* Re: [PATCH v2 bpf-next 03/10] bpf: introduce per-cpu cgroup local storage
From: Roman Gushchin @ 2018-09-26 8:42 UTC (permalink / raw)
To: Song Liu
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, Kernel Team,
Daniel Borkmann, Alexei Starovoitov
In-Reply-To: <27B81458-17C5-4840-9679-D1F5FBF6E805@fb.com>
On Tue, Sep 25, 2018 at 11:54:33AM -0700, Song Liu wrote:
>
>
> > On Sep 25, 2018, at 8:21 AM, Roman Gushchin <guro@fb.com> wrote:
> >
> > This commit introduced per-cpu cgroup local storage.
> >
> > Per-cpu cgroup local storage is very similar to simple cgroup storage
> > (let's call it shared), except all the data is per-cpu.
> >
> > The main goal of per-cpu variant is to implement super fast
> > counters (e.g. packet counters), which don't require neither
> > lookups, neither atomic operations.
> >
> > From userspace's point of view, accessing a per-cpu cgroup storage
> > is similar to other per-cpu map types (e.g. per-cpu hashmaps and
> > arrays).
> >
> > Writing to a per-cpu cgroup storage is not atomic, but is performed
> > by copying longs, so some minimal atomicity is here, exactly
> > as with other per-cpu maps.
> >
> > Signed-off-by: Roman Gushchin <guro@fb.com>
> > Cc: Daniel Borkmann <daniel@iogearbox.net>
> > Cc: Alexei Starovoitov <ast@kernel.org>
> > ---
> > include/linux/bpf-cgroup.h | 20 ++++-
> > include/linux/bpf.h | 1 +
> > include/linux/bpf_types.h | 1 +
> > include/uapi/linux/bpf.h | 1 +
> > kernel/bpf/helpers.c | 8 +-
> > kernel/bpf/local_storage.c | 148 ++++++++++++++++++++++++++++++++-----
> > kernel/bpf/syscall.c | 11 ++-
> > kernel/bpf/verifier.c | 15 +++-
> > 8 files changed, 177 insertions(+), 28 deletions(-)
> >
> > diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
> > index 7e0c9a1d48b7..9bd907657f9b 100644
> > --- a/include/linux/bpf-cgroup.h
> > +++ b/include/linux/bpf-cgroup.h
> > @@ -37,7 +37,10 @@ struct bpf_storage_buffer {
> > };
> >
> > struct bpf_cgroup_storage {
> > - struct bpf_storage_buffer *buf;
> > + union {
> > + struct bpf_storage_buffer *buf;
> > + char __percpu *percpu_buf;
>
> "char *" here looks weird. Did you mean to use "void *"?
Fair enough. It's probably a leftover from (previously used) char[0].
>
> > + };
> > struct bpf_cgroup_storage_map *map;
> > struct bpf_cgroup_storage_key key;
> > struct list_head list;
> > @@ -109,6 +112,9 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
> > static inline enum bpf_cgroup_storage_type cgroup_storage_type(
> > struct bpf_map *map)
> > {
> > + if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
> > + return BPF_CGROUP_STORAGE_PERCPU;
> > +
> > return BPF_CGROUP_STORAGE_SHARED;
> > }
> >
> > @@ -131,6 +137,10 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
> > int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map);
> > void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map);
> >
> > +int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value);
> > +int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
> > + void *value, u64 flags);
> > +
> > /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
> > #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \
> > ({ \
> > @@ -285,6 +295,14 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
> > struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; }
> > static inline void bpf_cgroup_storage_free(
> > struct bpf_cgroup_storage *storage) {}
> > +static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key,
> > + void *value) {
> > + return 0;
> > +}
> > +static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
> > + void *key, void *value, u64 flags) {
> > + return 0;
> > +}
> >
> > #define cgroup_bpf_enabled (0)
> > #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
> > diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> > index b457fbe7b70b..018299a595c8 100644
> > --- a/include/linux/bpf.h
> > +++ b/include/linux/bpf.h
> > @@ -274,6 +274,7 @@ struct bpf_prog_offload {
> >
> > enum bpf_cgroup_storage_type {
> > BPF_CGROUP_STORAGE_SHARED,
> > + BPF_CGROUP_STORAGE_PERCPU,
> > __BPF_CGROUP_STORAGE_MAX
> > };
> >
> > diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
> > index c9bd6fb765b0..5432f4c9f50e 100644
> > --- a/include/linux/bpf_types.h
> > +++ b/include/linux/bpf_types.h
> > @@ -43,6 +43,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops)
> > #endif
> > #ifdef CONFIG_CGROUP_BPF
> > BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops)
> > +BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, cgroup_storage_map_ops)
> > #endif
> > BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops)
> > BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops)
> > diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> > index aa5ccd2385ed..e2070d819e04 100644
> > --- a/include/uapi/linux/bpf.h
> > +++ b/include/uapi/linux/bpf.h
> > @@ -127,6 +127,7 @@ enum bpf_map_type {
> > BPF_MAP_TYPE_SOCKHASH,
> > BPF_MAP_TYPE_CGROUP_STORAGE,
> > BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
> > + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
> > };
> >
> > enum bpf_prog_type {
> > diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> > index e42f8789b7ea..1f21ef1c4ad3 100644
> > --- a/kernel/bpf/helpers.c
> > +++ b/kernel/bpf/helpers.c
> > @@ -206,10 +206,16 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
> > */
> > enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
> > struct bpf_cgroup_storage *storage;
> > + void *ptr = NULL;
>
> Not necessary to initialize to NULL.
Fixed.
>
> >
> > storage = this_cpu_read(bpf_cgroup_storage[stype]);
> >
> > - return (unsigned long)&READ_ONCE(storage->buf)->data[0];
> > + if (stype == BPF_CGROUP_STORAGE_SHARED)
> > + ptr = &READ_ONCE(storage->buf)->data[0];
> > + else
> > + ptr = this_cpu_ptr(storage->percpu_buf);
> > +
> > + return (unsigned long)ptr;
> > }
> >
> > const struct bpf_func_proto bpf_get_local_storage_proto = {
> > diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
> > index 6742292fb39e..d991355b5b46 100644
> > --- a/kernel/bpf/local_storage.c
> > +++ b/kernel/bpf/local_storage.c
> > @@ -152,6 +152,71 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
> > return 0;
> > }
> >
> > +int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key,
> > + void *value)
> > +{
> > + struct bpf_cgroup_storage_map *map = map_to_storage(_map);
> > + struct bpf_cgroup_storage_key *key = _key;
> > + struct bpf_cgroup_storage *storage;
> > + int cpu, off = 0;
> > + u32 size;
> > +
> > + rcu_read_lock();
> > + storage = cgroup_storage_lookup(map, key, false);
> > + if (!storage) {
> > + rcu_read_unlock();
> > + return -ENOENT;
> > + }
> > +
> > + /* per_cpu areas are zero-filled and bpf programs can only
> > + * access 'value_size' of them, so copying rounded areas
> > + * will not leak any kernel data
> > + */
> > + size = round_up(_map->value_size, 8);
> > + for_each_possible_cpu(cpu) {
> > + bpf_long_memcpy(value + off,
> > + per_cpu_ptr(storage->percpu_buf, cpu), size);
> > + off += size;
> > + }
> > + rcu_read_unlock();
> > + return 0;
> > +}
> > +
> > +int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
> > + void *value, u64 map_flags)
> > +{
> > + struct bpf_cgroup_storage_map *map = map_to_storage(_map);
> > + struct bpf_cgroup_storage_key *key = _key;
> > + struct bpf_cgroup_storage *storage;
> > + int cpu, off = 0;
> > + u32 size;
> > +
> > + if (unlikely(map_flags & BPF_EXIST))
> > + return -EINVAL;
> > +
> > + rcu_read_lock();
> > + storage = cgroup_storage_lookup(map, key, false);
> > + if (!storage) {
> > + rcu_read_unlock();
> > + return -ENOENT;
> > + }
> > +
> > + /* the user space will provide round_up(value_size, 8) bytes that
> > + * will be copied into per-cpu area. bpf programs can only access
> > + * value_size of it. During lookup the same extra bytes will be
> > + * returned or zeros which were zero-filled by percpu_alloc,
> > + * so no kernel data leaks possible
> > + */
> > + size = round_up(_map->value_size, 8);
> > + for_each_possible_cpu(cpu) {
> > + bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu),
> > + value + off, size);
> > + off += size;
> > + }
> > + rcu_read_unlock();
> > + return 0;
> > +}
> > +
> > static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
> > void *_next_key)
> > {
> > @@ -292,55 +357,98 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
> > {
> > struct bpf_cgroup_storage *storage;
> > struct bpf_map *map;
> > + gfp_t flags;
> > + size_t size;
> > u32 pages;
> >
> > map = prog->aux->cgroup_storage[stype];
> > if (!map)
> > return NULL;
> >
> > - pages = round_up(sizeof(struct bpf_cgroup_storage) +
> > - sizeof(struct bpf_storage_buffer) +
> > - map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
> > + if (stype == BPF_CGROUP_STORAGE_SHARED) {
> > + size = sizeof(struct bpf_storage_buffer) + map->value_size;
> > + pages = round_up(sizeof(struct bpf_cgroup_storage) + size,
> > + PAGE_SIZE) >> PAGE_SHIFT;
> > + } else {
> > + size = map->value_size;
> > + pages = round_up(round_up(size, 8) * num_possible_cpus(),
> > + PAGE_SIZE) >> PAGE_SHIFT;
> > + }
> > +
> > if (bpf_map_charge_memlock(map, pages))
> > return ERR_PTR(-EPERM);
> >
> > storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
> > __GFP_ZERO | GFP_USER, map->numa_node);
> > - if (!storage) {
> > - bpf_map_uncharge_memlock(map, pages);
> > - return ERR_PTR(-ENOMEM);
> > - }
> > + if (!storage)
> > + goto enomem;
> >
> > - storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) +
> > - map->value_size, __GFP_ZERO | GFP_USER,
> > - map->numa_node);
> > - if (!storage->buf) {
> > - bpf_map_uncharge_memlock(map, pages);
> > - kfree(storage);
> > - return ERR_PTR(-ENOMEM);
> > + flags = __GFP_ZERO | GFP_USER;
> > +
> > + if (stype == BPF_CGROUP_STORAGE_SHARED) {
> > + storage->buf = kmalloc_node(size, flags, map->numa_node);
> > + if (!storage->buf)
> > + goto enomem;
> > + } else {
> > + storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags);
> > + if (!storage->percpu_buf)
> > + goto enomem;
> > }
> >
> > storage->map = (struct bpf_cgroup_storage_map *)map;
> >
> > return storage;
> > +
> > +enomem:
> > + bpf_map_uncharge_memlock(map, pages);
> > + kfree(storage);
> > + return ERR_PTR(-ENOMEM);
> > +}
> > +
> > +static void free_cgroup_storage_rcu(struct rcu_head *rcu)
>
> Maybe rename as free_shared_cgroup_storage_rcu()?
Yeah, might be more clear.
Thank you for the review!
Will send v3 with these changes and your acks soon.
Thanks!
^ permalink raw reply
* [PATCH net] vxlan: fill ttl inherit info
From: Hangbin Liu @ 2018-09-26 2:35 UTC (permalink / raw)
To: netdev; +Cc: David Miller, Hangbin Liu
When add vxlan ttl inherit support, I forgot to fill it when dump
vlxan info. Fix it now.
Fixes: 72f6d71e491e6 ("vxlan: add ttl inherit support")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
drivers/net/vxlan.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ababba3..2b8da2b 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3539,6 +3539,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */
nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */
+ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL_INHERIT */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */
nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */
@@ -3603,6 +3604,8 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
}
if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) ||
+ nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT,
+ !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) ||
nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
nla_put_u8(skb, IFLA_VXLAN_LEARNING,
--
2.5.5
^ permalink raw reply related
* [PATCH] net: qed: list usage cleanup
From: zhong jiang @ 2018-09-26 8:53 UTC (permalink / raw)
To: davem; +Cc: Ariel.Elior, everest-linux-l2, netdev, linux-kernel
Trival cleanup, list_move_tail will implement the same function that
list_del() + list_add_tail() will do. hence just replace them.
Signed-off-by: zhong jiang <zhongjiang@huawei.com>
---
drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 9 ++++-----
drivers/net/ethernet/qlogic/qed/qed_ooo.c | 10 ++++------
drivers/net/ethernet/qlogic/qed/qed_spq.c | 3 +--
3 files changed, 9 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 17f3dfa..f99797a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -935,9 +935,8 @@ int qed_iwarp_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
}
spin_lock_bh(&p_hwfn->p_rdma_info->iwarp.iw_lock);
- list_del(&ep->list_entry);
- list_add_tail(&ep->list_entry,
- &p_hwfn->p_rdma_info->iwarp.ep_free_list);
+ list_move_tail(&ep->list_entry,
+ &p_hwfn->p_rdma_info->iwarp.ep_free_list);
spin_unlock_bh(&p_hwfn->p_rdma_info->iwarp.iw_lock);
}
@@ -2270,8 +2269,8 @@ static void qed_iwarp_process_pending_pkts(struct qed_hwfn *p_hwfn)
if (rc == -EBUSY)
break;
- list_del(&mpa_buf->list_entry);
- list_add_tail(&mpa_buf->list_entry, &iwarp_info->mpa_buf_list);
+ list_move_tail(&mpa_buf->list_entry,
+ &iwarp_info->mpa_buf_list);
if (rc) { /* different error, don't continue */
DP_NOTICE(p_hwfn, "process pkts failed rc=%d\n", rc);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
index 6172354..63931df 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
@@ -211,9 +211,8 @@ void qed_ooo_release_connection_isles(struct qed_hwfn *p_hwfn,
if (!p_buffer)
break;
- list_del(&p_buffer->list_entry);
- list_add_tail(&p_buffer->list_entry,
- &p_ooo_info->free_buffers_list);
+ list_move_tail(&p_buffer->list_entry,
+ &p_ooo_info->free_buffers_list);
}
list_add_tail(&p_isle->list_entry,
&p_ooo_info->free_isles_list);
@@ -247,9 +246,8 @@ void qed_ooo_release_all_isles(struct qed_hwfn *p_hwfn,
if (!p_buffer)
break;
- list_del(&p_buffer->list_entry);
- list_add_tail(&p_buffer->list_entry,
- &p_ooo_info->free_buffers_list);
+ list_move_tail(&p_buffer->list_entry,
+ &p_ooo_info->free_buffers_list);
}
list_add_tail(&p_isle->list_entry,
&p_ooo_info->free_isles_list);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 1673fc9..c4a6274 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -730,8 +730,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn,
!list_empty(head)) {
struct qed_spq_entry *p_ent =
list_first_entry(head, struct qed_spq_entry, list);
- list_del(&p_ent->list);
- list_add_tail(&p_ent->list, &p_spq->completion_pending);
+ list_move_tail(&p_ent->list, &p_spq->completion_pending);
p_spq->comp_sent_count++;
rc = qed_spq_hw_post(p_hwfn, p_spq, p_ent);
--
1.7.12.4
^ permalink raw reply related
* [PATCH] net: liquidio: list usage cleanup
From: zhong jiang @ 2018-09-26 8:56 UTC (permalink / raw)
To: davem; +Cc: derek.chickles, satananda.burla, felix.manlunas, netdev,
linux-kernel
Trival cleanup, list_move_tail will implement the same function that
list_del() + list_add_tail() will do. hence just replace them.
Signed-off-by: zhong jiang <zhongjiang@huawei.com>
---
drivers/net/ethernet/cavium/liquidio/octeon_device.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 0f0275c..ce8c3f8 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1044,8 +1044,7 @@ void octeon_delete_dispatch_list(struct octeon_device *oct)
dispatch = &oct->dispatch.dlist[i].list;
while (dispatch->next != dispatch) {
temp = dispatch->next;
- list_del(temp);
- list_add_tail(temp, &freelist);
+ list_move_tail(temp, &freelist);
}
oct->dispatch.dlist[i].opcode = 0;
--
1.7.12.4
^ permalink raw reply related
* Re: [PATCH v2 net-next] tcp: expose sk_state in tcp_retransmit_skb tracepoint
From: Eric Dumazet @ 2018-09-26 2:47 UTC (permalink / raw)
To: Yafang Shao, edumazet, davem; +Cc: netdev
In-Reply-To: <1537793849-32396-1-git-send-email-laoar.shao@gmail.com>
On 09/24/2018 05:57 AM, Yafang Shao wrote:
> After sk_state exposed, we can get in which state this retransmission
> occurs. That could give us more detail for dignostic.
> For example, if this retransmission occurs in SYN_SENT state, it may
> also indicates that the syn packet may be dropped on the remote peer due
> to syn backlog queue full and then we could check the remote peer.
>
> BTW,SYNACK retransmission is traced in tcp_retransmit_synack tracepoint.
>
> Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
^ permalink raw reply
* Re: [PATCH net-next v6 07/23] zinc: ChaCha20 ARM and ARM64 implementations
From: Ard Biesheuvel @ 2018-09-26 8:59 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: Linux Kernel Mailing List, <netdev@vger.kernel.org>,
open list:HARDWARE RANDOM NUMBER GENERATOR CORE, David S. Miller,
Greg Kroah-Hartman, Samuel Neves, Andy Lutomirski,
Jean-Philippe Aumasson, Russell King, linux-arm-kernel
In-Reply-To: <20180925145622.29959-8-Jason@zx2c4.com>
On Tue, 25 Sep 2018 at 17:00, Jason A. Donenfeld <Jason@zx2c4.com> wrote:
>
> These wire Andy Polyakov's implementations up to the kernel for ARMv7,8
> NEON, and introduce Eric Biggers' ultra-fast scalar implementation for
> CPUs without NEON or for CPUs with slow NEON (Cortex-A5,7).
>
> This commit does the following:
> - Adds the glue code for the assembly implementations.
> - Renames the ARMv8 code into place, since it can at this point be
> used wholesale.
> - Merges Andy Polyakov's ARMv7 NEON code with Eric Biggers' <=ARMv7
> scalar code.
>
> Commit note: Eric Biggers' scalar code is brand new, and quite possibly
> prematurely added to this commit, and so it may require a bit of revision.
>
> This commit delivers approximately the same or much better performance than
> the existing crypto API's code and has been measured to do as such on:
>
> - ARM1176JZF-S [ARMv6]
> - Cortex-A7 [ARMv7]
> - Cortex-A8 [ARMv7]
> - Cortex-A9 [ARMv7]
> - Cortex-A17 [ARMv7]
> - Cortex-A53 [ARMv8]
> - Cortex-A55 [ARMv8]
> - Cortex-A73 [ARMv8]
> - Cortex-A75 [ARMv8]
>
> Interestingly, Andy Polyakov's scalar code is slower than Eric Biggers',
> but is also significantly shorter. This has the advantage that it does
> not evict other code from L1 cache -- particularly on ARM11 chips -- and
> so in certain circumstances it can actually be faster. However, it wasn't
> found that this had an affect on any code existing in the kernel today.
>
> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
> Co-authored-by: Eric Biggers <ebiggers@google.com>
> Cc: Samuel Neves <sneves@dei.uc.pt>
> Cc: Andy Lutomirski <luto@kernel.org>
> Cc: Greg KH <gregkh@linuxfoundation.org>
> Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@gmail.com>
> Cc: Russell King <linux@armlinux.org.uk>
> Cc: linux-arm-kernel@lists.infradead.org
> ---
> lib/zinc/Makefile | 2 +
> lib/zinc/chacha20/chacha20-arm-glue.h | 88 +++
> ...acha20-arm-cryptogams.S => chacha20-arm.S} | 502 ++++++++++++++++--
> ...20-arm64-cryptogams.S => chacha20-arm64.S} | 0
> lib/zinc/chacha20/chacha20.c | 2 +
> 5 files changed, 556 insertions(+), 38 deletions(-)
> create mode 100644 lib/zinc/chacha20/chacha20-arm-glue.h
> rename lib/zinc/chacha20/{chacha20-arm-cryptogams.S => chacha20-arm.S} (71%)
> rename lib/zinc/chacha20/{chacha20-arm64-cryptogams.S => chacha20-arm64.S} (100%)
>
> diff --git a/lib/zinc/Makefile b/lib/zinc/Makefile
> index 223a0816c918..e47f64e12bbd 100644
> --- a/lib/zinc/Makefile
> +++ b/lib/zinc/Makefile
> @@ -4,4 +4,6 @@ ccflags-$(CONFIG_ZINC_DEBUG) += -DDEBUG
>
> zinc_chacha20-y := chacha20/chacha20.o
> zinc_chacha20-$(CONFIG_ZINC_ARCH_X86_64) += chacha20/chacha20-x86_64.o
> +zinc_chacha20-$(CONFIG_ZINC_ARCH_ARM) += chacha20/chacha20-arm.o
> +zinc_chacha20-$(CONFIG_ZINC_ARCH_ARM64) += chacha20/chacha20-arm64.o
> obj-$(CONFIG_ZINC_CHACHA20) += zinc_chacha20.o
> diff --git a/lib/zinc/chacha20/chacha20-arm-glue.h b/lib/zinc/chacha20/chacha20-arm-glue.h
> new file mode 100644
> index 000000000000..86cce851ed02
> --- /dev/null
> +++ b/lib/zinc/chacha20/chacha20-arm-glue.h
> @@ -0,0 +1,88 @@
> +/* SPDX-License-Identifier: GPL-2.0 OR MIT */
> +/*
> + * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
> + */
> +
> +#include <asm/hwcap.h>
> +#include <asm/neon.h>
> +#if defined(CONFIG_ARM)
> +#include <asm/system_info.h>
> +#include <asm/cputype.h>
> +#endif
> +
> +asmlinkage void chacha20_arm(u8 *out, const u8 *in, const size_t len,
> + const u32 key[8], const u32 counter[4]);
> +#if defined(CONFIG_ARM)
> +asmlinkage void hchacha20_arm(const u32 state[16], u32 out[8]);
> +#endif
> +#if defined(CONFIG_KERNEL_MODE_NEON)
> +asmlinkage void chacha20_neon(u8 *out, const u8 *in, const size_t len,
> + const u32 key[8], const u32 counter[4]);
> +#endif
> +
> +static bool chacha20_use_neon __ro_after_init;
> +
> +static void __init chacha20_fpu_init(void)
> +{
> +#if defined(CONFIG_ARM64)
> + chacha20_use_neon = elf_hwcap & HWCAP_ASIMD;
> +#elif defined(CONFIG_ARM)
> + switch (read_cpuid_part()) {
> + case ARM_CPU_PART_CORTEX_A7:
> + case ARM_CPU_PART_CORTEX_A5:
> + /* The Cortex-A7 and Cortex-A5 do not perform well with the NEON
> + * implementation but do incredibly with the scalar one and use
> + * less power.
> + */
> + break;
> + default:
> + chacha20_use_neon = elf_hwcap & HWCAP_NEON;
> + }
> +#endif
> +}
> +
> +static inline bool chacha20_arch(struct chacha20_ctx *state, u8 *dst,
> + const u8 *src, size_t len,
> + simd_context_t *simd_context)
> +{
> +#if defined(CONFIG_KERNEL_MODE_NEON)
> + if (chacha20_use_neon && len >= CHACHA20_BLOCK_SIZE * 3 &&
> + simd_use(simd_context))
> + chacha20_neon(dst, src, len, state->key, state->counter);
> + else
> +#endif
Better to use IS_ENABLED() here:
> + if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON)) &&
> + chacha20_use_neon && len >= CHACHA20_BLOCK_SIZE * 3 &&
> + simd_use(simd_context))
Also, this still has unbounded worst case scheduling latency, given
that the outer library function passes its entire input straight into
the NEON routine.
> + chacha20_arm(dst, src, len, state->key, state->counter);
> +
> + state->counter[0] += (len + 63) / 64;
> + return true;
> +}
> +
> +static inline bool hchacha20_arch(u32 derived_key[CHACHA20_KEY_WORDS],
> + const u8 nonce[HCHACHA20_NONCE_SIZE],
> + const u8 key[HCHACHA20_KEY_SIZE],
> + simd_context_t *simd_context)
> +{
> +#if defined(CONFIG_ARM)
> + u32 x[] = { CHACHA20_CONSTANT_EXPA,
> + CHACHA20_CONSTANT_ND_3,
> + CHACHA20_CONSTANT_2_BY,
> + CHACHA20_CONSTANT_TE_K,
> + get_unaligned_le32(key + 0),
> + get_unaligned_le32(key + 4),
> + get_unaligned_le32(key + 8),
> + get_unaligned_le32(key + 12),
> + get_unaligned_le32(key + 16),
> + get_unaligned_le32(key + 20),
> + get_unaligned_le32(key + 24),
> + get_unaligned_le32(key + 28),
> + get_unaligned_le32(nonce + 0),
> + get_unaligned_le32(nonce + 4),
> + get_unaligned_le32(nonce + 8),
> + get_unaligned_le32(nonce + 12)
> + };
> + hchacha20_arm(x, derived_key);
> + return true;
> +#else
> + return false;
> +#endif
> +}
> diff --git a/lib/zinc/chacha20/chacha20-arm-cryptogams.S b/lib/zinc/chacha20/chacha20-arm.S
> similarity index 71%
> rename from lib/zinc/chacha20/chacha20-arm-cryptogams.S
> rename to lib/zinc/chacha20/chacha20-arm.S
> index 770bab469171..5abedafcf129 100644
> --- a/lib/zinc/chacha20/chacha20-arm-cryptogams.S
> +++ b/lib/zinc/chacha20/chacha20-arm.S
> @@ -1,13 +1,475 @@
> /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
> /*
> + * Copyright (C) 2018 Google, Inc.
> * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
> * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
> - *
> - * This is based in part on Andy Polyakov's implementation from CRYPTOGAMS.
> */
>
> #include <linux/linkage.h>
>
> +/*
> + * The following scalar routine was written by Eric Biggers.
> + *
> + * Design notes:
> + *
> + * 16 registers would be needed to hold the state matrix, but only 14 are
> + * available because 'sp' and 'pc' cannot be used. So we spill the elements
> + * (x8, x9) to the stack and swap them out with (x10, x11). This adds one
> + * 'ldrd' and one 'strd' instruction per round.
> + *
> + * All rotates are performed using the implicit rotate operand accepted by the
> + * 'add' and 'eor' instructions. This is faster than using explicit rotate
> + * instructions. To make this work, we allow the values in the second and last
> + * rows of the ChaCha state matrix (rows 'b' and 'd') to temporarily have the
> + * wrong rotation amount. The rotation amount is then fixed up just in time
> + * when the values are used. 'brot' is the number of bits the values in row 'b'
> + * need to be rotated right to arrive at the correct values, and 'drot'
> + * similarly for row 'd'. (brot, drot) start out as (0, 0) but we make it such
> + * that they end up as (25, 24) after every round.
> + */
> +
> + // ChaCha state registers
> + X0 .req r0
> + X1 .req r1
> + X2 .req r2
> + X3 .req r3
> + X4 .req r4
> + X5 .req r5
> + X6 .req r6
> + X7 .req r7
> + X8_X10 .req r8 // shared by x8 and x10
> + X9_X11 .req r9 // shared by x9 and x11
> + X12 .req r10
> + X13 .req r11
> + X14 .req r12
> + X15 .req r14
> +
> +.Lexpand_32byte_k:
> + // "expand 32-byte k"
> + .word 0x61707865, 0x3320646e, 0x79622d32, 0x6b206574
> +
> +#ifdef __thumb2__
> +# define adrl adr
> +#endif
> +
> +.macro __rev out, in, t0, t1, t2
> +.if __LINUX_ARM_ARCH__ >= 6
> + rev \out, \in
> +.else
> + lsl \t0, \in, #24
> + and \t1, \in, #0xff00
> + and \t2, \in, #0xff0000
> + orr \out, \t0, \in, lsr #24
> + orr \out, \out, \t1, lsl #8
> + orr \out, \out, \t2, lsr #8
> +.endif
> +.endm
> +
> +.macro _le32_bswap x, t0, t1, t2
> +#ifdef __ARMEB__
> + __rev \x, \x, \t0, \t1, \t2
> +#endif
> +.endm
> +
> +.macro _le32_bswap_4x a, b, c, d, t0, t1, t2
> + _le32_bswap \a, \t0, \t1, \t2
> + _le32_bswap \b, \t0, \t1, \t2
> + _le32_bswap \c, \t0, \t1, \t2
> + _le32_bswap \d, \t0, \t1, \t2
> +.endm
> +
> +.macro __ldrd a, b, src, offset
> +#if __LINUX_ARM_ARCH__ >= 6
> + ldrd \a, \b, [\src, #\offset]
> +#else
> + ldr \a, [\src, #\offset]
> + ldr \b, [\src, #\offset + 4]
> +#endif
> +.endm
> +
> +.macro __strd a, b, dst, offset
> +#if __LINUX_ARM_ARCH__ >= 6
> + strd \a, \b, [\dst, #\offset]
> +#else
> + str \a, [\dst, #\offset]
> + str \b, [\dst, #\offset + 4]
> +#endif
> +.endm
> +
> +.macro _halfround a1, b1, c1, d1, a2, b2, c2, d2
> +
> + // a += b; d ^= a; d = rol(d, 16);
> + add \a1, \a1, \b1, ror #brot
> + add \a2, \a2, \b2, ror #brot
> + eor \d1, \a1, \d1, ror #drot
> + eor \d2, \a2, \d2, ror #drot
> + // drot == 32 - 16 == 16
> +
> + // c += d; b ^= c; b = rol(b, 12);
> + add \c1, \c1, \d1, ror #16
> + add \c2, \c2, \d2, ror #16
> + eor \b1, \c1, \b1, ror #brot
> + eor \b2, \c2, \b2, ror #brot
> + // brot == 32 - 12 == 20
> +
> + // a += b; d ^= a; d = rol(d, 8);
> + add \a1, \a1, \b1, ror #20
> + add \a2, \a2, \b2, ror #20
> + eor \d1, \a1, \d1, ror #16
> + eor \d2, \a2, \d2, ror #16
> + // drot == 32 - 8 == 24
> +
> + // c += d; b ^= c; b = rol(b, 7);
> + add \c1, \c1, \d1, ror #24
> + add \c2, \c2, \d2, ror #24
> + eor \b1, \c1, \b1, ror #20
> + eor \b2, \c2, \b2, ror #20
> + // brot == 32 - 7 == 25
> +.endm
> +
> +.macro _doubleround
> +
> + // column round
> +
> + // quarterrounds: (x0, x4, x8, x12) and (x1, x5, x9, x13)
> + _halfround X0, X4, X8_X10, X12, X1, X5, X9_X11, X13
> +
> + // save (x8, x9); restore (x10, x11)
> + __strd X8_X10, X9_X11, sp, 0
> + __ldrd X8_X10, X9_X11, sp, 8
> +
> + // quarterrounds: (x2, x6, x10, x14) and (x3, x7, x11, x15)
> + _halfround X2, X6, X8_X10, X14, X3, X7, X9_X11, X15
> +
> + .set brot, 25
> + .set drot, 24
> +
> + // diagonal round
> +
> + // quarterrounds: (x0, x5, x10, x15) and (x1, x6, x11, x12)
> + _halfround X0, X5, X8_X10, X15, X1, X6, X9_X11, X12
> +
> + // save (x10, x11); restore (x8, x9)
> + __strd X8_X10, X9_X11, sp, 8
> + __ldrd X8_X10, X9_X11, sp, 0
> +
> + // quarterrounds: (x2, x7, x8, x13) and (x3, x4, x9, x14)
> + _halfround X2, X7, X8_X10, X13, X3, X4, X9_X11, X14
> +.endm
> +
> +.macro _chacha_permute nrounds
> + .set brot, 0
> + .set drot, 0
> + .rept \nrounds / 2
> + _doubleround
> + .endr
> +.endm
> +
> +.macro _chacha nrounds
> +
> +.Lnext_block\@:
> + // Stack: unused0-unused1 x10-x11 x0-x15 OUT IN LEN
> + // Registers contain x0-x9,x12-x15.
> +
> + // Do the core ChaCha permutation to update x0-x15.
> + _chacha_permute \nrounds
> +
> + add sp, #8
> + // Stack: x10-x11 orig_x0-orig_x15 OUT IN LEN
> + // Registers contain x0-x9,x12-x15.
> + // x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
> +
> + // Free up some registers (r8-r12,r14) by pushing (x8-x9,x12-x15).
> + push {X8_X10, X9_X11, X12, X13, X14, X15}
> +
> + // Load (OUT, IN, LEN).
> + ldr r14, [sp, #96]
> + ldr r12, [sp, #100]
> + ldr r11, [sp, #104]
> +
> + orr r10, r14, r12
> +
> + // Use slow path if fewer than 64 bytes remain.
> + cmp r11, #64
> + blt .Lxor_slowpath\@
> +
> + // Use slow path if IN and/or OUT isn't 4-byte aligned. Needed even on
> + // ARMv6+, since ldmia and stmia (used below) still require alignment.
> + tst r10, #3
> + bne .Lxor_slowpath\@
> +
> + // Fast path: XOR 64 bytes of aligned data.
> +
> + // Stack: x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
> + // Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is OUT.
> + // x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
> +
> + // x0-x3
> + __ldrd r8, r9, sp, 32
> + __ldrd r10, r11, sp, 40
> + add X0, X0, r8
> + add X1, X1, r9
> + add X2, X2, r10
> + add X3, X3, r11
> + _le32_bswap_4x X0, X1, X2, X3, r8, r9, r10
> + ldmia r12!, {r8-r11}
> + eor X0, X0, r8
> + eor X1, X1, r9
> + eor X2, X2, r10
> + eor X3, X3, r11
> + stmia r14!, {X0-X3}
> +
> + // x4-x7
> + __ldrd r8, r9, sp, 48
> + __ldrd r10, r11, sp, 56
> + add X4, r8, X4, ror #brot
> + add X5, r9, X5, ror #brot
> + ldmia r12!, {X0-X3}
> + add X6, r10, X6, ror #brot
> + add X7, r11, X7, ror #brot
> + _le32_bswap_4x X4, X5, X6, X7, r8, r9, r10
> + eor X4, X4, X0
> + eor X5, X5, X1
> + eor X6, X6, X2
> + eor X7, X7, X3
> + stmia r14!, {X4-X7}
> +
> + // x8-x15
> + pop {r0-r7} // (x8-x9,x12-x15,x10-x11)
> + __ldrd r8, r9, sp, 32
> + __ldrd r10, r11, sp, 40
> + add r0, r0, r8 // x8
> + add r1, r1, r9 // x9
> + add r6, r6, r10 // x10
> + add r7, r7, r11 // x11
> + _le32_bswap_4x r0, r1, r6, r7, r8, r9, r10
> + ldmia r12!, {r8-r11}
> + eor r0, r0, r8 // x8
> + eor r1, r1, r9 // x9
> + eor r6, r6, r10 // x10
> + eor r7, r7, r11 // x11
> + stmia r14!, {r0,r1,r6,r7}
> + ldmia r12!, {r0,r1,r6,r7}
> + __ldrd r8, r9, sp, 48
> + __ldrd r10, r11, sp, 56
> + add r2, r8, r2, ror #drot // x12
> + add r3, r9, r3, ror #drot // x13
> + add r4, r10, r4, ror #drot // x14
> + add r5, r11, r5, ror #drot // x15
> + _le32_bswap_4x r2, r3, r4, r5, r9, r10, r11
> + ldr r9, [sp, #72] // load LEN
> + eor r2, r2, r0 // x12
> + eor r3, r3, r1 // x13
> + eor r4, r4, r6 // x14
> + eor r5, r5, r7 // x15
> + subs r9, #64 // decrement and check LEN
> + stmia r14!, {r2-r5}
> +
> + beq .Ldone\@
> +
> +.Lprepare_for_next_block\@:
> +
> + // Stack: x0-x15 OUT IN LEN
> +
> + // Increment block counter (x12)
> + add r8, #1
> +
> + // Store updated (OUT, IN, LEN)
> + str r14, [sp, #64]
> + str r12, [sp, #68]
> + str r9, [sp, #72]
> +
> + mov r14, sp
> +
> + // Store updated block counter (x12)
> + str r8, [sp, #48]
> +
> + sub sp, #16
> +
> + // Reload state and do next block
> + ldmia r14!, {r0-r11} // load x0-x11
> + __strd r10, r11, sp, 8 // store x10-x11 before state
> + ldmia r14, {r10-r12,r14} // load x12-x15
> + b .Lnext_block\@
> +
> +.Lxor_slowpath\@:
> + // Slow path: < 64 bytes remaining, or unaligned input or output buffer.
> + // We handle it by storing the 64 bytes of keystream to the stack, then
> + // XOR-ing the needed portion with the data.
> +
> + // Allocate keystream buffer
> + sub sp, #64
> + mov r14, sp
> +
> + // Stack: ks0-ks15 x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
> + // Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is &ks0.
> + // x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
> +
> + // Save keystream for x0-x3
> + __ldrd r8, r9, sp, 96
> + __ldrd r10, r11, sp, 104
> + add X0, X0, r8
> + add X1, X1, r9
> + add X2, X2, r10
> + add X3, X3, r11
> + _le32_bswap_4x X0, X1, X2, X3, r8, r9, r10
> + stmia r14!, {X0-X3}
> +
> + // Save keystream for x4-x7
> + __ldrd r8, r9, sp, 112
> + __ldrd r10, r11, sp, 120
> + add X4, r8, X4, ror #brot
> + add X5, r9, X5, ror #brot
> + add X6, r10, X6, ror #brot
> + add X7, r11, X7, ror #brot
> + _le32_bswap_4x X4, X5, X6, X7, r8, r9, r10
> + add r8, sp, #64
> + stmia r14!, {X4-X7}
> +
> + // Save keystream for x8-x15
> + ldm r8, {r0-r7} // (x8-x9,x12-x15,x10-x11)
> + __ldrd r8, r9, sp, 128
> + __ldrd r10, r11, sp, 136
> + add r0, r0, r8 // x8
> + add r1, r1, r9 // x9
> + add r6, r6, r10 // x10
> + add r7, r7, r11 // x11
> + _le32_bswap_4x r0, r1, r6, r7, r8, r9, r10
> + stmia r14!, {r0,r1,r6,r7}
> + __ldrd r8, r9, sp, 144
> + __ldrd r10, r11, sp, 152
> + add r2, r8, r2, ror #drot // x12
> + add r3, r9, r3, ror #drot // x13
> + add r4, r10, r4, ror #drot // x14
> + add r5, r11, r5, ror #drot // x15
> + _le32_bswap_4x r2, r3, r4, r5, r9, r10, r11
> + stmia r14, {r2-r5}
> +
> + // Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
> + // Registers: r8 is block counter, r12 is IN.
> +
> + ldr r9, [sp, #168] // LEN
> + ldr r14, [sp, #160] // OUT
> + cmp r9, #64
> + mov r0, sp
> + movle r1, r9
> + movgt r1, #64
> + // r1 is number of bytes to XOR, in range [1, 64]
> +
> +.if __LINUX_ARM_ARCH__ < 6
> + orr r2, r12, r14
> + tst r2, #3 // IN or OUT misaligned?
> + bne .Lxor_next_byte\@
> +.endif
> +
> + // XOR a word at a time
> +.rept 16
> + subs r1, #4
> + blt .Lxor_words_done\@
> + ldr r2, [r12], #4
> + ldr r3, [r0], #4
> + eor r2, r2, r3
> + str r2, [r14], #4
> +.endr
> + b .Lxor_slowpath_done\@
> +.Lxor_words_done\@:
> + ands r1, r1, #3
> + beq .Lxor_slowpath_done\@
> +
> + // XOR a byte at a time
> +.Lxor_next_byte\@:
> + ldrb r2, [r12], #1
> + ldrb r3, [r0], #1
> + eor r2, r2, r3
> + strb r2, [r14], #1
> + subs r1, #1
> + bne .Lxor_next_byte\@
> +
> +.Lxor_slowpath_done\@:
> + subs r9, #64
> + add sp, #96
> + bgt .Lprepare_for_next_block\@
> +
> +.Ldone\@:
> +.endm // _chacha
> +
> +/*
> + * void chacha20_arm(u8 *out, const u8 *in, size_t len, const u32 key[8],
> + * const u32 iv[4]);
> + */
> +ENTRY(chacha20_arm)
> + cmp r2, #0 // len == 0?
> + bxeq lr
> +
> + push {r0-r2,r4-r11,lr}
> +
> + // Push state x0-x15 onto stack.
> + // Also store an extra copy of x10-x11 just before the state.
> +
> + ldr r4, [sp, #48] // iv
> + mov r0, sp
> + sub sp, #80
> +
> + // iv: x12-x15
> + ldm r4, {X12,X13,X14,X15}
> + stmdb r0!, {X12,X13,X14,X15}
> +
> + // key: x4-x11
> + __ldrd X8_X10, X9_X11, r3, 24
> + __strd X8_X10, X9_X11, sp, 8
> + stmdb r0!, {X8_X10, X9_X11}
> + ldm r3, {X4-X9_X11}
> + stmdb r0!, {X4-X9_X11}
> +
> + // constants: x0-x3
> + adrl X3, .Lexpand_32byte_k
> + ldm X3, {X0-X3}
> + __strd X0, X1, sp, 16
> + __strd X2, X3, sp, 24
> +
> + _chacha 20
> +
> + add sp, #76
> + pop {r4-r11, pc}
> +ENDPROC(chacha20_arm)
> +
> +/*
> + * void hchacha20_arm(const u32 state[16], u32 out[8]);
> + */
> +ENTRY(hchacha20_arm)
> + push {r1,r4-r11,lr}
> +
> + mov r14, r0
> + ldmia r14!, {r0-r11} // load x0-x11
> + push {r10-r11} // store x10-x11 to stack
> + ldm r14, {r10-r12,r14} // load x12-x15
> + sub sp, #8
> +
> + _chacha_permute 20
> +
> + // Skip over (unused0-unused1, x10-x11)
> + add sp, #16
> +
> + // Fix up rotations of x12-x15
> + ror X12, X12, #drot
> + ror X13, X13, #drot
> + pop {r4} // load 'out'
> + ror X14, X14, #drot
> + ror X15, X15, #drot
> +
> + // Store (x0-x3,x12-x15) to 'out'
> + stm r4, {X0,X1,X2,X3,X12,X13,X14,X15}
> +
> + pop {r4-r11,pc}
> +ENDPROC(hchacha20_arm)
> +
> +#ifdef CONFIG_KERNEL_MODE_NEON
> +/*
> + * This following NEON routine was ported from Andy Polyakov's implementation
> + * from CRYPTOGAMS. It begins with parts of the CRYPTOGAMS scalar routine,
> + * since certain NEON code paths actually branch to it.
> + */
> +
> .text
> #if defined(__thumb2__) || defined(__clang__)
> .syntax unified
> @@ -22,39 +484,6 @@
> #define ldrhsb ldrbhs
> #endif
>
> -.align 5
> -.Lsigma:
> -.long 0x61707865,0x3320646e,0x79622d32,0x6b206574 @ endian-neutral
> -.Lone:
> -.long 1,0,0,0
> -.word -1
> -
> -.align 5
> -ENTRY(chacha20_arm)
> - ldr r12,[sp,#0] @ pull pointer to counter and nonce
> - stmdb sp!,{r0-r2,r4-r11,lr}
> - cmp r2,#0 @ len==0?
> -#ifdef __thumb2__
> - itt eq
> -#endif
> - addeq sp,sp,#4*3
> - beq .Lno_data_arm
> - ldmia r12,{r4-r7} @ load counter and nonce
> - sub sp,sp,#4*(16) @ off-load area
> -#if __LINUX_ARM_ARCH__ < 7 && !defined(__thumb2__)
> - sub r14,pc,#100 @ .Lsigma
> -#else
> - adr r14,.Lsigma @ .Lsigma
> -#endif
> - stmdb sp!,{r4-r7} @ copy counter and nonce
> - ldmia r3,{r4-r11} @ load key
> - ldmia r14,{r0-r3} @ load sigma
> - stmdb sp!,{r4-r11} @ copy key
> - stmdb sp!,{r0-r3} @ copy sigma
> - str r10,[sp,#4*(16+10)] @ off-load "rx"
> - str r11,[sp,#4*(16+11)] @ off-load "rx"
> - b .Loop_outer_enter
> -
> .align 4
> .Loop_outer:
> ldmia sp,{r0-r9} @ load key material
> @@ -748,11 +1177,8 @@ ENTRY(chacha20_arm)
>
> .Ldone:
> add sp,sp,#4*(32+3)
> -.Lno_data_arm:
> ldmia sp!,{r4-r11,pc}
> -ENDPROC(chacha20_arm)
>
> -#ifdef CONFIG_KERNEL_MODE_NEON
> .align 5
> .Lsigma2:
> .long 0x61707865,0x3320646e,0x79622d32,0x6b206574 @ endian-neutral
> diff --git a/lib/zinc/chacha20/chacha20-arm64-cryptogams.S b/lib/zinc/chacha20/chacha20-arm64.S
> similarity index 100%
> rename from lib/zinc/chacha20/chacha20-arm64-cryptogams.S
> rename to lib/zinc/chacha20/chacha20-arm64.S
> diff --git a/lib/zinc/chacha20/chacha20.c b/lib/zinc/chacha20/chacha20.c
> index 4354b874a6a5..fc4f74fca653 100644
> --- a/lib/zinc/chacha20/chacha20.c
> +++ b/lib/zinc/chacha20/chacha20.c
> @@ -16,6 +16,8 @@
>
> #if defined(CONFIG_ZINC_ARCH_X86_64)
> #include "chacha20-x86_64-glue.h"
> +#elif defined(CONFIG_ZINC_ARCH_ARM) || defined(CONFIG_ZINC_ARCH_ARM64)
> +#include "chacha20-arm-glue.h"
> #else
> void __init chacha20_fpu_init(void)
> {
> --
> 2.19.0
>
^ permalink raw reply
* Re: [PATCH] net-tcp: /proc/sys/net/ipv4/tcp_probe_interval is a u32 not int
From: Eric Dumazet @ 2018-09-26 2:53 UTC (permalink / raw)
To: Maciej Żenczykowski, Maciej Żenczykowski,
David S . Miller, Eric Dumazet
Cc: netdev
In-Reply-To: <20180926004103.163145-1-zenczykowski@gmail.com>
On 09/25/2018 05:41 PM, Maciej Żenczykowski wrote:
> From: Maciej Żenczykowski <maze@google.com>
>
> (fix documentation and sysctl access to treat it as such)
>
> Signed-off-by: Maciej Żenczykowski <maze@google.com>
> ---
While we are at it, we probably should add sane limits,
given tcp_mtu_check_reprobe() does :
u32 interval = net->ipv4.sysctl_tcp_probe_interval;
...
if (unlikely(delta >= interval * HZ)) {
A limit of UINT_MAX / HZ would avoid an overflow I guess.
^ permalink raw reply
* Re: [PATCH net RFT] bnxt_en: Fix TX timeout during netpoll.
From: Michael Chan @ 2018-09-26 2:54 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Eric Dumazet, Song Liu, David Miller, Netdev
In-Reply-To: <CANn89iLiYE81yDHpfV3UWUVFxrbqJJiTkA6Tg6DAShAwdBeQ6w@mail.gmail.com>
On Tue, Sep 25, 2018 at 7:25 PM Eric Dumazet <edumazet@google.com> wrote:
>
> On Tue, Sep 25, 2018 at 7:15 PM Michael Chan <michael.chan@broadcom.com> wrote:
> >
> > On Tue, Sep 25, 2018 at 4:11 PM Michael Chan <michael.chan@broadcom.com> wrote:
> > >
> > > On Tue, Sep 25, 2018 at 3:15 PM Eric Dumazet <eric.dumazet@gmail.com> wrote:
> > >
> > > >
> > > > It seems bnx2 should have a similar issue ?
> > > >
> > >
> > > Yes, I think so. The MSIX mode in bnx2 is also auto-masking, meaning
> > > that MSIX will only assert once after it is ARMed. If we return from
> > > ->poll() when budget of 0 is reached without ARMing, we may not get
> > > another MSIX.
> > >
> >
> > On second thought, I think bnx2 is ok. If netpoll is polling on the
> > TX packets and reaching budget of 0 and returning, the INT_ACK_CMD
> > register is untouched. bnx2 uses the status block for events and the
> > producers/consumers are cumulative. So there is no need to ACK the
> > status block unless ARMing for interrupts. If there is an IRQ about
> > to be fired, it won't be affected by the polling done by netpoll.
> >
> > In the case of bnxt, a completion ring is used for the events. The
> > polling done by netpoll will cause the completion ring to be ACKed as
> > entries are processed. ACKing the completion ring without ARMing may
> > cause future IRQs to be disabled for that ring.
>
> About bnxt : Are you sure it is all about IRQ problems ?
I'm pretty sure, because FB first reported TX timeouts followed by
ring reset failures when running netconsole. These ring reset
failures are caused by IRQs no longer working on some rings.
>
> What if the whole ring buffer is is filled, then all entries
> are processed from netpoll.
>
> If cp_raw_cons becomes too high without the NIC knowing its (updated)
> value, maybe no IRQ can be generated anymore because
> of some wrapping issue (based on ring size)
Good point. We have logic to handle that. We will ACK the ring at
least once every tp->tx_wake_thresh TX packets. But this logic fails
when the budget is 0, so I need to send a revised patch take care of
this one case.
>
> I guess that in order to test this, we would need something bursting
> 16000 messages while holding napi->poll_owner.
> The (single) IRQ would set/grab the SCHED bit but the cpu responsible
> to service this (soft)irq would spin for the whole test,
> and no more IRQ should be fired really.
Right, not easy to hit. But it should be handled by my v2 patch. Thanks.
^ permalink raw reply
* [PATCH net-next] net: smsc: fix return type of ndo_start_xmit function
From: YueHaibing @ 2018-09-26 9:06 UTC (permalink / raw)
To: davem, nico, steve.glendinning, robert.jarzmik
Cc: linux-kernel, netdev, YueHaibing
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.
Found by coccinelle.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/ethernet/smsc/smc911x.c | 3 ++-
drivers/net/ethernet/smsc/smc91x.c | 3 ++-
drivers/net/ethernet/smsc/smsc911x.c | 3 ++-
3 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index b1b53f6..8355dfb 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -513,7 +513,8 @@ static void smc911x_hardware_send_pkt(struct net_device *dev)
* now, or set the card to generates an interrupt when ready
* for the packet.
*/
-static int smc911x_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t
+smc911x_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct smc911x_local *lp = netdev_priv(dev);
unsigned int free;
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index b944828..8d6cff8 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -638,7 +638,8 @@ static void smc_hardware_send_pkt(unsigned long data)
* now, or set the card to generates an interrupt when ready
* for the packet.
*/
-static int smc_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t
+smc_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct smc_local *lp = netdev_priv(dev);
void __iomem *ioaddr = lp->base;
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index c009407..99a5a8a 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1786,7 +1786,8 @@ static int smsc911x_stop(struct net_device *dev)
}
/* Entry point for transmitting a packet */
-static int smsc911x_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t
+smsc911x_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct smsc911x_data *pdata = netdev_priv(dev);
unsigned int freespace;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] net: ti: fix return type of ndo_start_xmit function
From: YueHaibing @ 2018-09-26 9:09 UTC (permalink / raw)
To: davem, f.fainelli, grygorii.strashko, w-kwok2, m-karicheri2,
lukas, bgolaszewski, ivan.khoronzhuk, dan.carpenter
Cc: linux-kernel, netdev, linux-omap, YueHaibing
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.
Found by coccinelle.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/ethernet/ti/cpmac.c | 2 +-
drivers/net/ethernet/ti/davinci_emac.c | 2 +-
drivers/net/ethernet/ti/netcp_core.c | 8 ++++----
3 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index 9b8a30b..64c45eb 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -544,7 +544,7 @@ static int cpmac_poll(struct napi_struct *napi, int budget)
}
-static int cpmac_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t cpmac_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
int queue;
unsigned int len;
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index f270bee..b83f32d 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -943,7 +943,7 @@ static void emac_tx_handler(void *token, int len, int status)
*
* Returns success(NETDEV_TX_OK) or error code (typically out of desc's)
*/
-static int emac_dev_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t emac_dev_xmit(struct sk_buff *skb, struct net_device *ndev)
{
struct device *emac_dev = &ndev->dev;
int ret_code;
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 1f61226..2d8cfe8 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1270,7 +1270,8 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp,
}
/* Submit the packet */
-static int netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t
+netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev)
{
struct netcp_intf *netcp = netdev_priv(ndev);
struct netcp_stats *tx_stats = &netcp->stats;
@@ -1290,7 +1291,7 @@ static int netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev)
dev_warn(netcp->ndev_dev, "padding failed (%d), packet dropped\n",
ret);
tx_stats->tx_dropped++;
- return ret;
+ return NETDEV_TX_BUSY;
}
skb->len = NETCP_MIN_PACKET_SIZE;
}
@@ -1298,7 +1299,6 @@ static int netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev)
desc = netcp_tx_map_skb(skb, netcp);
if (unlikely(!desc)) {
netif_stop_subqueue(ndev, subqueue);
- ret = -ENOBUFS;
goto drop;
}
@@ -1319,7 +1319,7 @@ static int netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev)
if (desc)
netcp_free_tx_desc_chain(netcp, desc, sizeof(*desc));
dev_kfree_skb(skb);
- return ret;
+ return NETDEV_TX_BUSY;
}
int netcp_txpipe_close(struct netcp_tx_pipe *tx_pipe)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] net: faraday: fix return type of ndo_start_xmit function
From: YueHaibing @ 2018-09-26 9:13 UTC (permalink / raw)
To: davem, andrew, f.fainelli, joel, sam, garsilva
Cc: linux-kernel, netdev, YueHaibing
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.
Found by coccinelle.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/ethernet/faraday/ftgmac100.c | 4 ++--
drivers/net/ethernet/faraday/ftmac100.c | 7 ++++---
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index d8ead7e..4d67322 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -712,8 +712,8 @@ static bool ftgmac100_prep_tx_csum(struct sk_buff *skb, u32 *csum_vlan)
return skb_checksum_help(skb) == 0;
}
-static int ftgmac100_hard_start_xmit(struct sk_buff *skb,
- struct net_device *netdev)
+static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
+ struct net_device *netdev)
{
struct ftgmac100 *priv = netdev_priv(netdev);
struct ftgmac100_txdes *txdes, *first;
diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index a1197d3..570caeb 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -634,8 +634,8 @@ static void ftmac100_tx_complete(struct ftmac100 *priv)
;
}
-static int ftmac100_xmit(struct ftmac100 *priv, struct sk_buff *skb,
- dma_addr_t map)
+static netdev_tx_t ftmac100_xmit(struct ftmac100 *priv, struct sk_buff *skb,
+ dma_addr_t map)
{
struct net_device *netdev = priv->netdev;
struct ftmac100_txdes *txdes;
@@ -1016,7 +1016,8 @@ static int ftmac100_stop(struct net_device *netdev)
return 0;
}
-static int ftmac100_hard_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t
+ftmac100_hard_start_xmit(struct sk_buff *skb, struct net_device *netdev)
{
struct ftmac100 *priv = netdev_priv(netdev);
dma_addr_t map;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] net: ovs: fix return type of ndo_start_xmit function
From: YueHaibing @ 2018-09-26 9:15 UTC (permalink / raw)
To: davem, pshelar; +Cc: linux-kernel, netdev, dev, YueHaibing
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.
Found by coccinelle.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
net/openvswitch/vport-internal_dev.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index bb95c43..26f71cb 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -43,7 +43,8 @@ static struct internal_dev *internal_dev_priv(struct net_device *netdev)
}
/* Called with rcu_read_lock_bh. */
-static int internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t
+internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
{
int len, err;
@@ -62,7 +63,7 @@ static int internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
} else {
netdev->stats.tx_errors++;
}
- return 0;
+ return NETDEV_TX_OK;
}
static int internal_dev_open(struct net_device *netdev)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] net: caif: fix return type of ndo_start_xmit function
From: YueHaibing @ 2018-09-26 9:27 UTC (permalink / raw)
To: davem, dmitry.tarnyagin; +Cc: linux-kernel, netdev, YueHaibing
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.
Found by coccinelle.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/caif/caif_hsi.c | 10 +++++-----
drivers/net/caif/caif_serial.c | 7 +++++--
drivers/net/caif/caif_spi.c | 6 +++---
drivers/net/caif/caif_virtio.c | 2 +-
net/caif/chnl_net.c | 3 ++-
5 files changed, 16 insertions(+), 12 deletions(-)
diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index 433a14b..70c449e 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -1006,7 +1006,7 @@ static void cfhsi_aggregation_tout(struct timer_list *t)
cfhsi_start_tx(cfhsi);
}
-static int cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct cfhsi *cfhsi = NULL;
int start_xfer = 0;
@@ -1014,7 +1014,7 @@ static int cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
int prio;
if (!dev)
- return -EINVAL;
+ return NETDEV_TX_BUSY;
cfhsi = netdev_priv(dev);
@@ -1048,7 +1048,7 @@ static int cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
if (WARN_ON(test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))) {
spin_unlock_bh(&cfhsi->lock);
cfhsi_abort_tx(cfhsi);
- return -EINVAL;
+ return NETDEV_TX_BUSY;
}
/* Send flow off if number of packets is above high water mark. */
@@ -1072,7 +1072,7 @@ static int cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
spin_unlock_bh(&cfhsi->lock);
if (aggregate_ready)
cfhsi_start_tx(cfhsi);
- return 0;
+ return NETDEV_TX_OK;
}
/* Delete inactivity timer if started. */
@@ -1102,7 +1102,7 @@ static int cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
queue_work(cfhsi->wq, &cfhsi->wake_up_work);
}
- return 0;
+ return NETDEV_TX_OK;
}
static const struct net_device_ops cfhsi_netdevops;
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index a0f954f..acb3264 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -275,7 +275,7 @@ static int handle_tx(struct ser_device *ser)
return tty_wr;
}
-static int caif_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t caif_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ser_device *ser;
@@ -290,7 +290,10 @@ static int caif_xmit(struct sk_buff *skb, struct net_device *dev)
ser->common.flowctrl(ser->dev, OFF);
skb_queue_tail(&ser->head, skb);
- return handle_tx(ser);
+ if (handle_tx(ser))
+ return NETDEV_TX_BUSY;
+
+ return NETDEV_TX_OK;
}
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
index d28a139..9040658 100644
--- a/drivers/net/caif/caif_spi.c
+++ b/drivers/net/caif/caif_spi.c
@@ -486,12 +486,12 @@ static void cfspi_xfer_done_cb(struct cfspi_ifc *ifc)
complete(&cfspi->comp);
}
-static int cfspi_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t cfspi_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct cfspi *cfspi = NULL;
unsigned long flags;
if (!dev)
- return -EINVAL;
+ return NETDEV_TX_BUSY;
cfspi = netdev_priv(dev);
@@ -512,7 +512,7 @@ static int cfspi_xmit(struct sk_buff *skb, struct net_device *dev)
cfspi->cfdev.flowctrl(cfspi->ndev, 0);
}
- return 0;
+ return NETDEV_TX_OK;
}
int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len)
diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 2814e0d..f5507db 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -519,7 +519,7 @@ static struct buf_info *cfv_alloc_and_copy_to_shm(struct cfv_info *cfv,
}
/* Put the CAIF packet on the virtio ring and kick the receiver */
-static int cfv_netdev_tx(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t cfv_netdev_tx(struct sk_buff *skb, struct net_device *netdev)
{
struct cfv_info *cfv = netdev_priv(netdev);
struct buf_info *buf_info;
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 13e2ae6..30be426 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -211,7 +211,8 @@ static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow,
}
}
-static int chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t
+chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct chnl_net *priv;
struct cfpkt *pkt = NULL;
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH 2/2] net: if_arp: use define instead of hard-coded value
From: Stephen Hemminger @ 2018-09-26 9:27 UTC (permalink / raw)
To: Håkon Bugge
Cc: David S . Miller, Alexey Kuznetsov, Hideaki YOSHIFUJI,
linux-kernel, netdev
In-Reply-To: <20180921103930.1420679-3-Haakon.Bugge@oracle.com>
On Fri, 21 Sep 2018 12:39:30 +0200
Håkon Bugge <Haakon.Bugge@oracle.com> wrote:
> uapi/linux/if_arp.h includes linux/netdevice.h, which uses
> IFNAMSIZ. Hence, use it instead of hard-coded value.
>
> Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
I tested build of iproute2 with updated header and there is no issue.
Tested-by: Stephen Hemminger <stephen@networkplumber.org>
^ permalink raw reply
* Re: [PATCH net-next v3 00/10] Refactor classifier API to work with Qdisc/blocks without rtnl lock
From: David Miller @ 2018-09-26 3:18 UTC (permalink / raw)
To: vladbu
Cc: netdev, jhs, xiyou.wangcong, jiri, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc
In-Reply-To: <1537805922-10744-1-git-send-email-vladbu@mellanox.com>
From: Vlad Buslov <vladbu@mellanox.com>
Date: Mon, 24 Sep 2018 19:18:32 +0300
...
> The goal of this change is to refactor tcf_block_find() and its
> dependencies to allow concurrent execution:
> - Extend Qdisc API with rcu to lookup and take reference to Qdisc
> without relying on rtnl lock.
> - Extend tcf_block with atomic reference counting and rcu.
> - Always take reference to tcf_block while working with it.
> - Implement tcf_block_release() to release resources obtained by
> tcf_block_find()
> - Create infrastructure to allow registering Qdiscs with class ops that
> do not require the caller to hold rtnl lock.
Series applied, thank you.
^ permalink raw reply
* [PATCH] net: arp, ipv6: handle special case of tap device
From: Vladis Dronov @ 2018-09-26 9:30 UTC (permalink / raw)
To: David S . Miller, Alexey Kuznetsov, Hideaki YOSHIFUJI, netdev,
syzkaller, linux-kernel
Cc: Vladis Dronov
dev->type can be set to any value for tun/tap devices by TUNSETLINK ioctl.
Nevertheless, all other dev's fields related to the link level like addr_len
and broadcast remain the same as configured previously for ARPHRD_ETHER type,
making dev inconsistent. This can lead to read from uninitialized memory.
Fix this by checking for the case of tun/tap device and act according to the
real link level type of dev while mapping a multicast IP onto multicast MAC
Reported-by: syzbot+d3402c47f680ff24b29c@syzkaller.appspotmail.com
Signed-off-by: Vladis Dronov <vdronov@redhat.com>
---
net/ipv4/arp.c | 9 ++++++++-
net/ipv6/ndisc.c | 9 ++++++++-
2 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index e90c89ef8c08..9ce472cf98a3 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -187,7 +187,14 @@ EXPORT_SYMBOL(arp_tbl);
int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir)
{
- switch (dev->type) {
+ unsigned short type = dev->type;
+
+#if IS_ENABLED(CONFIG_TAP)
+ if (dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "tun"))
+ type = ARPHRD_ETHER;
+#endif /* CONFIG_TAP */
+
+ switch (type) {
case ARPHRD_ETHER:
case ARPHRD_FDDI:
case ARPHRD_IEEE802:
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 0ec273997d1d..9371ff4454f7 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -283,7 +283,14 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
{
- switch (dev->type) {
+ unsigned short type = dev->type;
+
+#if IS_ENABLED(CONFIG_TAP)
+ if (dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "tun"))
+ type = ARPHRD_ETHER;
+#endif /* CONFIG_TAP */
+
+ switch (type) {
case ARPHRD_ETHER:
case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */
case ARPHRD_FDDI:
--
2.19.0
^ permalink raw reply related
* Re: [net-next 00/10][pull request] 40GbE Intel Wired LAN Driver Updates 2018-09-25
From: David Miller @ 2018-09-26 3:25 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: netdev, nhorman, sassmann, jogreene
In-Reply-To: <20180925202004.27726-1-jeffrey.t.kirsher@intel.com>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Tue, 25 Sep 2018 13:19:54 -0700
> This series contains updates to i40e and xsk.
...
> The following are changes since commit bd6207202db8974ca3d3183ca0d5611d45b2973c:
> net: macb: Clean 64b dma addresses if they are not detected
> and are available in the git repository at:
> git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue 40GbE
Pulled, thanks Jeff.
^ permalink raw reply
* Re: [PATCH] net: dsa: lantiq_gswip: Depend on HAS_IOMEM
From: David Miller @ 2018-09-26 3:27 UTC (permalink / raw)
To: hauke; +Cc: netdev, f.fainelli, andrew, vivien.didelot
In-Reply-To: <20180925195533.10753-1-hauke@hauke-m.de>
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Tue, 25 Sep 2018 21:55:33 +0200
> The driver uses devm_ioremap_resource() which is only available when
> CONFIG_HAS_IOMEM is set, make the driver depend on this config option.
> User mode Linux does not have CONFIG_HAS_IOMEM set and the driver was
> failing on this architecture.
>
> Fixes: 14fceff4771e ("net: dsa: Add Lantiq / Intel DSA driver for vrx200")
> Reported-by: kbuild test robot <lkp@intel.com>
> Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Applied to net-next.
^ permalink raw reply
* [PATCH net-next] net: hamradio: fix return type of ndo_start_xmit function
From: YueHaibing @ 2018-09-26 9:40 UTC (permalink / raw)
To: davem, t.sailer, jreuter; +Cc: linux-kernel, netdev, linux-hams, YueHaibing
The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.
Found by coccinelle.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/hamradio/baycom_epp.c | 3 ++-
drivers/net/hamradio/dmascc.c | 4 ++--
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 1e62d00..f4ceccf 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -772,7 +772,8 @@ static void epp_bh(struct work_struct *work)
* ===================== network driver interface =========================
*/
-static int baycom_send_packet(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t
+baycom_send_packet(struct sk_buff *skb, struct net_device *dev)
{
struct baycom_state *bc = netdev_priv(dev);
diff --git a/drivers/net/hamradio/dmascc.c b/drivers/net/hamradio/dmascc.c
index cde4120..2798870 100644
--- a/drivers/net/hamradio/dmascc.c
+++ b/drivers/net/hamradio/dmascc.c
@@ -239,7 +239,7 @@ struct scc_info {
static int scc_open(struct net_device *dev);
static int scc_close(struct net_device *dev);
static int scc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
-static int scc_send_packet(struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t scc_send_packet(struct sk_buff *skb, struct net_device *dev);
static int scc_set_mac_address(struct net_device *dev, void *sa);
static inline void tx_on(struct scc_priv *priv);
@@ -921,7 +921,7 @@ static int scc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
}
-static int scc_send_packet(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t scc_send_packet(struct sk_buff *skb, struct net_device *dev)
{
struct scc_priv *priv = dev->ml_priv;
unsigned long flags;
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH net-next] bridge: br_arp_nd_proxy: set icmp6_router if neigh has NTF_ROUTER
From: David Miller @ 2018-09-26 3:34 UTC (permalink / raw)
To: roopa; +Cc: netdev
In-Reply-To: <1537911554-40232-1-git-send-email-roopa@cumulusnetworks.com>
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Tue, 25 Sep 2018 14:39:14 -0700
> From: Roopa Prabhu <roopa@cumulusnetworks.com>
>
> Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next] tls: Fix socket mem accounting error under async encryption
From: David Miller @ 2018-09-26 3:40 UTC (permalink / raw)
To: vakul.garg; +Cc: netdev, borisp, aviadye, davejwatson, doronrk
In-Reply-To: <DB7PR04MB4252659DBF89BBB5EFEAD8308B150@DB7PR04MB4252.eurprd04.prod.outlook.com>
From: Vakul Garg <vakul.garg@nxp.com>
Date: Wed, 26 Sep 2018 01:54:25 +0000
> I don't find this patch and one other ("tls: Fixed a memory leak
> during socket close") in linux-net-next. Could you please kindly
> check? Regards.
After applying I didn't push out and instead I started a test build,
closed my laptop, did a lot of other things and just came back to
finish the build.
It'll show up momentarily.
Thanks for your patience.
^ permalink raw reply
* Re: pull-request: bpf-next 2018-09-25
From: David Miller @ 2018-09-26 3:40 UTC (permalink / raw)
To: daniel; +Cc: ast, netdev
In-Reply-To: <20180925204343.30270-1-daniel@iogearbox.net>
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 25 Sep 2018 22:43:43 +0200
> The following pull-request contains BPF updates for your *net-next*
> tree.
Pulled, there was a minor merge conflict. Please double check my work.
Thanks.
^ permalink raw reply
* Re: KASAN: global-out-of-bounds Read in __aa_lookupn_ns
From: Dmitry Vyukov @ 2018-09-26 10:06 UTC (permalink / raw)
To: syzbot, John Johansen, James Morris, Serge E. Hallyn,
linux-security-module
Cc: David Miller, LKML, netdev, syzkaller-bugs
In-Reply-To: <000000000000a7487d0576c18693@google.com>
On Wed, Sep 26, 2018 at 9:54 AM, syzbot
<syzbot+71b6643475f707f93fdc@syzkaller.appspotmail.com> wrote:
> Hello,
>
> syzbot found the following crash on:
>
> HEAD commit: 02214bfc89c7 Merge tag 'media/v4.19-2' of git://git.kernel..
> git tree: upstream
> console output: https://syzkaller.appspot.com/x/log.txt?x=1456f8a1400000
> kernel config: https://syzkaller.appspot.com/x/.config?x=22a62640793a83c9
> dashboard link: https://syzkaller.appspot.com/bug?extid=71b6643475f707f93fdc
> compiler: gcc (GCC) 8.0.1 20180413 (experimental)
>
> Unfortunately, I don't have any reproducer for this crash yet.
Again misattributed to net. This misattribution should now be fixed by:
https://github.com/google/syzkaller/commit/db716d6653d073b0abfb51186cd4ac2d5418c9c6
Adding security/apparmor/policy_ns.c maintainers explicitly.
> IMPORTANT: if you fix the bug, please add the following tag to the commit:
> Reported-by: syzbot+71b6643475f707f93fdc@syzkaller.appspotmail.com
>
> sock_common_setsockopt+0x9a/0xe0 net/core/sock.c:3038
> __sys_setsockopt+0x1ba/0x3c0 net/socket.c:1902
> __do_sys_setsockopt net/socket.c:1913 [inline]
> __se_sys_setsockopt net/socket.c:1910 [inline]
> __x64_sys_setsockopt+0xbe/0x150 net/socket.c:1910
> do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
> ==================================================================
> BUG: KASAN: global-out-of-bounds in memcmp+0xe3/0x160 lib/string.c:861
> Read of size 1 at addr ffffffff88000008 by task syz-executor0/10914
>
> entry_SYSCALL_64_after_hwframe+0x49/0xbe
> RIP: 0033:0x457579
> Code: 1d b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7
> 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff
> 0f 83 eb b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00
> RSP: 002b:00007f4c14533c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
> RAX: ffffffffffffffda RBX: 00007f4c14533c90 RCX: 0000000000457579
> RDX: 0000000000000040 RSI: 0000000000000000 RDI: 0000000000000003
> RBP: 000000000072bf00 R08: 0000000000000004 R09: 0000000000000000
> R10: 0000000020000080 R11: 0000000000000246 R12: 00007f4c145346d4
> R13: 00000000004c3ed9 R14: 00000000004d6260 R15: 0000000000000004
> CPU: 0 PID: 10914 Comm: syz-executor0 Not tainted 4.19.0-rc5+ #252
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
> Google 01/01/2011
> Call Trace:
> __dump_stack lib/dump_stack.c:77 [inline]
> dump_stack+0x1c4/0x2b4 lib/dump_stack.c:113
> print_address_description.cold.8+0x58/0x1ff mm/kasan/report.c:256
> kasan_report_error mm/kasan/report.c:354 [inline]
> kasan_report.cold.9+0x242/0x309 mm/kasan/report.c:412
> __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430
> memcmp+0xe3/0x160 lib/string.c:861
> strnstr+0x4b/0x70 lib/string.c:934
> __aa_lookupn_ns+0xc1/0x570 security/apparmor/policy_ns.c:209
> aa_lookupn_ns+0x88/0x1e0 security/apparmor/policy_ns.c:240
> aa_fqlookupn_profile+0x1b9/0x1010 security/apparmor/policy.c:468
> fqlookupn_profile+0x80/0xc0 security/apparmor/label.c:1844
> aa_label_strn_parse+0xa3a/0x1230 security/apparmor/label.c:1908
> aa_label_parse+0x42/0x50 security/apparmor/label.c:1943
> aa_change_profile+0x513/0x3510 security/apparmor/domain.c:1362
> apparmor_setprocattr+0xa8b/0x1150 security/apparmor/lsm.c:656
> security_setprocattr+0x66/0xc0 security/security.c:1298
> proc_pid_attr_write+0x301/0x540 fs/proc/base.c:2555
> __vfs_write+0x119/0x9f0 fs/read_write.c:485
> vfs_write+0x1fc/0x560 fs/read_write.c:549
> ksys_write+0x101/0x260 fs/read_write.c:598
> __do_sys_write fs/read_write.c:610 [inline]
> __se_sys_write fs/read_write.c:607 [inline]
> __x64_sys_write+0x73/0xb0 fs/read_write.c:607
> do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
> entry_SYSCALL_64_after_hwframe+0x49/0xbe
> RIP: 0033:0x457579
> Code: 1d b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7
> 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff
> 0f 83 eb b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00
> RSP: 002b:00007f5a92ec2c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
> RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457579
> RDX: 000000000000002c RSI: 00000000200000c0 RDI: 0000000000000004
> RBP: 000000000072bf00 R08: 0000000000000000 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000246 R12: 00007f5a92ec36d4
> R13: 00000000004c5454 R14: 00000000004d8c78 R15: 00000000ffffffff
>
> CPU: 1 PID: 10921 Comm: syz-executor3 Not tainted 4.19.0-rc5+ #252
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
> Google 01/01/2011
> The buggy address belongs to the variable:
> __start_rodata+0x8/0x1000
> Call Trace:
> __dump_stack lib/dump_stack.c:77 [inline]
> dump_stack+0x1c4/0x2b4 lib/dump_stack.c:113
>
> Memory state around the buggy address:
> ffffffff87ffff00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
> ffffffff87ffff80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
> fail_dump lib/fault-inject.c:51 [inline]
> should_fail.cold.4+0xa/0x17 lib/fault-inject.c:149
>>
>> ffffffff88000000: 00 fa fa fa fa fa fa fa 00 01 fa fa fa fa fa fa
>
> ^
> ffffffff88000080: 00 00 00 07 fa fa fa fa 00 04 fa fa fa fa fa fa
> ffffffff88000100: 05 fa fa fa fa fa fa fa 00 00 00 00 05 fa fa fa
> ==================================================================
>
>
> ---
> This bug is generated by a bot. It may contain errors.
> See https://goo.gl/tpsmEJ for more information about syzbot.
> syzbot engineers can be reached at syzkaller@googlegroups.com.
>
> syzbot will keep track of this bug report. See:
> https://goo.gl/tpsmEJ#bug-status-tracking for how to communicate with
> syzbot.
>
> --
> You received this message because you are subscribed to the Google Groups
> "syzkaller-bugs" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to syzkaller-bugs+unsubscribe@googlegroups.com.
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/syzkaller-bugs/000000000000a7487d0576c18693%40google.com.
> For more options, visit https://groups.google.com/d/optout.
^ permalink raw reply
* [PATCH 1/2] net-ipv4: remove 2 always zero parameters from ipv4_update_pmtu()
From: Maciej Żenczykowski @ 2018-09-26 3:56 UTC (permalink / raw)
To: Maciej Żenczykowski, David S . Miller, Eric Dumazet
Cc: netdev, David Ahern
From: Maciej Żenczykowski <maze@google.com>
(the parameters in question are mark and flow_flags)
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
---
include/net/route.h | 2 +-
net/ipv4/ah4.c | 2 +-
net/ipv4/esp4.c | 2 +-
net/ipv4/icmp.c | 2 +-
net/ipv4/ip_gre.c | 2 +-
net/ipv4/ip_vti.c | 2 +-
net/ipv4/ipcomp.c | 2 +-
net/ipv4/ipip.c | 3 +--
net/ipv4/route.c | 8 +++-----
net/ipv6/sit.c | 2 +-
net/netfilter/ipvs/ip_vs_core.c | 3 +--
net/xfrm/xfrm_interface.c | 2 +-
12 files changed, 14 insertions(+), 18 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index bb53cdba38dc..73c605bdd6d8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -201,7 +201,7 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,
- u32 mark, u8 protocol, int flow_flags);
+ u8 protocol);
void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
u8 protocol, int flow_flags);
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 4dd95cdd8070..8811fe30282a 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -461,7 +461,7 @@ static int ah4_err(struct sk_buff *skb, u32 info)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
+ ipv4_update_pmtu(skb, net, info, 0, IPPROTO_AH);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
xfrm_state_put(x);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 97689012b357..2d0274441923 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -820,7 +820,7 @@ static int esp4_err(struct sk_buff *skb, u32 info)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
+ ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ESP);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
xfrm_state_put(x);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 695979b7ef6d..8013b37b598f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1098,7 +1098,7 @@ void icmp_err(struct sk_buff *skb, u32 info)
}
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0);
+ ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP);
else if (type == ICMP_REDIRECT)
ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0);
}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c3385a84f8ff..83b80fafd8f2 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -239,7 +239,7 @@ static void gre_err(struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- skb->dev->ifindex, 0, IPPROTO_GRE, 0);
+ skb->dev->ifindex, IPPROTO_GRE);
return;
}
if (type == ICMP_REDIRECT) {
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index f38cb21d773d..1b5571cb3282 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -318,7 +318,7 @@ static int vti4_err(struct sk_buff *skb, u32 info)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
+ ipv4_update_pmtu(skb, net, info, 0, protocol);
else
ipv4_redirect(skb, net, 0, 0, protocol, 0);
xfrm_state_put(x);
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index d97f4f2787f5..04049d1330a2 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -48,7 +48,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info)
return 0;
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
+ ipv4_update_pmtu(skb, net, info, 0, IPPROTO_COMP);
else
ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
xfrm_state_put(x);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index c891235b4966..6ff008e5818d 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -175,8 +175,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
}
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
- ipv4_update_pmtu(skb, net, info, t->parms.link, 0,
- iph->protocol, 0);
+ ipv4_update_pmtu(skb, net, info, t->parms.link, iph->protocol);
goto out;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b678466da451..7bbe3fc80b90 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1040,17 +1040,15 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
- int oif, u32 mark, u8 protocol, int flow_flags)
+ int oif, u8 protocol)
{
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
-
- if (!mark)
- mark = IP4_REPLY_MARK(net, skb->mark);
+ u32 mark = IP4_REPLY_MARK(net, skb->mark);
__build_flow_key(net, &fl4, NULL, iph, oif,
- RT_TOS(iph->tos), protocol, mark, flow_flags);
+ RT_TOS(iph->tos), protocol, mark, 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_rt_update_pmtu(rt, &fl4, mtu);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e9400ffa7875..085c588ebfe0 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -534,7 +534,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->parms.link, 0, iph->protocol, 0);
+ t->parms.link, iph->protocol);
err = 0;
goto out;
}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 7ca926a03b81..fe9abf3cc10a 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1686,8 +1686,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
skb_reset_network_header(skb);
IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
- ipv4_update_pmtu(skb, ipvs->net,
- mtu, 0, 0, 0, 0);
+ ipv4_update_pmtu(skb, ipvs->net, mtu, 0, 0);
/* Client uses PMTUD? */
if (!(frag_off & htons(IP_DF)))
goto ignore_ipip;
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 31acc6f33d98..16bc5ecb7869 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -469,7 +469,7 @@ static int xfrmi4_err(struct sk_buff *skb, u32 info)
}
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
- ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
+ ipv4_update_pmtu(skb, net, info, 0, protocol);
else
ipv4_redirect(skb, net, 0, 0, protocol, 0);
xfrm_state_put(x);
--
2.19.0.605.g01d371f741-goog
^ permalink raw reply related
* [PATCH 2/2] net-ipv4: remove 2 always zero parameters from ipv4_redirect()
From: Maciej Żenczykowski @ 2018-09-26 3:56 UTC (permalink / raw)
To: Maciej Żenczykowski, David S . Miller, Eric Dumazet
Cc: netdev, David Ahern
In-Reply-To: <20180926035627.221286-1-zenczykowski@gmail.com>
From: Maciej Żenczykowski <maze@google.com>
(the parameters in question are mark and flow_flags)
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
---
include/net/route.h | 3 +--
net/ipv4/ah4.c | 2 +-
net/ipv4/esp4.c | 2 +-
net/ipv4/icmp.c | 2 +-
net/ipv4/ip_gre.c | 4 ++--
net/ipv4/ip_vti.c | 2 +-
net/ipv4/ipcomp.c | 2 +-
net/ipv4/ipip.c | 2 +-
net/ipv4/route.c | 4 ++--
net/ipv6/sit.c | 4 ++--
net/xfrm/xfrm_interface.c | 2 +-
11 files changed, 14 insertions(+), 15 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 73c605bdd6d8..9883dc82f723 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -203,8 +203,7 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,
u8 protocol);
void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
-void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
- u8 protocol, int flow_flags);
+void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol);
void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk);
void ip_rt_send_redirect(struct sk_buff *skb);
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 8811fe30282a..c01fa791260d 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -463,7 +463,7 @@ static int ah4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_AH);
else
- ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
+ ipv4_redirect(skb, net, 0, IPPROTO_AH);
xfrm_state_put(x);
return 0;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 2d0274441923..071533dd33c2 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -822,7 +822,7 @@ static int esp4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ESP);
else
- ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
+ ipv4_redirect(skb, net, 0, IPPROTO_ESP);
xfrm_state_put(x);
return 0;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 8013b37b598f..d832beed6e3a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1100,7 +1100,7 @@ void icmp_err(struct sk_buff *skb, u32 info)
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP);
else if (type == ICMP_REDIRECT)
- ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0);
+ ipv4_redirect(skb, net, 0, IPPROTO_ICMP);
}
/*
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 83b80fafd8f2..38befe829caf 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -243,8 +243,8 @@ static void gre_err(struct sk_buff *skb, u32 info)
return;
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0,
- IPPROTO_GRE, 0);
+ ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex,
+ IPPROTO_GRE);
return;
}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1b5571cb3282..de31b302d69c 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -320,7 +320,7 @@ static int vti4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, protocol);
else
- ipv4_redirect(skb, net, 0, 0, protocol, 0);
+ ipv4_redirect(skb, net, 0, protocol);
xfrm_state_put(x);
return 0;
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 04049d1330a2..9119d012ba46 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -50,7 +50,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_COMP);
else
- ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
+ ipv4_redirect(skb, net, 0, IPPROTO_COMP);
xfrm_state_put(x);
return 0;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 6ff008e5818d..e65287c27e3d 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -180,7 +180,7 @@ static int ipip_err(struct sk_buff *skb, u32 info)
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, net, t->parms.link, 0, iph->protocol, 0);
+ ipv4_redirect(skb, net, t->parms.link, iph->protocol);
goto out;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7bbe3fc80b90..dce2ed66ebe1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1130,14 +1130,14 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
void ipv4_redirect(struct sk_buff *skb, struct net *net,
- int oif, u32 mark, u8 protocol, int flow_flags)
+ int oif, u8 protocol)
{
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
__build_flow_key(net, &fl4, NULL, iph, oif,
- RT_TOS(iph->tos), protocol, mark, flow_flags);
+ RT_TOS(iph->tos), protocol, 0, 0);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 085c588ebfe0..51c9f75f34b9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -539,8 +539,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
goto out;
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
- iph->protocol, 0);
+ ipv4_redirect(skb, dev_net(skb->dev), t->parms.link,
+ iph->protocol);
err = 0;
goto out;
}
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 16bc5ecb7869..4b4ef4f662d9 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -471,7 +471,7 @@ static int xfrmi4_err(struct sk_buff *skb, u32 info)
if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, protocol);
else
- ipv4_redirect(skb, net, 0, 0, protocol, 0);
+ ipv4_redirect(skb, net, 0, protocol);
xfrm_state_put(x);
return 0;
--
2.19.0.605.g01d371f741-goog
^ 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