[PATCH net-next v11 08/13] net: support non paged skb frags

From: Mina Almasry
Date: Thu Jun 06 2024 - 20:56:22 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>


---

v10:
- Fixed newly generated kdoc warnings found by patchwork. While we're
at it, fix the Return section of the functions I touched.

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 | 42 +++++++++++++++++++++++++++++++++++++-
include/linux/skbuff_ref.h | 9 ++++----
net/core/dev.c | 3 ++-
net/core/gro.c | 3 ++-
net/core/skbuff.c | 11 ++++++++++
net/ipv4/esp4.c | 3 ++-
net/ipv4/tcp.c | 3 +++
net/ipv6/esp6.c | 3 ++-
8 files changed, 67 insertions(+), 10 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fe7d8dbef77e1..0a4df0025e6dc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3492,21 +3492,58 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto,
fragto->offset = fragfrom->offset;
}

+/* Return: 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
+ *
+ * Return: 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.
+ * Return: 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
+ *
+ * Return: the &netmem_ref associated with @frag.
+ */
+static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag)
+{
+ return frag->netmem;
+}
+
int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
unsigned int headroom);
int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
struct bpf_prog *prog);
+
/**
* skb_frag_address - gets the address of the data contained in a paged fragment
* @frag: the paged fragment buffer
@@ -3516,6 +3553,9 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
*/
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/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h
index 16c241a234728..0f3c58007488a 100644
--- a/include/linux/skbuff_ref.h
+++ b/include/linux/skbuff_ref.h
@@ -34,14 +34,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)

bool napi_pp_put_page(netmem_ref netmem);

-static inline void
-skb_page_unref(struct page *page, bool recycle)
+static inline void skb_page_unref(netmem_ref netmem, bool recycle)
{
#ifdef CONFIG_PAGE_POOL
- if (recycle && napi_pp_put_page(page_to_netmem(page)))
+ if (recycle && napi_pp_put_page(netmem))
return;
#endif
- put_page(page);
+ put_page(netmem_to_page(netmem));
}

/**
@@ -54,7 +53,7 @@ skb_page_unref(struct page *page, bool recycle)
*/
static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle)
{
- skb_page_unref(skb_frag_page(frag), recycle);
+ skb_page_unref(skb_frag_netmem(frag), recycle);
}

/**
diff --git a/net/core/dev.c b/net/core/dev.c
index 25faa1fd64fc1..9fd81cf68350f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3432,8 +3432,9 @@ 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 b3b43de1a6502..26f09c3e830b7 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -408,7 +408,8 @@ 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 5aaaa796c5fb4..a0cd848a18dfa 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1352,6 +1352,14 @@ 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 -= skb_frag_size(frag);
+ 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 3968d3f98e083..4ce0bc41e7806 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -115,7 +115,8 @@ 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(sg_page(sg), skb->pp_recycle);
+ skb_page_unref(page_to_netmem(sg_page(sg)),
+ skb->pp_recycle);
}

#ifdef CONFIG_INET_ESPINTCP
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6553221694ec2..5395f0e22c65f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2176,6 +2176,9 @@ 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 34a9a5b9ed00b..0318aea0d4ce6 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -132,7 +132,8 @@ 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(sg_page(sg), skb->pp_recycle);
+ skb_page_unref(page_to_netmem(sg_page(sg)),
+ skb->pp_recycle);
}

#ifdef CONFIG_INET6_ESPINTCP
--
2.45.2.505.gda0bf45e8d-goog