From 7c90584c66cc4b033a3b684b0e0950f79e7b7166 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 23 Sep 2017 12:39:12 -0700
Subject: net: speed up skb_rbtree_purge()
As measured in my prior patch ("sch_netem: faster rb tree removal"),
rbtree_postorder_for_each_entry_safe() is nice looking but much slower
than using rb_next() directly, except when tree is small enough
to fit in CPU caches (then the cost is the same)
Also note that there is not even an increase of text size :
$ size net/core/skbuff.o.before net/core/skbuff.o
text data bss dec hex filename
40711 1298 0 42009 a419 net/core/skbuff.o.before
40711 1298 0 42009 a419 net/core/skbuff.o
From: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/skbuff.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
(limited to 'net/core/skbuff.c')
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 16982de..000ce73 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2848,12 +2848,15 @@ EXPORT_SYMBOL(skb_queue_purge);
*/
void skb_rbtree_purge(struct rb_root *root)
{
- struct sk_buff *skb, *next;
+ struct rb_node *p = rb_first(root);
- rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode)
- kfree_skb(skb);
+ while (p) {
+ struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
- *root = RB_ROOT;
+ p = rb_next(p);
+ rb_erase(&skb->rbnode, root);
+ kfree_skb(skb);
+ }
}
/**
--
cgit v1.1
From de8f3a83b0a0fddb2cf56e7a718127e9619ea3da Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 25 Sep 2017 02:25:51 +0200
Subject: bpf: add meta pointer for direct access
This work enables generic transfer of metadata from XDP into skb. The
basic idea is that we can make use of the fact that the resulting skb
must be linear and already comes with a larger headroom for supporting
bpf_xdp_adjust_head(), which mangles xdp->data. Here, we base our work
on a similar principle and introduce a small helper bpf_xdp_adjust_meta()
for adjusting a new pointer called xdp->data_meta. Thus, the packet has
a flexible and programmable room for meta data, followed by the actual
packet data. struct xdp_buff is therefore laid out that we first point
to data_hard_start, then data_meta directly prepended to data followed
by data_end marking the end of packet. bpf_xdp_adjust_head() takes into
account whether we have meta data already prepended and if so, memmove()s
this along with the given offset provided there's enough room.
xdp->data_meta is optional and programs are not required to use it. The
rationale is that when we process the packet in XDP (e.g. as DoS filter),
we can push further meta data along with it for the XDP_PASS case, and
give the guarantee that a clsact ingress BPF program on the same device
can pick this up for further post-processing. Since we work with skb
there, we can also set skb->mark, skb->priority or other skb meta data
out of BPF, thus having this scratch space generic and programmable
allows for more flexibility than defining a direct 1:1 transfer of
potentially new XDP members into skb (it's also more efficient as we
don't need to initialize/handle each of such new members). The facility
also works together with GRO aggregation. The scratch space at the head
of the packet can be multiple of 4 byte up to 32 byte large. Drivers not
yet supporting xdp->data_meta can simply be set up with xdp->data_meta
as xdp->data + 1 as bpf_xdp_adjust_meta() will detect this and bail out,
such that the subsequent match against xdp->data for later access is
guaranteed to fail.
The verifier treats xdp->data_meta/xdp->data the same way as we treat
xdp->data/xdp->data_end pointer comparisons. The requirement for doing
the compare against xdp->data is that it hasn't been modified from it's
original address we got from ctx access. It may have a range marking
already from prior successful xdp->data/xdp->data_end pointer comparisons
though.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/skbuff.c | 2 ++
1 file changed, 2 insertions(+)
(limited to 'net/core/skbuff.c')
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 000ce73..d98c2e3 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1509,6 +1509,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
skb->nohdr = 0;
atomic_set(&skb_shinfo(skb)->dataref, 1);
+ skb_metadata_clear(skb);
+
/* It is not generally safe to change skb->truesize.
* For the moment, we really care of rx path, or
* when skb is orphaned (not attached to a socket).
--
cgit v1.1
From c818fa9e288be5be7e360c33cf4f5e30f9fa206e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Oct 2017 10:48:35 -0700
Subject: net: cache skb_shinfo() in skb_try_coalesce()
Compiler does not really know that skb_shinfo(to|from) are constants
in skb_try_coalesce(), lets cache their values to shrink code.
We might even take care of skb_zcopy() calls later.
$ size net/core/skbuff.o.before net/core/skbuff.o
text data bss dec hex filename
40727 1298 0 42025 a429 net/core/skbuff.o.before
40631 1298 0 41929 a3c9 net/core/skbuff.o
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/skbuff.c | 29 ++++++++++++++++-------------
1 file changed, 16 insertions(+), 13 deletions(-)
(limited to 'net/core/skbuff.c')
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d98c2e3..822a90e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4767,6 +4767,7 @@ EXPORT_SYMBOL(kfree_skb_partial);
bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
bool *fragstolen, int *delta_truesize)
{
+ struct skb_shared_info *to_shinfo, *from_shinfo;
int i, delta, len = from->len;
*fragstolen = false;
@@ -4781,7 +4782,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
return true;
}
- if (skb_has_frag_list(to) || skb_has_frag_list(from))
+ to_shinfo = skb_shinfo(to);
+ from_shinfo = skb_shinfo(from);
+ if (to_shinfo->frag_list || from_shinfo->frag_list)
return false;
if (skb_zcopy(to) || skb_zcopy(from))
return false;
@@ -4790,8 +4793,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
struct page *page;
unsigned int offset;
- if (skb_shinfo(to)->nr_frags +
- skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ if (to_shinfo->nr_frags +
+ from_shinfo->nr_frags >= MAX_SKB_FRAGS)
return false;
if (skb_head_is_locked(from))
@@ -4802,12 +4805,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
page = virt_to_head_page(from->head);
offset = from->data - (unsigned char *)page_address(page);
- skb_fill_page_desc(to, skb_shinfo(to)->nr_frags,
+ skb_fill_page_desc(to, to_shinfo->nr_frags,
page, offset, skb_headlen(from));
*fragstolen = true;
} else {
- if (skb_shinfo(to)->nr_frags +
- skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS)
+ if (to_shinfo->nr_frags +
+ from_shinfo->nr_frags > MAX_SKB_FRAGS)
return false;
delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from));
@@ -4815,19 +4818,19 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
WARN_ON_ONCE(delta < len);
- memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags,
- skb_shinfo(from)->frags,
- skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
- skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
+ memcpy(to_shinfo->frags + to_shinfo->nr_frags,
+ from_shinfo->frags,
+ from_shinfo->nr_frags * sizeof(skb_frag_t));
+ to_shinfo->nr_frags += from_shinfo->nr_frags;
if (!skb_cloned(from))
- skb_shinfo(from)->nr_frags = 0;
+ from_shinfo->nr_frags = 0;
/* if the skb is not cloned this does nothing
* since we set nr_frags to 0.
*/
- for (i = 0; i < skb_shinfo(from)->nr_frags; i++)
- skb_frag_ref(from, i);
+ for (i = 0; i < from_shinfo->nr_frags; i++)
+ __skb_frag_ref(&from_shinfo->frags[i]);
to->truesize += delta;
to->len += len;
--
cgit v1.1
From 9f77fad3c2e3b923984fc617ea45b60264115fc3 Mon Sep 17 00:00:00 2001
From: Tim Hansen <devtimhansen@gmail.com>
Date: Mon, 9 Oct 2017 11:37:59 -0400
Subject: net/core: Fix BUG to BUG_ON conditionals.
Fix BUG() calls to use BUG_ON(conditional) macros.
This was found using make coccicheck M=net/core on linux next
tag next-2017092
Signed-off-by: Tim Hansen <devtimhansen@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/skbuff.c | 15 ++++++---------
1 file changed, 6 insertions(+), 9 deletions(-)
(limited to 'net/core/skbuff.c')
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 822a90e..4071750 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1350,8 +1350,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
/* Set the tail pointer and length */
skb_put(n, skb->len);
- if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len))
- BUG();
+ BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
copy_skb_header(n, skb);
return n;
@@ -1449,8 +1448,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
BUG_ON(nhead < 0);
- if (skb_shared(skb))
- BUG();
+ BUG_ON(skb_shared(skb));
size = SKB_DATA_ALIGN(size);
@@ -1595,9 +1593,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
head_copy_off = newheadroom - head_copy_len;
/* Copy the linear header and data. */
- if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
- skb->len + head_copy_len))
- BUG();
+ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
+ skb->len + head_copy_len));
copy_skb_header(n, skb);
@@ -1878,8 +1875,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
return NULL;
}
- if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta))
- BUG();
+ BUG_ON(skb_copy_bits(skb, skb_headlen(skb),
+ skb_tail_pointer(skb), delta));
/* Optimization: no fragments, no reasons to preestimate
* size of pulled pages. Superb.
--
cgit v1.1