ static int mv3310_config_init(struct phy_device *phydev)
{
/* Check that the PHY interface type is compatible */
if (phydev->interface != PHY_INTERFACE_MODE_SGMII &&
+ phydev->interface != PHY_INTERFACE_MODE_2500BASEX &&
phydev->interface != PHY_INTERFACE_MODE_XAUI &&
phydev->interface != PHY_INTERFACE_MODE_RXAUI &&
phydev->interface != PHY_INTERFACE_MODE_10GKR)
@@ -313,18 +314,29 @@ static int mv3310_aneg_done(struct phy_device *phydev)
static void mv3310_update_interface(struct phy_device *phydev)
{
if ((phydev->interface == PHY_INTERFACE_MODE_SGMII ||
+ phydev->interface == PHY_INTERFACE_MODE_2500BASEX ||
phydev->interface == PHY_INTERFACE_MODE_10GKR) && phydev->link) {
/* The PHY automatically switches its serdes interface (and
- * active PHYXS instance) between Cisco SGMII and 10GBase-KR
- * modes according to the speed. Florian suggests setting
- * phydev->interface to communicate this to the MAC. Only do
- * this if we are already in either SGMII or 10GBase-KR mode.
+ * active PHYXS instance) between Cisco SGMII, 10GBase-KR and
+ * 2500BaseX modes according to the speed. Florian suggests
+ * setting phydev->interface to communicate this to the MAC.
+ * Only do this if we are already in one of the above modes.
*/
- if (phydev->speed == SPEED_10000)
+ switch (phydev->speed) {
+ case SPEED_10000:
phydev->interface = PHY_INTERFACE_MODE_10GKR;
- else if (phydev->speed >= SPEED_10 &&
- phydev->speed < SPEED_10000)
+ break;
+ case SPEED_2500:
+ phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
+ break;
+ case SPEED_1000:
+ case SPEED_100:
+ case SPEED_10:
phydev->interface = PHY_INTERFACE_MODE_SGMII;
+ break;
+ default:
+ break;
+ }
}
}
--
2.19.2
^ permalink raw reply related
* [PATCH net-next v2 4/7] net: phy: marvell10g: Use a #define for 88X3310 family id
From: Maxime Chevallier @ 2019-02-22 23:37 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Andrew Lunn,
Florian Fainelli, Heiner Kallweit, Russell King, linux-arm-kernel,
Antoine Tenart, thomas.petazzoni, gregory.clement, miquel.raynal,
nadavh, stefanc, mw
In-Reply-To: <20190222233744.25735-1-maxime.chevallier@bootlin.com>
The PHY ID corresponding to the 88X3310 is also used for other PHYs in
the same family, such as the 88E2010. Use a #define for the PHY id, that
ignores the last nibble.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/phy/marvell10g.c | 4 ++--
include/linux/marvell_phy.h | 1 +
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 9342d8c2ff7f..9c0b8f16cec5 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -430,7 +430,7 @@ static int mv3310_read_status(struct phy_device *phydev)
static struct phy_driver mv3310_drivers[] = {
{
- .phy_id = 0x002b09aa,
+ .phy_id = MARVELL_PHY_ID_88X3310,
.phy_id_mask = MARVELL_PHY_ID_MASK,
.name = "mv88x3310",
.get_features = mv3310_get_features,
@@ -448,7 +448,7 @@ static struct phy_driver mv3310_drivers[] = {
module_phy_driver(mv3310_drivers);
static struct mdio_device_id __maybe_unused mv3310_tbl[] = {
- { 0x002b09aa, MARVELL_PHY_ID_MASK },
+ { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK },
{ },
};
MODULE_DEVICE_TABLE(mdio, mv3310_tbl);
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 1eb6f244588d..70c17345e118 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -20,6 +20,7 @@
#define MARVELL_PHY_ID_88E1540 0x01410eb0
#define MARVELL_PHY_ID_88E1545 0x01410ea0
#define MARVELL_PHY_ID_88E3016 0x01410e60
+#define MARVELL_PHY_ID_88X3310 0x002b09a0
/* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do
* not have a model ID. So the switch driver traps reads to the ID2
--
2.19.2
^ permalink raw reply related
* [PATCH net-next v2 5/7] net: phy: marvell10g: Force reading of 2.5/5G
From: Maxime Chevallier @ 2019-02-22 23:37 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Andrew Lunn,
Florian Fainelli, Heiner Kallweit, Russell King, linux-arm-kernel,
Antoine Tenart, thomas.petazzoni, gregory.clement, miquel.raynal,
nadavh, stefanc, mw
In-Reply-To: <20190222233744.25735-1-maxime.chevallier@bootlin.com>
As per 802.3bz, if bit 14 of (1.11) "PMA Extended Abilities" indicates
whether or not we should read register (1.21) "2.52/5G PMA Extended
Abilities", which contains information on the support of 2.5GBASET and
5GBASET.
After testing on several variants of PHYS of this family, it appears
that bit 14 in (1.11) isn't always set when it should be.
PHYs 88X3310 (on MacchiatoBin) and 88E2010 do support 2.5G and 5GBASET,
but don't have 1.11.14 set. Their register 1.21 is filled with the
correct values, indicating 2.5G and 5G support.
PHYs 88E2110 do have their 1.11.14 bit set, as it should.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/phy/marvell10g.c | 35 +++++++++++++++++++++++++++++++++++
1 file changed, 35 insertions(+)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 9c0b8f16cec5..8f354c3f3876 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -27,6 +27,9 @@
#include <linux/marvell_phy.h>
#include <linux/phy.h>
+#define MV_PHY_ALASKA_NBT_QUIRK_MASK 0xfffffffe
+#define MV_PHY_ALASKA_NBT_QUIRK_REV (MARVELL_PHY_ID_88X3310 | 0xa)
+
enum {
MV_PCS_BASE_T = 0x0000,
MV_PCS_BASE_R = 0x1000,
@@ -231,6 +234,23 @@ static int mv3310_resume(struct phy_device *phydev)
return mv3310_hwmon_config(phydev, true);
}
+/* Some PHYs in the Alaska family such as the 88X3310 and the 88E2010
+ * don't set bit 14 in PMA Extended Abilities (1.11), although they do
+ * support 2.5GBASET and 5GBASET. For these models, we can still read their
+ * 2.5G/5G extended abilities register (1.21). We detect these models based on
+ * the PMA device identifier, with a mask matching models known to have this
+ * issue
+ */
+static bool mv3310_has_pma_ngbaset_quirk(struct phy_device *phydev)
+{
+ if (!(phydev->c45_ids.devices_in_package & MDIO_DEVS_PMAPMD))
+ return false;
+
+ /* Only some revisions of the 88X3310 family PMA seem to be impacted */
+ return (phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] &
+ MV_PHY_ALASKA_NBT_QUIRK_MASK) == MV_PHY_ALASKA_NBT_QUIRK_REV;
+}
+
static int mv3310_config_init(struct phy_device *phydev)
{
/* Check that the PHY interface type is compatible */
@@ -262,6 +282,21 @@ static int mv3310_get_features(struct phy_device *phydev)
if (ret)
return ret;
+ if (mv3310_has_pma_ngbaset_quirk(phydev)) {
+ val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD,
+ MDIO_PMA_NG_EXTABLE);
+ if (val < 0)
+ return val;
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+ phydev->supported,
+ val & MDIO_PMA_NG_EXTABLE_2_5GBT);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+ phydev->supported,
+ val & MDIO_PMA_NG_EXTABLE_5GBT);
+ }
+
return 0;
}
--
2.19.2
^ permalink raw reply related
* [PATCH net-next v2 6/7] net: mvpp2: Add 2.5GBaseT support
From: Maxime Chevallier @ 2019-02-22 23:37 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Andrew Lunn,
Florian Fainelli, Heiner Kallweit, Russell King, linux-arm-kernel,
Antoine Tenart, thomas.petazzoni, gregory.clement, miquel.raynal,
nadavh, stefanc, mw
In-Reply-To: <20190222233744.25735-1-maxime.chevallier@bootlin.com>
The PPv2 controller is able to support 2.5G speeds, allowing to use
2.5GBASET in conjunction with PHYs that use 2500BASEX as their MII
interface when using this mode.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
---
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 191d9ce85b7e..6638a3339efc 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -4403,6 +4403,7 @@ static void mvpp2_phylink_validate(struct net_device *dev,
case PHY_INTERFACE_MODE_2500BASEX:
phylink_set(mask, 1000baseT_Full);
phylink_set(mask, 1000baseX_Full);
+ phylink_set(mask, 2500baseT_Full);
phylink_set(mask, 2500baseX_Full);
break;
default:
--
2.19.2
^ permalink raw reply related
* [PATCH net-next v2 7/7] net: phy: marvell10g: add support for the 88x2110 PHY
From: Maxime Chevallier @ 2019-02-22 23:37 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Andrew Lunn,
Florian Fainelli, Heiner Kallweit, Russell King, linux-arm-kernel,
Antoine Tenart, thomas.petazzoni, gregory.clement, miquel.raynal,
nadavh, stefanc, mw
In-Reply-To: <20190222233744.25735-1-maxime.chevallier@bootlin.com>
This patch adds support for the 88x2110 PHY, which is similar to the
already supported 88x3310 PHY without the SFP interface.
It supports 10/100/1000BASET along with 2.5GBASET, 5GBASET and 10GBASET,
with the same interface modes that are used by the 3310.
This PHY don't have the same issue as the 88x3310 regarding 2.5/5G
abilities, and correctly follows the 802.3bz standard to list the
supported abilities.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Suggested-by: Antoine Tenart <antoine.tenart@bootlin.com>
---
drivers/net/phy/marvell10g.c | 13 +++++++++++++
include/linux/marvell_phy.h | 1 +
2 files changed, 14 insertions(+)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 8f354c3f3876..580e91deadbc 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -478,12 +478,25 @@ static struct phy_driver mv3310_drivers[] = {
.aneg_done = mv3310_aneg_done,
.read_status = mv3310_read_status,
},
+ {
+ .phy_id = MARVELL_PHY_ID_88E2110,
+ .phy_id_mask = MARVELL_PHY_ID_MASK,
+ .name = "mv88x2110",
+ .features = PHY_10GBIT_FEATURES,
+ .probe = mv3310_probe,
+ .soft_reset = gen10g_no_soft_reset,
+ .config_init = mv3310_config_init,
+ .config_aneg = mv3310_config_aneg,
+ .aneg_done = mv3310_aneg_done,
+ .read_status = mv3310_read_status,
+ },
};
module_phy_driver(mv3310_drivers);
static struct mdio_device_id __maybe_unused mv3310_tbl[] = {
{ MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK },
+ { MARVELL_PHY_ID_88E2110, MARVELL_PHY_ID_MASK },
{ },
};
MODULE_DEVICE_TABLE(mdio, mv3310_tbl);
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 70c17345e118..73d04743a2bb 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -21,6 +21,7 @@
#define MARVELL_PHY_ID_88E1545 0x01410ea0
#define MARVELL_PHY_ID_88E3016 0x01410e60
#define MARVELL_PHY_ID_88X3310 0x002b09a0
+#define MARVELL_PHY_ID_88E2110 0x002b09b0
/* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do
* not have a model ID. So the switch driver traps reads to the ID2
--
2.19.2
^ permalink raw reply related
* Re: [PATCH net v2] af_packet: fix raw sockets over 6in4 tunnel
From: Willem de Bruijn @ 2019-02-22 23:53 UTC (permalink / raw)
To: David Miller
Cc: Sasha Levin, Nicolas Dichtel, Network Development,
Willem de Bruijn, Maxim Mikityanskiy
In-Reply-To: <20190222.115010.2277570236847613044.davem@davemloft.net>
On Fri, Feb 22, 2019 at 2:50 PM David Miller <davem@davemloft.net> wrote:
>
> From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
> Date: Wed, 20 Feb 2019 13:39:23 -0500
>
> > On Mon, Feb 18, 2019 at 1:50 PM Sasha Levin <sashal@kernel.org> wrote:
> >> Should this go to -stable as well? The patch it fixes is in 4.20.
> >
> > I believe so. It was also backported to 4.19 stable.
>
> It's queued up now.
Thanks David!
^ permalink raw reply
* Re: [PATCH 1/2 v2] kprobe: Do not use uaccess functions to access kernel memory that can fault
From: Alexei Starovoitov @ 2019-02-22 23:56 UTC (permalink / raw)
To: Linus Torvalds
Cc: David Miller, Masami Hiramatsu, Steven Rostedt, Andy Lutomirski,
Linux List Kernel Mailing, Ingo Molnar, Andrew Morton, stable,
Changbin Du, Jann Horn, Kees Cook, Andrew Lutomirski,
Daniel Borkmann, Netdev, bpf
In-Reply-To: <CAHk-=wjJqVXydQf_dprBmr=zXsyNVrB9mBCmDL0nGmH_b0vY5g@mail.gmail.com>
On Fri, Feb 22, 2019 at 03:16:35PM -0800, Linus Torvalds wrote:
>
> So a kernel pointer value of 0x12345678 could be a value kernel
> pointer pointing to some random kmalloc'ed kernel memory, and a user
> pointer value of 0x12345678 could be a valid _user_ pointer pointing
> to some user mapping.
>
> See?
>
> If you access a user pointer, you need to use a user accessor function
> (eg "get_user()"), while if you access a kernel pointer you need to
> just dereference it directly (unless you can't trust it, in which case
> you need to use a _different_ accessor function).
that was clear already.
Reading 0x12345678 via probe_kernel_read can return valid value
and via get_user() can return another valid value on _some_ architectures.
> The fact that user and kernel pointers happen to be distinct on x86-64
> (right now) is just a random implementation detail.
yes and my point that people already rely on this implementation detail.
Say we implement
int bpf_probe_read(void *val, void *unsafe_ptr)
{
if (probe_kernel_read(val, unsafe_ptr) == OK) {
return 0;
} else (get_user(val, unsafe_ptr) == OK) {
return 0;
} else {
*val = 0;
return -EFAULT;
}
}
It will preserve existing bpf_probe_read() behavior on x86.
If x86 implementation changes tomorrow then progs that read user
addresses may start failing randomly because first probe_kernel_read()
will be returning random values from kernel memory and that's no good,
but at least we won't be breaking them today, so we have time to
introduce bpf_user_read and bpf_kernel_read and folks have time to adopt them.
Imo that's much better than making current bpf_probe_read() fail
on user addresses today and not providing a non disruptive path forward.
^ permalink raw reply
* Re: [PATCH 1/2 v2] kprobe: Do not use uaccess functions to access kernel memory that can fault
From: Andy Lutomirski @ 2019-02-22 23:59 UTC (permalink / raw)
To: Jann Horn
Cc: Nadav Amit, Alexei Starovoitov, Steven Rostedt, Linus Torvalds,
Masami Hiramatsu, Linux List Kernel Mailing, Ingo Molnar,
Andrew Morton, Changbin Du, Kees Cook, Andy Lutomirski,
Daniel Borkmann, Network Development, bpf@vger.kernel.org,
Rick Edgecombe, Dave Hansen, Peter Zijlstra (Intel), Igor Stoppa
In-Reply-To: <CAG48ez1Dm04kg2x3O=OOmBFFBSDr+RmnhBYChcwYv5zLbPGudQ@mail.gmail.com>
On Fri, Feb 22, 2019 at 3:02 PM Jann Horn <jannh@google.com> wrote:
>
> On Fri, Feb 22, 2019 at 11:39 PM Nadav Amit <namit@vmware.com> wrote:
> > > On Feb 22, 2019, at 2:21 PM, Nadav Amit <namit@vmware.com> wrote:
> > >
> > >> On Feb 22, 2019, at 2:17 PM, Jann Horn <jannh@google.com> wrote:
> > >>
> > >> On Fri, Feb 22, 2019 at 11:08 PM Nadav Amit <namit@vmware.com> wrote:
> > >>>> On Feb 22, 2019, at 1:43 PM, Jann Horn <jannh@google.com> wrote:
> > >>>>
> > >>>> (adding some people from the text_poke series to the thread, removing stable@)
> > >>>>
> > >>>> On Fri, Feb 22, 2019 at 8:55 PM Andy Lutomirski <luto@amacapital.net> wrote:
> > >>>>>> On Feb 22, 2019, at 11:34 AM, Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote:
> > >>>>>>> On Fri, Feb 22, 2019 at 02:30:26PM -0500, Steven Rostedt wrote:
> > >>>>>>> On Fri, 22 Feb 2019 11:27:05 -0800
> > >>>>>>> Alexei Starovoitov <alexei.starovoitov@gmail.com> wrote:
> > >>>>>>>
> > >>>>>>>>> On Fri, Feb 22, 2019 at 09:43:14AM -0800, Linus Torvalds wrote:
> > >>>>>>>>>
> > >>>>>>>>> Then we should still probably fix up "__probe_kernel_read()" to not
> > >>>>>>>>> allow user accesses. The easiest way to do that is actually likely to
> > >>>>>>>>> use the "unsafe_get_user()" functions *without* doing a
> > >>>>>>>>> uaccess_begin(), which will mean that modern CPU's will simply fault
> > >>>>>>>>> on a kernel access to user space.
> > >>>>>>>>
> > >>>>>>>> On bpf side the bpf_probe_read() helper just calls probe_kernel_read()
> > >>>>>>>> and users pass both user and kernel addresses into it and expect
> > >>>>>>>> that the helper will actually try to read from that address.
> > >>>>>>>>
> > >>>>>>>> If __probe_kernel_read will suddenly start failing on all user addresses
> > >>>>>>>> it will break the expectations.
> > >>>>>>>> How do we solve it in bpf_probe_read?
> > >>>>>>>> Call probe_kernel_read and if that fails call unsafe_get_user byte-by-byte
> > >>>>>>>> in the loop?
> > >>>>>>>> That's doable, but people already complain that bpf_probe_read() is slow
> > >>>>>>>> and shows up in their perf report.
> > >>>>>>>
> > >>>>>>> We're changing kprobes to add a specific flag to say that we want to
> > >>>>>>> differentiate between kernel or user reads. Can this be done with
> > >>>>>>> bpf_probe_read()? If it's showing up in perf report, I doubt a single
> > >>>>>>
> > >>>>>> so you're saying you will break existing kprobe scripts?
> > >>>>>> I don't think it's a good idea.
> > >>>>>> It's not acceptable to break bpf_probe_read uapi.
> > >>>>>
> > >>>>> If so, the uapi is wrong: a long-sized number does not reliably identify an address if you don’t separately know whether it’s a user or kernel address. s390x and 4G:4G x86_32 are the notable exceptions. I have lobbied for RISC-V and future x86_64 to join the crowd. I don’t know whether I’ll win this fight, but the uapi will probably have to change for at least s390x.
> > >>>>>
> > >>>>> What to do about existing scripts is a different question.
> > >>>>
> > >>>> This lack of logical separation between user and kernel addresses
> > >>>> might interact interestingly with the text_poke series, specifically
> > >>>> "[PATCH v3 05/20] x86/alternative: Initialize temporary mm for
> > >>>> patching" (https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Flore.kernel.org%2Flkml%2F20190221234451.17632-6-rick.p.edgecombe%40intel.com%2F&data=02%7C01%7Cnamit%40vmware.com%7Cf2513009ef734ecd6b0d08d69913a5ae%7Cb39138ca3cee4b4aa4d6cd83d9dd62f0%7C0%7C0%7C636864707020821793&sdata=HAbnDcrBne64JyPuVUMKmM7nQk67F%2BFvjuXEn8TmHeo%3D&reserved=0)
> > >>>> and "[PATCH v3 06/20] x86/alternative: Use temporary mm for text
> > >>>> poking" (https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Flore.kernel.org%2Flkml%2F20190221234451.17632-7-rick.p.edgecombe%40intel.com%2F&data=02%7C01%7Cnamit%40vmware.com%7Cf2513009ef734ecd6b0d08d69913a5ae%7Cb39138ca3cee4b4aa4d6cd83d9dd62f0%7C0%7C0%7C636864707020821793&sdata=vNRIMKtFDy%2F3z5FlTwDiJY6VGEV%2FMHgQPTdFSFtCo4s%3D&reserved=0),
> > >>>> right? If someone manages to get a tracing BPF program to trigger in a
> > >>>> task that has switched to the patching mm, could they use
> > >>>> bpf_probe_write_user() - which uses probe_kernel_write() after
> > >>>> checking that KERNEL_DS isn't active and that access_ok() passes - to
> > >>>> overwrite kernel text that is mapped writable in the patching mm?
> > >>>
> > >>> Yes, this is a good point. I guess text_poke() should be defined with
> > >>> “__kprobes” and open-code memcpy.
> > >>>
> > >>> Does it sound reasonable?
> > >>
> > >> Doesn't __text_poke() as implemented in the proposed patch use a
> > >> couple other kernel functions, too? Like switch_mm_irqs_off() and
> > >> pte_clear() (which can be a call into a separate function on paravirt
> > >> kernels)?
> > >
> > > I will move the pte_clear() to be done after the poking mm was unloaded.
> > > Give me a few minutes to send a sketch of what I think should be done.
> >
> > Err.. You are right, I don’t see an easy way of preventing a kprobe from
> > being set on switch_mm_irqs_off(), and open-coding this monster is too ugly.
> >
> > The reasonable solution seems to me as taking all the relevant pieces of
> > code (and data) that might be used during text-poking and encapsulating them, so they
> > will be set in a memory area which cannot be kprobe'd. This can also be
> > useful to write-protect data structures of code that calls text_poke(),
> > e.g., static-keys. It can also protect data on that stack that is used
> > during text_poke() from being overwritten from another core.
> >
> > This solution is somewhat similar to Igor Stoppa’s idea of using “enclaves”
> > when doing write-rarely operations.
> >
> > Right now, I think that text_poke() will keep being susceptible to such
> > an attack, unless you have a better suggestion.
>
> A relatively simple approach might be to teach BPF not to run kprobe
> programs and such in contexts where current->mm isn't the active mm?
> Maybe using nmi_uaccess_okay(), or something like that? It looks like
> perf_callchain_user() also already uses that. Except that a lot of
> this code is x86-specific...
This sounds like exactly the right solution. If you're running from
some unknown context (like NMI or tracing), then you should check
nmi_uaccess_okay(). I think we should just promote that to be a
non-arch-specific function (that returns true by default) and check it
the relevant bpf_probe_xyz() functions.
Alexei, does that seem reasonable?
^ permalink raw reply
* [PATCH net-next 0/8] net: Remove switchdev_ops
From: Florian Fainelli @ 2019-02-22 23:59 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
Hi all,
This patch series completes the removal of the switchdev_ops by
converting switchdev_port_attr_set() to use either the blocking
(process) or non-blocking (atomic) notifier since we typically need to
deal with both depending on where in the bridge code we get called from.
This was tested with the forwarding selftests and DSA hardware.
Ido, Jiri, please review :)
Florian Fainelli (8):
switchdev: Add SWITCHDEV_PORT_ATTR_SET
rocker: Handle SWITCHDEV_PORT_ATTR_SET
net: dsa: Handle SWITCHDEV_PORT_ATTR_SET
mlxsw: spectrum_switchdev: Handle SWITCHDEV_PORT_ATTR_SET
net: mscc: ocelot: Handle SWITCHDEV_PORT_ATTR_SET
staging: fsl-dpaa2: ethsw: Handle SWITCHDEV_PORT_ATTR_SET
net: switchdev: Replace port attr set SDO with a notification
net: Remove switchdev_ops
.../net/ethernet/mellanox/mlxsw/spectrum.c | 12 --
.../net/ethernet/mellanox/mlxsw/spectrum.h | 2 -
.../mellanox/mlxsw/spectrum_switchdev.c | 24 +--
drivers/net/ethernet/mscc/ocelot.c | 32 +++-
drivers/net/ethernet/mscc/ocelot.h | 1 +
drivers/net/ethernet/mscc/ocelot_board.c | 2 +
drivers/net/ethernet/rocker/rocker_main.c | 23 ++-
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 26 +++-
include/linux/netdevice.h | 3 -
include/net/switchdev.h | 42 ++---
net/dsa/slave.c | 23 ++-
net/switchdev/switchdev.c | 147 +++++++++---------
12 files changed, 200 insertions(+), 137 deletions(-)
--
2.17.1
^ permalink raw reply
* [PATCH net-next 1/8] switchdev: Add SWITCHDEV_PORT_ATTR_SET
From: Florian Fainelli @ 2019-02-22 23:59 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190222235927.10295-1-f.fainelli@gmail.com>
In preparation for allowing switchdev enabled drivers to veto specific
attribute settings from within the context of the caller, introduce a
new switchdev notifier type for port attributes.
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
include/net/switchdev.h | 27 +++++++++++++++++++++
net/switchdev/switchdev.c | 51 +++++++++++++++++++++++++++++++++++++++
2 files changed, 78 insertions(+)
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 45310ddf2d7e..ca56b7487540 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -136,6 +136,7 @@ enum switchdev_notifier_type {
SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */
SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */
+ SWITCHDEV_PORT_ATTR_SET, /* May be blocking . */
SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE,
SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE,
@@ -164,6 +165,13 @@ struct switchdev_notifier_port_obj_info {
bool handled;
};
+struct switchdev_notifier_port_attr_info {
+ struct switchdev_notifier_info info; /* must be first */
+ const struct switchdev_attr *attr;
+ struct switchdev_trans *trans;
+ bool handled;
+};
+
static inline struct net_device *
switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info)
{
@@ -216,7 +224,15 @@ int switchdev_handle_port_obj_del(struct net_device *dev,
int (*del_cb)(struct net_device *dev,
const struct switchdev_obj *obj));
+int switchdev_handle_port_attr_set(struct net_device *dev,
+ struct switchdev_notifier_port_attr_info *port_attr_info,
+ bool (*check_cb)(const struct net_device *dev),
+ int (*set_cb)(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans));
+
#define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops))
+
#else
static inline void switchdev_deferred_process(void)
@@ -303,6 +319,17 @@ switchdev_handle_port_obj_del(struct net_device *dev,
return 0;
}
+static inline int
+switchdev_handle_port_attr_set(struct net_device *dev,
+ struct switchdev_notifier_port_attr_info *port_attr_info,
+ bool (*check_cb)(const struct net_device *dev),
+ int (*set_cb)(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans))
+{
+ return 0;
+}
+
#define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0)
#endif
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 7e1357db33d7..94400f5b8e07 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -697,3 +697,54 @@ int switchdev_handle_port_obj_del(struct net_device *dev,
return err;
}
EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del);
+
+static int __switchdev_handle_port_attr_set(struct net_device *dev,
+ struct switchdev_notifier_port_attr_info *port_attr_info,
+ bool (*check_cb)(const struct net_device *dev),
+ int (*set_cb)(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans))
+{
+ struct net_device *lower_dev;
+ struct list_head *iter;
+ int err = -EOPNOTSUPP;
+
+ if (check_cb(dev)) {
+ port_attr_info->handled = true;
+ return set_cb(dev, port_attr_info->attr,
+ port_attr_info->trans);
+ }
+
+ /* Switch ports might be stacked under e.g. a LAG. Ignore the
+ * unsupported devices, another driver might be able to handle them. But
+ * propagate to the callers any hard errors.
+ *
+ * If the driver does its own bookkeeping of stacked ports, it's not
+ * necessary to go through this helper.
+ */
+ netdev_for_each_lower_dev(dev, lower_dev, iter) {
+ err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info,
+ check_cb, set_cb);
+ if (err && err != -EOPNOTSUPP)
+ return err;
+ }
+
+ return err;
+}
+
+int switchdev_handle_port_attr_set(struct net_device *dev,
+ struct switchdev_notifier_port_attr_info *port_attr_info,
+ bool (*check_cb)(const struct net_device *dev),
+ int (*set_cb)(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans))
+{
+ int err;
+
+ err = __switchdev_handle_port_attr_set(dev, port_attr_info, check_cb,
+ set_cb);
+ if (err == -EOPNOTSUPP)
+ err = 0;
+ return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_handle_port_attr_set);
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 2/8] rocker: Handle SWITCHDEV_PORT_ATTR_SET
From: Florian Fainelli @ 2019-02-22 23:59 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190222235927.10295-1-f.fainelli@gmail.com>
Following patches will change the way we communicate setting a port's
attribute and use notifiers towards that goal.
Prepare rocker to support receiving notifier events targeting
SWITCHDEV_PORT_ATTR_SET from both atomic and process context and use a
small helper to translate the event notifier into something that
rocker_port_attr_set() can process.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/ethernet/rocker/rocker_main.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 309a6bf9130c..fc772cf079cc 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2710,6 +2710,19 @@ static bool rocker_port_dev_check(const struct net_device *dev)
return dev->netdev_ops == &rocker_port_netdev_ops;
}
+static int
+rocker_switchdev_port_attr_set_event(struct net_device *netdev,
+ struct switchdev_notifier_port_attr_info *port_attr_info)
+{
+ int err;
+
+ err = rocker_port_attr_set(netdev, port_attr_info->attr,
+ port_attr_info->trans);
+
+ port_attr_info->handled = true;
+ return notifier_from_errno(err);
+}
+
struct rocker_switchdev_event_work {
struct work_struct work;
struct switchdev_notifier_fdb_info fdb_info;
@@ -2779,6 +2792,9 @@ static int rocker_switchdev_event(struct notifier_block *unused,
if (!rocker_port_dev_check(dev))
return NOTIFY_DONE;
+ if (event == SWITCHDEV_PORT_ATTR_SET)
+ return rocker_switchdev_port_attr_set_event(dev, ptr);
+
rocker_port = netdev_priv(dev);
switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
if (WARN_ON(!switchdev_work))
@@ -2841,6 +2857,8 @@ static int rocker_switchdev_blocking_event(struct notifier_block *unused,
case SWITCHDEV_PORT_OBJ_ADD:
case SWITCHDEV_PORT_OBJ_DEL:
return rocker_switchdev_port_obj_event(event, dev, ptr);
+ case SWITCHDEV_PORT_ATTR_SET:
+ return rocker_switchdev_port_attr_set_event(dev, ptr);
}
return NOTIFY_DONE;
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 3/8] net: dsa: Handle SWITCHDEV_PORT_ATTR_SET
From: Florian Fainelli @ 2019-02-22 23:59 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190222235927.10295-1-f.fainelli@gmail.com>
Following patches will change the way we communicate setting a port's
attribute and use notifiers towards that goal.
Prepare DSA to support receiving notifier events targeting
SWITCHDEV_PORT_ATTR_SET from both atomic and process context and use a
small helper to translate the event notifier into something that
dsa_slave_port_attr_set() can process.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
net/dsa/slave.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index a78b2bba0332..49a5b29fe884 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1422,6 +1422,19 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb,
return NOTIFY_DONE;
}
+static int
+dsa_slave_switchdev_port_attr_set_event(struct net_device *netdev,
+ struct switchdev_notifier_port_attr_info *port_attr_info)
+{
+ int err;
+
+ err = dsa_slave_port_attr_set(netdev, port_attr_info->attr,
+ port_attr_info->trans);
+
+ port_attr_info->handled = true;
+ return notifier_from_errno(err);
+}
+
struct dsa_switchdev_event_work {
struct work_struct work;
struct switchdev_notifier_fdb_info fdb_info;
@@ -1500,6 +1513,9 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused,
if (!dsa_slave_dev_check(dev))
return NOTIFY_DONE;
+ if (event == SWITCHDEV_PORT_ATTR_SET)
+ return dsa_slave_switchdev_port_attr_set_event(dev, ptr);
+
switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
if (!switchdev_work)
return NOTIFY_BAD;
@@ -1562,6 +1578,8 @@ static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused,
case SWITCHDEV_PORT_OBJ_ADD: /* fall through */
case SWITCHDEV_PORT_OBJ_DEL:
return dsa_slave_switchdev_port_obj_event(event, dev, ptr);
+ case SWITCHDEV_PORT_ATTR_SET:
+ return dsa_slave_switchdev_port_attr_set_event(dev, ptr);
}
return NOTIFY_DONE;
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 5/8] net: mscc: ocelot: Handle SWITCHDEV_PORT_ATTR_SET
From: Florian Fainelli @ 2019-02-22 23:59 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190222235927.10295-1-f.fainelli@gmail.com>
Following patches will change the way we communicate setting a port's
attribute and use notifiers to perform those tasks.
Ocelot does not currently have an atomic notifier registered for
switchdev events, so we need to register one in order to deal with
atomic context SWITCHDEV_PORT_ATTR_SET events.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/ethernet/mscc/ocelot.c | 27 ++++++++++++++++++++++++
drivers/net/ethernet/mscc/ocelot.h | 1 +
drivers/net/ethernet/mscc/ocelot_board.c | 2 ++
3 files changed, 30 insertions(+)
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 195306d05bcd..83a678b11757 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1582,6 +1582,28 @@ struct notifier_block ocelot_netdevice_nb __read_mostly = {
};
EXPORT_SYMBOL(ocelot_netdevice_nb);
+static int ocelot_switchdev_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+ int err;
+
+ switch (event) {
+ case SWITCHDEV_PORT_ATTR_SET:
+ err = switchdev_handle_port_attr_set(dev, ptr,
+ ocelot_netdevice_dev_check,
+ ocelot_port_attr_set);
+ return notifier_from_errno(err);
+ }
+
+ return NOTIFY_DONE;
+}
+
+struct notifier_block ocelot_switchdev_nb __read_mostly = {
+ .notifier_call = ocelot_switchdev_event,
+};
+EXPORT_SYMBOL(ocelot_switchdev_nb);
+
static int ocelot_switchdev_blocking_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
@@ -1600,6 +1622,11 @@ static int ocelot_switchdev_blocking_event(struct notifier_block *unused,
ocelot_netdevice_dev_check,
ocelot_port_obj_del);
return notifier_from_errno(err);
+ case SWITCHDEV_PORT_ATTR_SET:
+ err = switchdev_handle_port_attr_set(dev, ptr,
+ ocelot_netdevice_dev_check,
+ ocelot_port_attr_set);
+ return notifier_from_errno(err);
}
return NOTIFY_DONE;
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 086775f7b52f..ba3b3380b4d0 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -499,6 +499,7 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
struct phy_device *phy);
extern struct notifier_block ocelot_netdevice_nb;
+extern struct notifier_block ocelot_switchdev_nb;
extern struct notifier_block ocelot_switchdev_blocking_nb;
#endif
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index ca3ea2fbfcd0..2c1121d86edf 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -329,6 +329,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
}
register_netdevice_notifier(&ocelot_netdevice_nb);
+ register_switchdev_notifier(&ocelot_switchdev_nb);
register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
dev_info(&pdev->dev, "Ocelot switch probed\n");
@@ -345,6 +346,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev)
ocelot_deinit(ocelot);
unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
+ unregister_switchdev_notifier(&ocelot_switchdev_nb);
unregister_netdevice_notifier(&ocelot_netdevice_nb);
return 0;
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 7/8] net: switchdev: Replace port attr set SDO with a notification
From: Florian Fainelli @ 2019-02-22 23:59 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190222235927.10295-1-f.fainelli@gmail.com>
Drop switchdev_ops.switchdev_port_attr_set. Drop the uses of this field
from all clients, which were migrated to use switchdev notification in
the previous patches.
Add a new function switchdev_port_attr_notify() that sends the switchdev
notifications SWITCHDEV_PORT_ATTR_SET and takes care, depending on
SWITCHDEV_F_DEFER to call the blocking (process) or non-blocking
(atomic) notifier chain accordingly.
Drop __switchdev_port_attr_set() and update switchdev_port_attr_set()
likewise.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
net/switchdev/switchdev.c | 96 +++++++++++----------------------------
1 file changed, 26 insertions(+), 70 deletions(-)
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 94400f5b8e07..a1f16836ef89 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -174,81 +174,35 @@ static int switchdev_deferred_enqueue(struct net_device *dev,
return 0;
}
-/**
- * switchdev_port_attr_get - Get port attribute
- *
- * @dev: port device
- * @attr: attribute to get
- */
-int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+static int switchdev_port_attr_notify(enum switchdev_notifier_type nt,
+ struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans)
{
- const struct switchdev_ops *ops = dev->switchdev_ops;
- struct net_device *lower_dev;
- struct list_head *iter;
- struct switchdev_attr first = {
- .id = SWITCHDEV_ATTR_ID_UNDEFINED
- };
- int err = -EOPNOTSUPP;
+ int err;
+ int rc;
- if (ops && ops->switchdev_port_attr_get)
- return ops->switchdev_port_attr_get(dev, attr);
+ struct switchdev_notifier_port_attr_info attr_info = {
+ .attr = attr,
+ .trans = trans,
+ .handled = false,
+ };
- if (attr->flags & SWITCHDEV_F_NO_RECURSE)
+ if (attr & SWITCHDEV_F_DEFER)
+ rc = call_switchdev_blocking_notifiers(nt, dev,
+ &attr_info.info, NULL);
+ else
+ rc = call_switchdev_notifiers(nt, dev, &attr_info.info, NULL);
+ err = notifier_to_errno(rc);
+ if (err) {
+ WARN_ON(!attr_info.handled);
return err;
-
- /* Switch device port(s) may be stacked under
- * bond/team/vlan dev, so recurse down to get attr on
- * each port. Return -ENODATA if attr values don't
- * compare across ports.
- */
-
- netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = switchdev_port_attr_get(lower_dev, attr);
- if (err)
- break;
- if (first.id == SWITCHDEV_ATTR_ID_UNDEFINED)
- first = *attr;
- else if (memcmp(&first, attr, sizeof(*attr)))
- return -ENODATA;
}
- return err;
-}
-EXPORT_SYMBOL_GPL(switchdev_port_attr_get);
-
-static int __switchdev_port_attr_set(struct net_device *dev,
- const struct switchdev_attr *attr,
- struct switchdev_trans *trans)
-{
- const struct switchdev_ops *ops = dev->switchdev_ops;
- struct net_device *lower_dev;
- struct list_head *iter;
- int err = -EOPNOTSUPP;
-
- if (ops && ops->switchdev_port_attr_set) {
- err = ops->switchdev_port_attr_set(dev, attr, trans);
- goto done;
- }
-
- if (attr->flags & SWITCHDEV_F_NO_RECURSE)
- goto done;
-
- /* Switch device port(s) may be stacked under
- * bond/team/vlan dev, so recurse down to set attr on
- * each port.
- */
-
- netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = __switchdev_port_attr_set(lower_dev, attr, trans);
- if (err)
- break;
- }
-
-done:
- if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP)
- err = 0;
+ if (!attr_info.handled)
+ return -EOPNOTSUPP;
- return err;
+ return 0;
}
static int switchdev_port_attr_set_now(struct net_device *dev,
@@ -267,7 +221,8 @@ static int switchdev_port_attr_set_now(struct net_device *dev,
*/
trans.ph_prepare = true;
- err = __switchdev_port_attr_set(dev, attr, &trans);
+ err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr,
+ &trans);
if (err) {
/* Prepare phase failed: abort the transaction. Any
* resources reserved in the prepare phase are
@@ -286,7 +241,8 @@ static int switchdev_port_attr_set_now(struct net_device *dev,
*/
trans.ph_prepare = false;
- err = __switchdev_port_attr_set(dev, attr, &trans);
+ err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr,
+ &trans);
WARN(err, "%s: Commit of attribute (id=%d) failed.\n",
dev->name, attr->id);
switchdev_trans_items_warn_destroy(dev, &trans);
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 8/8] net: Remove switchdev_ops
From: Florian Fainelli @ 2019-02-22 23:59 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190222235927.10295-1-f.fainelli@gmail.com>
Now that we have converted all possible callers to using a switchdev
notifier for attributes we do not have a need for implementing
switchdev_ops anymore, and this can be removed from all drivers the
net_device structure.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
.../net/ethernet/mellanox/mlxsw/spectrum.c | 12 -----------
.../net/ethernet/mellanox/mlxsw/spectrum.h | 2 --
.../mellanox/mlxsw/spectrum_switchdev.c | 12 -----------
drivers/net/ethernet/mscc/ocelot.c | 5 -----
drivers/net/ethernet/rocker/rocker_main.c | 5 -----
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 5 -----
include/linux/netdevice.h | 3 ---
include/net/switchdev.h | 21 -------------------
net/dsa/slave.c | 5 -----
9 files changed, 70 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f018b0607dac..5d998517653a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3215,7 +3215,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
}
mlxsw_sp_port->default_vlan = mlxsw_sp_port_vlan;
- mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
mlxsw_sp->ports[local_port] = mlxsw_sp_port;
err = register_netdev(dev);
if (err) {
@@ -3232,7 +3231,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
err_register_netdev:
mlxsw_sp->ports[local_port] = NULL;
- mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
err_port_vlan_create:
err_port_pvid_set:
@@ -3275,7 +3273,6 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
mlxsw_sp->ports[local_port] = NULL;
- mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
mlxsw_sp_port_nve_fini(mlxsw_sp_port);
mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
@@ -3996,12 +3993,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
goto err_span_init;
}
- err = mlxsw_sp_switchdev_init(mlxsw_sp);
- if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize switchdev\n");
- goto err_switchdev_init;
- }
-
err = mlxsw_sp_counter_pool_init(mlxsw_sp);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
@@ -4072,8 +4063,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
err_afa_init:
mlxsw_sp_counter_pool_fini(mlxsw_sp);
err_counter_pool_init:
- mlxsw_sp_switchdev_fini(mlxsw_sp);
-err_switchdev_init:
mlxsw_sp_span_fini(mlxsw_sp);
err_span_init:
mlxsw_sp_lag_fini(mlxsw_sp);
@@ -4138,7 +4127,6 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
mlxsw_sp_nve_fini(mlxsw_sp);
mlxsw_sp_afa_fini(mlxsw_sp);
mlxsw_sp_counter_pool_fini(mlxsw_sp);
- mlxsw_sp_switchdev_fini(mlxsw_sp);
mlxsw_sp_span_fini(mlxsw_sp);
mlxsw_sp_lag_fini(mlxsw_sp);
mlxsw_sp_buffers_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 8bb83d0facc2..b1342fe9ca48 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -381,8 +381,6 @@ extern const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals;
/* spectrum_switchdev.c */
int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp);
-void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port);
-void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port);
int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
bool adding);
void
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index c1aedfea3a31..f6ce386c3036 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1938,10 +1938,6 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp,
return NULL;
}
-static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = {
- .switchdev_port_attr_set = mlxsw_sp_port_attr_set,
-};
-
static int
mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
struct mlxsw_sp_bridge_port *bridge_port,
@@ -3545,11 +3541,3 @@ void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
kfree(mlxsw_sp->bridge);
}
-void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port)
-{
- mlxsw_sp_port->dev->switchdev_ops = &mlxsw_sp_port_switchdev_ops;
-}
-
-void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-}
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 83a678b11757..a1d0d6e42533 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1324,10 +1324,6 @@ static int ocelot_port_obj_del(struct net_device *dev,
return ret;
}
-static const struct switchdev_ops ocelot_port_switchdev_ops = {
- .switchdev_port_attr_set = ocelot_port_attr_set,
-};
-
static int ocelot_port_bridge_join(struct ocelot_port *ocelot_port,
struct net_device *bridge)
{
@@ -1660,7 +1656,6 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
dev->netdev_ops = &ocelot_port_netdev_ops;
dev->ethtool_ops = &ocelot_ethtool_ops;
- dev->switchdev_ops = &ocelot_port_switchdev_ops;
dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXFCS;
dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index fc772cf079cc..c883aa89b7ca 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2142,10 +2142,6 @@ static int rocker_port_obj_del(struct net_device *dev,
return err;
}
-static const struct switchdev_ops rocker_port_switchdev_ops = {
- .switchdev_port_attr_set = rocker_port_attr_set,
-};
-
struct rocker_fib_event_work {
struct work_struct work;
union {
@@ -2599,7 +2595,6 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
rocker_port_dev_addr_init(rocker_port);
dev->netdev_ops = &rocker_port_netdev_ops;
dev->ethtool_ops = &rocker_port_ethtool_ops;
- dev->switchdev_ops = &rocker_port_switchdev_ops;
netif_tx_napi_add(dev, &rocker_port->napi_tx, rocker_port_poll_tx,
NAPI_POLL_WEIGHT);
netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx,
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 73efc2a5fd91..ef7ec02da2fa 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -925,10 +925,6 @@ static int swdev_port_obj_del(struct net_device *netdev,
return err;
}
-static const struct switchdev_ops ethsw_port_switchdev_ops = {
- .switchdev_port_attr_set = swdev_port_attr_set,
-};
-
/* For the moment, only flood setting needs to be updated */
static int port_bridge_join(struct net_device *netdev,
struct net_device *upper_dev)
@@ -1455,7 +1451,6 @@ static int ethsw_probe_port(struct ethsw_core *ethsw, u16 port_idx)
SET_NETDEV_DEV(port_netdev, dev);
port_netdev->netdev_ops = ðsw_port_ops;
port_netdev->ethtool_ops = ðsw_port_ethtool_ops;
- port_netdev->switchdev_ops = ðsw_port_switchdev_ops;
/* Set MTU limits */
port_netdev->min_mtu = ETH_MIN_MTU;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index aab4d9f6613d..a3c60ba35046 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1835,9 +1835,6 @@ struct net_device {
#endif
const struct net_device_ops *netdev_ops;
const struct ethtool_ops *ethtool_ops;
-#ifdef CONFIG_NET_SWITCHDEV
- const struct switchdev_ops *switchdev_ops;
-#endif
#ifdef CONFIG_NET_L3_MASTER_DEV
const struct l3mdev_ops *l3mdev_ops;
#endif
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index ca56b7487540..e4f751e19ecf 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -112,21 +112,6 @@ void *switchdev_trans_item_dequeue(struct switchdev_trans *trans);
typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj);
-/**
- * struct switchdev_ops - switchdev operations
- *
- * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr).
- *
- * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr).
- */
-struct switchdev_ops {
- int (*switchdev_port_attr_get)(struct net_device *dev,
- struct switchdev_attr *attr);
- int (*switchdev_port_attr_set)(struct net_device *dev,
- const struct switchdev_attr *attr,
- struct switchdev_trans *trans);
-};
-
enum switchdev_notifier_type {
SWITCHDEV_FDB_ADD_TO_BRIDGE = 1,
SWITCHDEV_FDB_DEL_TO_BRIDGE,
@@ -230,9 +215,6 @@ int switchdev_handle_port_attr_set(struct net_device *dev,
int (*set_cb)(struct net_device *dev,
const struct switchdev_attr *attr,
struct switchdev_trans *trans));
-
-#define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops))
-
#else
static inline void switchdev_deferred_process(void)
@@ -329,9 +311,6 @@ switchdev_handle_port_attr_set(struct net_device *dev,
{
return 0;
}
-
-#define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0)
-
#endif
#endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 49a5b29fe884..49dc87309bd6 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1050,10 +1050,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
.ndo_get_port_parent_id = dsa_slave_get_port_parent_id,
};
-static const struct switchdev_ops dsa_slave_switchdev_ops = {
- .switchdev_port_attr_set = dsa_slave_port_attr_set,
-};
-
static struct device_type dsa_type = {
.name = "dsa",
};
@@ -1313,7 +1309,6 @@ int dsa_slave_create(struct dsa_port *port)
eth_hw_addr_inherit(slave_dev, master);
slave_dev->priv_flags |= IFF_NO_QUEUE;
slave_dev->netdev_ops = &dsa_slave_netdev_ops;
- slave_dev->switchdev_ops = &dsa_slave_switchdev_ops;
slave_dev->min_mtu = 0;
slave_dev->max_mtu = ETH_MAX_MTU;
SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
--
2.17.1
^ permalink raw reply related
* [PATCH 1/8] switchdev: Add SWITCHDEV_PORT_ATTR_SET
From: Florian Fainelli @ 2019-02-22 23:59 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Ido Schimmel, open list,
open list:STAGING SUBSYSTEM, moderated list:ETHERNET BRIDGE, jiri,
andrew, vivien.didelot
In-Reply-To: <20190222235927.10295-1-f.fainelli@gmail.com>
In preparation for allowing switchdev enabled drivers to veto specific
attribute settings from within the context of the caller, introduce a
new switchdev notifier type for port attributes.
Suggested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
include/net/switchdev.h | 27 +++++++++++++++++++++
net/switchdev/switchdev.c | 51 +++++++++++++++++++++++++++++++++++++++
2 files changed, 78 insertions(+)
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 45310ddf2d7e..ca56b7487540 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -136,6 +136,7 @@ enum switchdev_notifier_type {
SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */
SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */
+ SWITCHDEV_PORT_ATTR_SET, /* May be blocking . */
SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE,
SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE,
@@ -164,6 +165,13 @@ struct switchdev_notifier_port_obj_info {
bool handled;
};
+struct switchdev_notifier_port_attr_info {
+ struct switchdev_notifier_info info; /* must be first */
+ const struct switchdev_attr *attr;
+ struct switchdev_trans *trans;
+ bool handled;
+};
+
static inline struct net_device *
switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info)
{
@@ -216,7 +224,15 @@ int switchdev_handle_port_obj_del(struct net_device *dev,
int (*del_cb)(struct net_device *dev,
const struct switchdev_obj *obj));
+int switchdev_handle_port_attr_set(struct net_device *dev,
+ struct switchdev_notifier_port_attr_info *port_attr_info,
+ bool (*check_cb)(const struct net_device *dev),
+ int (*set_cb)(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans));
+
#define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops))
+
#else
static inline void switchdev_deferred_process(void)
@@ -303,6 +319,17 @@ switchdev_handle_port_obj_del(struct net_device *dev,
return 0;
}
+static inline int
+switchdev_handle_port_attr_set(struct net_device *dev,
+ struct switchdev_notifier_port_attr_info *port_attr_info,
+ bool (*check_cb)(const struct net_device *dev),
+ int (*set_cb)(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans))
+{
+ return 0;
+}
+
#define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0)
#endif
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 7e1357db33d7..94400f5b8e07 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -697,3 +697,54 @@ int switchdev_handle_port_obj_del(struct net_device *dev,
return err;
}
EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del);
+
+static int __switchdev_handle_port_attr_set(struct net_device *dev,
+ struct switchdev_notifier_port_attr_info *port_attr_info,
+ bool (*check_cb)(const struct net_device *dev),
+ int (*set_cb)(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans))
+{
+ struct net_device *lower_dev;
+ struct list_head *iter;
+ int err = -EOPNOTSUPP;
+
+ if (check_cb(dev)) {
+ port_attr_info->handled = true;
+ return set_cb(dev, port_attr_info->attr,
+ port_attr_info->trans);
+ }
+
+ /* Switch ports might be stacked under e.g. a LAG. Ignore the
+ * unsupported devices, another driver might be able to handle them. But
+ * propagate to the callers any hard errors.
+ *
+ * If the driver does its own bookkeeping of stacked ports, it's not
+ * necessary to go through this helper.
+ */
+ netdev_for_each_lower_dev(dev, lower_dev, iter) {
+ err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info,
+ check_cb, set_cb);
+ if (err && err != -EOPNOTSUPP)
+ return err;
+ }
+
+ return err;
+}
+
+int switchdev_handle_port_attr_set(struct net_device *dev,
+ struct switchdev_notifier_port_attr_info *port_attr_info,
+ bool (*check_cb)(const struct net_device *dev),
+ int (*set_cb)(struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans))
+{
+ int err;
+
+ err = __switchdev_handle_port_attr_set(dev, port_attr_info, check_cb,
+ set_cb);
+ if (err == -EOPNOTSUPP)
+ err = 0;
+ return err;
+}
+EXPORT_SYMBOL_GPL(switchdev_handle_port_attr_set);
--
2.17.1
From ba4f6d2c1528229131147b177722c1714df8231e Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 31 Jan 2019 11:10:34 -0800
Subject: [PATCH 2/8] rocker: Handle SWITCHDEV_PORT_ATTR_SET
Following patches will change the way we communicate setting a port's
attribute and use notifiers towards that goal.
Prepare rocker to support receiving notifier events targeting
SWITCHDEV_PORT_ATTR_SET from both atomic and process context and use a
small helper to translate the event notifier into something that
rocker_port_attr_set() can process.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/ethernet/rocker/rocker_main.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 309a6bf9130c..fc772cf079cc 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2710,6 +2710,19 @@ static bool rocker_port_dev_check(const struct net_device *dev)
return dev->netdev_ops == &rocker_port_netdev_ops;
}
+static int
+rocker_switchdev_port_attr_set_event(struct net_device *netdev,
+ struct switchdev_notifier_port_attr_info *port_attr_info)
+{
+ int err;
+
+ err = rocker_port_attr_set(netdev, port_attr_info->attr,
+ port_attr_info->trans);
+
+ port_attr_info->handled = true;
+ return notifier_from_errno(err);
+}
+
struct rocker_switchdev_event_work {
struct work_struct work;
struct switchdev_notifier_fdb_info fdb_info;
@@ -2779,6 +2792,9 @@ static int rocker_switchdev_event(struct notifier_block *unused,
if (!rocker_port_dev_check(dev))
return NOTIFY_DONE;
+ if (event == SWITCHDEV_PORT_ATTR_SET)
+ return rocker_switchdev_port_attr_set_event(dev, ptr);
+
rocker_port = netdev_priv(dev);
switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
if (WARN_ON(!switchdev_work))
@@ -2841,6 +2857,8 @@ static int rocker_switchdev_blocking_event(struct notifier_block *unused,
case SWITCHDEV_PORT_OBJ_ADD:
case SWITCHDEV_PORT_OBJ_DEL:
return rocker_switchdev_port_obj_event(event, dev, ptr);
+ case SWITCHDEV_PORT_ATTR_SET:
+ return rocker_switchdev_port_attr_set_event(dev, ptr);
}
return NOTIFY_DONE;
--
2.17.1
From f80f3e7ac04da99d9cf3e3b8d12eccb1b49e6480 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 31 Jan 2019 13:26:26 -0800
Subject: [PATCH 3/8] net: dsa: Handle SWITCHDEV_PORT_ATTR_SET
Following patches will change the way we communicate setting a port's
attribute and use notifiers towards that goal.
Prepare DSA to support receiving notifier events targeting
SWITCHDEV_PORT_ATTR_SET from both atomic and process context and use a
small helper to translate the event notifier into something that
dsa_slave_port_attr_set() can process.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
net/dsa/slave.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index a78b2bba0332..49a5b29fe884 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1422,6 +1422,19 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb,
return NOTIFY_DONE;
}
+static int
+dsa_slave_switchdev_port_attr_set_event(struct net_device *netdev,
+ struct switchdev_notifier_port_attr_info *port_attr_info)
+{
+ int err;
+
+ err = dsa_slave_port_attr_set(netdev, port_attr_info->attr,
+ port_attr_info->trans);
+
+ port_attr_info->handled = true;
+ return notifier_from_errno(err);
+}
+
struct dsa_switchdev_event_work {
struct work_struct work;
struct switchdev_notifier_fdb_info fdb_info;
@@ -1500,6 +1513,9 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused,
if (!dsa_slave_dev_check(dev))
return NOTIFY_DONE;
+ if (event == SWITCHDEV_PORT_ATTR_SET)
+ return dsa_slave_switchdev_port_attr_set_event(dev, ptr);
+
switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
if (!switchdev_work)
return NOTIFY_BAD;
@@ -1562,6 +1578,8 @@ static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused,
case SWITCHDEV_PORT_OBJ_ADD: /* fall through */
case SWITCHDEV_PORT_OBJ_DEL:
return dsa_slave_switchdev_port_obj_event(event, dev, ptr);
+ case SWITCHDEV_PORT_ATTR_SET:
+ return dsa_slave_switchdev_port_attr_set_event(dev, ptr);
}
return NOTIFY_DONE;
--
2.17.1
From 001e6b9b955cb5035c79c223d07a1e47febac0af Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 31 Jan 2019 13:30:31 -0800
Subject: [PATCH 4/8] mlxsw: spectrum_switchdev: Handle SWITCHDEV_PORT_ATTR_SET
Following patches will change the way we communicate setting a port's
attribute and use a notifier to perform those tasks.
Prepare mlxsw to support receiving notifier events targeting
SWITCHDEV_PORT_ATTR_SET and utilize the switchdev_handle_port_attr_set()
to handle stacking of devices.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
.../net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 766f5b5f1cf5..c1aedfea3a31 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -3123,6 +3123,13 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused,
struct net_device *br_dev;
int err;
+ if (event == SWITCHDEV_PORT_ATTR_SET) {
+ err = switchdev_handle_port_attr_set(dev, ptr,
+ mlxsw_sp_port_dev_check,
+ mlxsw_sp_port_attr_set);
+ return notifier_from_errno(err);
+ }
+
/* Tunnel devices are not our uppers, so check their master instead */
br_dev = netdev_master_upper_dev_get_rcu(dev);
if (!br_dev)
@@ -3446,6 +3453,11 @@ static int mlxsw_sp_switchdev_blocking_event(struct notifier_block *unused,
mlxsw_sp_port_dev_check,
mlxsw_sp_port_obj_del);
return notifier_from_errno(err);
+ case SWITCHDEV_PORT_ATTR_SET:
+ err = switchdev_handle_port_attr_set(dev, ptr,
+ mlxsw_sp_port_dev_check,
+ mlxsw_sp_port_attr_set);
+ return notifier_from_errno(err);
}
return NOTIFY_DONE;
--
2.17.1
From e3776307a8ec8ce8726cbbb338cf1988afd90310 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 31 Jan 2019 13:31:58 -0800
Subject: [PATCH 5/8] net: mscc: ocelot: Handle SWITCHDEV_PORT_ATTR_SET
Following patches will change the way we communicate setting a port's
attribute and use notifiers to perform those tasks.
Ocelot does not currently have an atomic notifier registered for
switchdev events, so we need to register one in order to deal with
atomic context SWITCHDEV_PORT_ATTR_SET events.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/ethernet/mscc/ocelot.c | 27 ++++++++++++++++++++++++
drivers/net/ethernet/mscc/ocelot.h | 1 +
drivers/net/ethernet/mscc/ocelot_board.c | 2 ++
3 files changed, 30 insertions(+)
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 195306d05bcd..83a678b11757 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1582,6 +1582,28 @@ struct notifier_block ocelot_netdevice_nb __read_mostly = {
};
EXPORT_SYMBOL(ocelot_netdevice_nb);
+static int ocelot_switchdev_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+ int err;
+
+ switch (event) {
+ case SWITCHDEV_PORT_ATTR_SET:
+ err = switchdev_handle_port_attr_set(dev, ptr,
+ ocelot_netdevice_dev_check,
+ ocelot_port_attr_set);
+ return notifier_from_errno(err);
+ }
+
+ return NOTIFY_DONE;
+}
+
+struct notifier_block ocelot_switchdev_nb __read_mostly = {
+ .notifier_call = ocelot_switchdev_event,
+};
+EXPORT_SYMBOL(ocelot_switchdev_nb);
+
static int ocelot_switchdev_blocking_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
@@ -1600,6 +1622,11 @@ static int ocelot_switchdev_blocking_event(struct notifier_block *unused,
ocelot_netdevice_dev_check,
ocelot_port_obj_del);
return notifier_from_errno(err);
+ case SWITCHDEV_PORT_ATTR_SET:
+ err = switchdev_handle_port_attr_set(dev, ptr,
+ ocelot_netdevice_dev_check,
+ ocelot_port_attr_set);
+ return notifier_from_errno(err);
}
return NOTIFY_DONE;
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 086775f7b52f..ba3b3380b4d0 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -499,6 +499,7 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
struct phy_device *phy);
extern struct notifier_block ocelot_netdevice_nb;
+extern struct notifier_block ocelot_switchdev_nb;
extern struct notifier_block ocelot_switchdev_blocking_nb;
#endif
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index ca3ea2fbfcd0..2c1121d86edf 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -329,6 +329,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
}
register_netdevice_notifier(&ocelot_netdevice_nb);
+ register_switchdev_notifier(&ocelot_switchdev_nb);
register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
dev_info(&pdev->dev, "Ocelot switch probed\n");
@@ -345,6 +346,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev)
ocelot_deinit(ocelot);
unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
+ unregister_switchdev_notifier(&ocelot_switchdev_nb);
unregister_netdevice_notifier(&ocelot_netdevice_nb);
return 0;
--
2.17.1
From 3a90b167eddfaafb2d31dbcf139bfcca67fe6299 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 31 Jan 2019 13:33:31 -0800
Subject: [PATCH 6/8] staging: fsl-dpaa2: ethsw: Handle SWITCHDEV_PORT_ATTR_SET
Following patches will change the way we communicate setting a port's
attribute and use a blocking notifier to perform those tasks.
Prepare ethsw to support receiving notifier events targeting
SWITCHDEV_PORT_ATTR_SET and simply translate that into the existing
swdev_port_attr_set() call.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 018399ee8731..73efc2a5fd91 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -1047,6 +1047,12 @@ static int port_switchdev_event(struct notifier_block *unused,
struct ethsw_switchdev_event_work *switchdev_work;
struct switchdev_notifier_fdb_info *fdb_info = ptr;
+ if (!ethsw_port_dev_check(dev))
+ return NOTIFY_DONE;
+
+ if (event == SWITCHDEV_PORT_ATTR_SET)
+ return ethsw_switchdev_port_attr_set_event(dev, ptr);
+
switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
if (!switchdev_work)
return NOTIFY_BAD;
@@ -1103,6 +1109,19 @@ ethsw_switchdev_port_obj_event(unsigned long event, struct net_device *netdev,
return notifier_from_errno(err);
}
+static int
+ethsw_switchdev_port_attr_set_event(struct net_device *netdev,
+ struct switchdev_notifier_port_attr_info *port_attr_info)
+{
+ int err;
+
+ err = swdev_port_attr_set(netdev, port_attr_info->attr,
+ port_attr_info->trans);
+
+ port_attr_info->handled = true;
+ return notifier_from_errno(err);
+}
+
static int port_switchdev_blocking_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
@@ -1115,6 +1134,8 @@ static int port_switchdev_blocking_event(struct notifier_block *unused,
case SWITCHDEV_PORT_OBJ_ADD: /* fall through */
case SWITCHDEV_PORT_OBJ_DEL:
return ethsw_switchdev_port_obj_event(event, dev, ptr);
+ case SWITCHDEV_PORT_ATTR_SET:
+ return ethsw_switchdev_port_attr_set_event(dev, ptr);
}
return NOTIFY_DONE;
--
2.17.1
From dbad862260ca273ef066ebb5ad42d007205d86ff Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 8 Feb 2019 16:21:26 -0800
Subject: [PATCH 7/8] net: switchdev: Replace port attr set SDO with a
notification
Drop switchdev_ops.switchdev_port_attr_set. Drop the uses of this field
from all clients, which were migrated to use switchdev notification in
the previous patches.
Add a new function switchdev_port_attr_notify() that sends the switchdev
notifications SWITCHDEV_PORT_ATTR_SET and takes care, depending on
SWITCHDEV_F_DEFER to call the blocking (process) or non-blocking
(atomic) notifier chain accordingly.
Drop __switchdev_port_attr_set() and update switchdev_port_attr_set()
likewise.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
net/switchdev/switchdev.c | 96 +++++++++++----------------------------
1 file changed, 26 insertions(+), 70 deletions(-)
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 94400f5b8e07..a1f16836ef89 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -174,81 +174,35 @@ static int switchdev_deferred_enqueue(struct net_device *dev,
return 0;
}
-/**
- * switchdev_port_attr_get - Get port attribute
- *
- * @dev: port device
- * @attr: attribute to get
- */
-int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+static int switchdev_port_attr_notify(enum switchdev_notifier_type nt,
+ struct net_device *dev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans)
{
- const struct switchdev_ops *ops = dev->switchdev_ops;
- struct net_device *lower_dev;
- struct list_head *iter;
- struct switchdev_attr first = {
- .id = SWITCHDEV_ATTR_ID_UNDEFINED
- };
- int err = -EOPNOTSUPP;
+ int err;
+ int rc;
- if (ops && ops->switchdev_port_attr_get)
- return ops->switchdev_port_attr_get(dev, attr);
+ struct switchdev_notifier_port_attr_info attr_info = {
+ .attr = attr,
+ .trans = trans,
+ .handled = false,
+ };
- if (attr->flags & SWITCHDEV_F_NO_RECURSE)
+ if (attr & SWITCHDEV_F_DEFER)
+ rc = call_switchdev_blocking_notifiers(nt, dev,
+ &attr_info.info, NULL);
+ else
+ rc = call_switchdev_notifiers(nt, dev, &attr_info.info, NULL);
+ err = notifier_to_errno(rc);
+ if (err) {
+ WARN_ON(!attr_info.handled);
return err;
-
- /* Switch device port(s) may be stacked under
- * bond/team/vlan dev, so recurse down to get attr on
- * each port. Return -ENODATA if attr values don't
- * compare across ports.
- */
-
- netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = switchdev_port_attr_get(lower_dev, attr);
- if (err)
- break;
- if (first.id == SWITCHDEV_ATTR_ID_UNDEFINED)
- first = *attr;
- else if (memcmp(&first, attr, sizeof(*attr)))
- return -ENODATA;
}
- return err;
-}
-EXPORT_SYMBOL_GPL(switchdev_port_attr_get);
-
-static int __switchdev_port_attr_set(struct net_device *dev,
- const struct switchdev_attr *attr,
- struct switchdev_trans *trans)
-{
- const struct switchdev_ops *ops = dev->switchdev_ops;
- struct net_device *lower_dev;
- struct list_head *iter;
- int err = -EOPNOTSUPP;
-
- if (ops && ops->switchdev_port_attr_set) {
- err = ops->switchdev_port_attr_set(dev, attr, trans);
- goto done;
- }
-
- if (attr->flags & SWITCHDEV_F_NO_RECURSE)
- goto done;
-
- /* Switch device port(s) may be stacked under
- * bond/team/vlan dev, so recurse down to set attr on
- * each port.
- */
-
- netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = __switchdev_port_attr_set(lower_dev, attr, trans);
- if (err)
- break;
- }
-
-done:
- if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP)
- err = 0;
+ if (!attr_info.handled)
+ return -EOPNOTSUPP;
- return err;
+ return 0;
}
static int switchdev_port_attr_set_now(struct net_device *dev,
@@ -267,7 +221,8 @@ static int switchdev_port_attr_set_now(struct net_device *dev,
*/
trans.ph_prepare = true;
- err = __switchdev_port_attr_set(dev, attr, &trans);
+ err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr,
+ &trans);
if (err) {
/* Prepare phase failed: abort the transaction. Any
* resources reserved in the prepare phase are
@@ -286,7 +241,8 @@ static int switchdev_port_attr_set_now(struct net_device *dev,
*/
trans.ph_prepare = false;
- err = __switchdev_port_attr_set(dev, attr, &trans);
+ err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr,
+ &trans);
WARN(err, "%s: Commit of attribute (id=%d) failed.\n",
dev->name, attr->id);
switchdev_trans_items_warn_destroy(dev, &trans);
--
2.17.1
From 84dade3ae80b842ba1692618fba235f43a25c1ae Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 8 Feb 2019 16:22:06 -0800
Subject: [PATCH 8/8] net: Remove switchdev_ops
Now that we have converted all possible callers to using a switchdev
notifier for attributes we do not have a need for implementing
switchdev_ops anymore, and this can be removed from all drivers the
net_device structure.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
.../net/ethernet/mellanox/mlxsw/spectrum.c | 12 -----------
.../net/ethernet/mellanox/mlxsw/spectrum.h | 2 --
.../mellanox/mlxsw/spectrum_switchdev.c | 12 -----------
drivers/net/ethernet/mscc/ocelot.c | 5 -----
drivers/net/ethernet/rocker/rocker_main.c | 5 -----
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 5 -----
include/linux/netdevice.h | 3 ---
include/net/switchdev.h | 21 -------------------
net/dsa/slave.c | 5 -----
9 files changed, 70 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f018b0607dac..5d998517653a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3215,7 +3215,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
}
mlxsw_sp_port->default_vlan = mlxsw_sp_port_vlan;
- mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
mlxsw_sp->ports[local_port] = mlxsw_sp_port;
err = register_netdev(dev);
if (err) {
@@ -3232,7 +3231,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
err_register_netdev:
mlxsw_sp->ports[local_port] = NULL;
- mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
err_port_vlan_create:
err_port_pvid_set:
@@ -3275,7 +3273,6 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
mlxsw_sp->ports[local_port] = NULL;
- mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
mlxsw_sp_port_nve_fini(mlxsw_sp_port);
mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
@@ -3996,12 +3993,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
goto err_span_init;
}
- err = mlxsw_sp_switchdev_init(mlxsw_sp);
- if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize switchdev\n");
- goto err_switchdev_init;
- }
-
err = mlxsw_sp_counter_pool_init(mlxsw_sp);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Failed to init counter pool\n");
@@ -4072,8 +4063,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
err_afa_init:
mlxsw_sp_counter_pool_fini(mlxsw_sp);
err_counter_pool_init:
- mlxsw_sp_switchdev_fini(mlxsw_sp);
-err_switchdev_init:
mlxsw_sp_span_fini(mlxsw_sp);
err_span_init:
mlxsw_sp_lag_fini(mlxsw_sp);
@@ -4138,7 +4127,6 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
mlxsw_sp_nve_fini(mlxsw_sp);
mlxsw_sp_afa_fini(mlxsw_sp);
mlxsw_sp_counter_pool_fini(mlxsw_sp);
- mlxsw_sp_switchdev_fini(mlxsw_sp);
mlxsw_sp_span_fini(mlxsw_sp);
mlxsw_sp_lag_fini(mlxsw_sp);
mlxsw_sp_buffers_fini(mlxsw_sp);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 8bb83d0facc2..b1342fe9ca48 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -381,8 +381,6 @@ extern const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals;
/* spectrum_switchdev.c */
int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp);
-void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port);
-void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port);
int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
bool adding);
void
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index c1aedfea3a31..f6ce386c3036 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1938,10 +1938,6 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp,
return NULL;
}
-static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = {
- .switchdev_port_attr_set = mlxsw_sp_port_attr_set,
-};
-
static int
mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
struct mlxsw_sp_bridge_port *bridge_port,
@@ -3545,11 +3541,3 @@ void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
kfree(mlxsw_sp->bridge);
}
-void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port)
-{
- mlxsw_sp_port->dev->switchdev_ops = &mlxsw_sp_port_switchdev_ops;
-}
-
-void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-}
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 83a678b11757..a1d0d6e42533 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1324,10 +1324,6 @@ static int ocelot_port_obj_del(struct net_device *dev,
return ret;
}
-static const struct switchdev_ops ocelot_port_switchdev_ops = {
- .switchdev_port_attr_set = ocelot_port_attr_set,
-};
-
static int ocelot_port_bridge_join(struct ocelot_port *ocelot_port,
struct net_device *bridge)
{
@@ -1660,7 +1656,6 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
dev->netdev_ops = &ocelot_port_netdev_ops;
dev->ethtool_ops = &ocelot_ethtool_ops;
- dev->switchdev_ops = &ocelot_port_switchdev_ops;
dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXFCS;
dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index fc772cf079cc..c883aa89b7ca 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2142,10 +2142,6 @@ static int rocker_port_obj_del(struct net_device *dev,
return err;
}
-static const struct switchdev_ops rocker_port_switchdev_ops = {
- .switchdev_port_attr_set = rocker_port_attr_set,
-};
-
struct rocker_fib_event_work {
struct work_struct work;
union {
@@ -2599,7 +2595,6 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
rocker_port_dev_addr_init(rocker_port);
dev->netdev_ops = &rocker_port_netdev_ops;
dev->ethtool_ops = &rocker_port_ethtool_ops;
- dev->switchdev_ops = &rocker_port_switchdev_ops;
netif_tx_napi_add(dev, &rocker_port->napi_tx, rocker_port_poll_tx,
NAPI_POLL_WEIGHT);
netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx,
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index 73efc2a5fd91..ef7ec02da2fa 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -925,10 +925,6 @@ static int swdev_port_obj_del(struct net_device *netdev,
return err;
}
-static const struct switchdev_ops ethsw_port_switchdev_ops = {
- .switchdev_port_attr_set = swdev_port_attr_set,
-};
-
/* For the moment, only flood setting needs to be updated */
static int port_bridge_join(struct net_device *netdev,
struct net_device *upper_dev)
@@ -1455,7 +1451,6 @@ static int ethsw_probe_port(struct ethsw_core *ethsw, u16 port_idx)
SET_NETDEV_DEV(port_netdev, dev);
port_netdev->netdev_ops = ðsw_port_ops;
port_netdev->ethtool_ops = ðsw_port_ethtool_ops;
- port_netdev->switchdev_ops = ðsw_port_switchdev_ops;
/* Set MTU limits */
port_netdev->min_mtu = ETH_MIN_MTU;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index aab4d9f6613d..a3c60ba35046 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1835,9 +1835,6 @@ struct net_device {
#endif
const struct net_device_ops *netdev_ops;
const struct ethtool_ops *ethtool_ops;
-#ifdef CONFIG_NET_SWITCHDEV
- const struct switchdev_ops *switchdev_ops;
-#endif
#ifdef CONFIG_NET_L3_MASTER_DEV
const struct l3mdev_ops *l3mdev_ops;
#endif
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index ca56b7487540..e4f751e19ecf 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -112,21 +112,6 @@ void *switchdev_trans_item_dequeue(struct switchdev_trans *trans);
typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj);
-/**
- * struct switchdev_ops - switchdev operations
- *
- * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr).
- *
- * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr).
- */
-struct switchdev_ops {
- int (*switchdev_port_attr_get)(struct net_device *dev,
- struct switchdev_attr *attr);
- int (*switchdev_port_attr_set)(struct net_device *dev,
- const struct switchdev_attr *attr,
- struct switchdev_trans *trans);
-};
-
enum switchdev_notifier_type {
SWITCHDEV_FDB_ADD_TO_BRIDGE = 1,
SWITCHDEV_FDB_DEL_TO_BRIDGE,
@@ -230,9 +215,6 @@ int switchdev_handle_port_attr_set(struct net_device *dev,
int (*set_cb)(struct net_device *dev,
const struct switchdev_attr *attr,
struct switchdev_trans *trans));
-
-#define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops))
-
#else
static inline void switchdev_deferred_process(void)
@@ -329,9 +311,6 @@ switchdev_handle_port_attr_set(struct net_device *dev,
{
return 0;
}
-
-#define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0)
-
#endif
#endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 49a5b29fe884..49dc87309bd6 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1050,10 +1050,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
.ndo_get_port_parent_id = dsa_slave_get_port_parent_id,
};
-static const struct switchdev_ops dsa_slave_switchdev_ops = {
- .switchdev_port_attr_set = dsa_slave_port_attr_set,
-};
-
static struct device_type dsa_type = {
.name = "dsa",
};
@@ -1313,7 +1309,6 @@ int dsa_slave_create(struct dsa_port *port)
eth_hw_addr_inherit(slave_dev, master);
slave_dev->priv_flags |= IFF_NO_QUEUE;
slave_dev->netdev_ops = &dsa_slave_netdev_ops;
- slave_dev->switchdev_ops = &dsa_slave_switchdev_ops;
slave_dev->min_mtu = 0;
slave_dev->max_mtu = ETH_MAX_MTU;
SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
--
2.17.1
^ 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