[RFC PATCH net-next v7 09/14] net: support non paged skb frags

From: Mina Almasry
Date: Tue Mar 26 2024 - 18:54:54 EST


Make skb_frag_page() fail in the case where the frag is not backed
by a page, and fix its relevant callers to handle this case.

Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>


---

v6:
- Rebased on top of the merged netmem changes.

Changes in v1:
- Fix illegal_highdma() (Yunsheng).
- Rework napi_pp_put_page() slightly to reduce code churn (Willem).

---
include/linux/skbuff.h | 53 +++++++++++++++++++++++++++++++++++-------
net/core/dev.c | 3 ++-
net/core/gro.c | 3 ++-
net/core/skbuff.c | 11 +++++++++
net/ipv4/esp4.c | 2 +-
net/ipv4/tcp.c | 3 +++
net/ipv6/esp6.c | 2 +-
7 files changed, 65 insertions(+), 12 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 78659c8efa4e..8143aee8d911 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3483,17 +3483,53 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto,
fragto->offset = fragfrom->offset;
}

+/* Returns true if the skb_frag contains a net_iov. */
+static inline bool skb_frag_is_net_iov(const skb_frag_t *frag)
+{
+ return netmem_is_net_iov(frag->netmem);
+}
+
+/**
+ * skb_frag_net_iov - retrieve the net_iov referred to by fragment
+ * @frag: the fragment
+ *
+ * Returns the &struct net_iov associated with @frag. Returns NULL if this
+ * frag has no associated net_iov.
+ */
+static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag)
+{
+ if (!skb_frag_is_net_iov(frag))
+ return NULL;
+
+ return netmem_to_net_iov(frag->netmem);
+}
+
/**
* skb_frag_page - retrieve the page referred to by a paged fragment
* @frag: the paged fragment
*
- * Returns the &struct page associated with @frag.
+ * Returns the &struct page associated with @frag. Returns NULL if this frag
+ * has no associated page.
*/
static inline struct page *skb_frag_page(const skb_frag_t *frag)
{
+ if (skb_frag_is_net_iov(frag))
+ return NULL;
+
return netmem_to_page(frag->netmem);
}

+/**
+ * skb_frag_netmem - retrieve the netmem referred to by a fragment
+ * @frag: the fragment
+ *
+ * Returns the &netmem_ref associated with @frag.
+ */
+static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag)
+{
+ return frag->netmem;
+}
+
/**
* __skb_frag_ref - take an addition reference on a paged fragment.
* @frag: the paged fragment
@@ -3524,25 +3560,23 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
bool napi_pp_put_page(netmem_ref netmem, bool napi_safe);

static inline void
-skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe)
+skb_page_unref(const struct sk_buff *skb, netmem_ref netmem, bool napi_safe)
{
#ifdef CONFIG_PAGE_POOL
- if (skb->pp_recycle && napi_pp_put_page(page, napi_safe))
+ if (skb->pp_recycle && napi_pp_put_page(netmem, napi_safe))
return;
#endif
- put_page(page);
+ put_page(netmem_to_page(netmem));
}

static inline void
napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe)
{
- struct page *page = skb_frag_page(frag);
-
#ifdef CONFIG_PAGE_POOL
- if (recycle && napi_pp_put_page(page_to_netmem(page), napi_safe))
+ if (recycle && napi_pp_put_page(skb_frag_netmem(frag), napi_safe))
return;
#endif
- put_page(page);
+ put_page(skb_frag_page(frag));
}

/**
@@ -3582,6 +3616,9 @@ static inline void skb_frag_unref(struct sk_buff *skb, int f)
*/
static inline void *skb_frag_address(const skb_frag_t *frag)
{
+ if (!skb_frag_page(frag))
+ return NULL;
+
return page_address(skb_frag_page(frag)) + skb_frag_off(frag);
}

diff --git a/net/core/dev.c b/net/core/dev.c
index e10610698a0a..8228432cb600 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3411,8 +3411,9 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
if (!(dev->features & NETIF_F_HIGHDMA)) {
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ struct page *page = skb_frag_page(frag);

- if (PageHighMem(skb_frag_page(frag)))
+ if (page && PageHighMem(page))
return 1;
}
}
diff --git a/net/core/gro.c b/net/core/gro.c
index ee30d4f0c038..eef20c82c5c3 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -380,7 +380,8 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff)
pinfo = skb_shinfo(skb);
frag0 = &pinfo->frags[0];

- if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) &&
+ if (pinfo->nr_frags && skb_frag_page(frag0) &&
+ !PageHighMem(skb_frag_page(frag0)) &&
(!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b7e974f0ae51..b4ea842ac9c7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1375,6 +1375,14 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
struct page *p;
u8 *vaddr;

+ if (skb_frag_is_net_iov(frag)) {
+ printk("%sskb frag %d: not readable\n", level, i);
+ len -= frag->bv_len;
+ if (!len)
+ break;
+ continue;
+ }
+
skb_frag_foreach_page(frag, skb_frag_off(frag),
skb_frag_size(frag), p, p_off, p_len,
copied) {
@@ -3142,6 +3150,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];

+ if (WARN_ON_ONCE(!skb_frag_page(f)))
+ return false;
+
if (__splice_segment(skb_frag_page(f),
skb_frag_off(f), skb_frag_size(f),
offset, len, spd, false, sk, pipe))
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index d33d12421814..3b2a6a033efa 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
*/
if (req->src != req->dst)
for (sg = sg_next(req->src); sg; sg = sg_next(sg))
- skb_page_unref(skb, sg_page(sg), false);
+ skb_page_unref(skb, page_to_netmem(sg_page(sg)), false);
}

#ifdef CONFIG_INET_ESPINTCP
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d20b62d52171..9f6497c53d61 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2167,6 +2167,9 @@ static int tcp_zerocopy_receive(struct sock *sk,
break;
}
page = skb_frag_page(frags);
+ if (WARN_ON_ONCE(!page))
+ break;
+
prefetchw(page);
pages[pages_to_map++] = page;
length += PAGE_SIZE;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 7371886d4f9f..342c07f0c6c4 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -131,7 +131,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
*/
if (req->src != req->dst)
for (sg = sg_next(req->src); sg; sg = sg_next(sg))
- skb_page_unref(skb, sg_page(sg), false);
+ skb_page_unref(skb, page_to_netmem(sg_page(sg)), false);
}

#ifdef CONFIG_INET6_ESPINTCP
--
2.44.0.396.g6e790dbe36-goog