diff mbox

[RFC,1/7] net: add support for per-paged-fragment destructors

Message ID 1359124027-1170-2-git-send-email-alex@alex.org.uk
State RFC, archived
Delegated to: David Miller
Headers show

Commit Message

Alex Bligh Jan. 25, 2013, 2:27 p.m. UTC 
From: Mel Gorman <mgorman@suse.de>

Entities which care about the complete lifecycle of pages which they inject
into the network stack via an skb paged fragment can choose to set this
destructor in order to receive a callback when the stack is really finished
with a page (including all clones, retransmits, pull-ups etc etc).

This destructor will always be propagated alongside the struct page when
copying skb_frag_t->page. This is the reason I chose to embed the destructor in
a "struct { } page" within the skb_frag_t, rather than as a separate field,
since it allows existing code which propagates ->frags[N].page to Just
Work(tm).

When the destructor is present the page reference counting is done slightly
differently. No references are held by the network stack on the struct page (it
is up to the caller to manage this as necessary) instead the network stack will
track references via the count embedded in the destructor structure. When this
reference count reaches zero then the destructor will be called and the caller
can take the necesary steps to release the page (i.e. release the struct page
reference itself).

The intention is that callers can use this callback to delay completion to
_their_ callers until the network stack has completely released the page, in
order to prevent use-after-free or modification of data pages which are still
in use by the stack.

It is allowable (indeed expected) for a caller to share a single destructor
instance between multiple pages injected into the stack e.g. a group of pages
included in a single higher level operation might share a destructor which is
used to complete that higher level operation.

NB: a small number of drivers use skb_frag_t independently of struct sk_buff so
this patch is slightly larger than necessary. I did consider leaving skb_frag_t
alone and defining a new (but similar) structure to be used in the struct
sk_buff itself. This would also have the advantage of more clearly separating
the two uses, which is useful since there are now special reference counting
accessors for skb_frag_t within a struct sk_buff but not (necessarily) for
those used outside of an skb.

Signed-off-by: Ian Campbell <ian.campbell <at> citrix.com>
Cc: "David S. Miller" <davem <at> davemloft.net>
Cc: "James E.J. Bottomley" <JBottomley <at> parallels.com>
Cc: Dimitris Michailidis <dm <at> chelsio.com>
Cc: Casey Leedom <leedom <at> chelsio.com>
Cc: Yevgeny Petrilin <yevgenyp <at> mellanox.co.il>
Cc: Eric Dumazet <eric.dumazet <at> gmail.com>
Cc: "Michał Mirosław" <mirq-linux <at> rere.qmqm.pl>
Cc: netdev <at> vger.kernel.org
Cc: linux-scsi <at> vger.kernel.org
Signed-off-by: Alex Bligh <alex@alex.org.uk>
---
 include/linux/skbuff.h |   44 ++++++++++++++++++++++++++++++++++++++++++++
 net/core/skbuff.c      |   17 +++++++++++++++++
 2 files changed, 61 insertions(+)
diff mbox

Patch

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fe86488..2619a61 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -139,9 +139,16 @@  struct sk_buff;
 
 typedef struct skb_frag_struct skb_frag_t;
 
+struct skb_frag_destructor {
+	atomic_t ref;
+	int (*destroy)(void *data);
+	void *data;
+};
+
 struct skb_frag_struct {
 	struct {
 		struct page *p;
+		struct skb_frag_destructor *destructor;
 	} page;
 #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
 	__u32 page_offset;
@@ -1160,6 +1167,31 @@  static inline int skb_pagelen(const struct sk_buff *skb)
 }
 
 /**
+ * skb_frag_set_destructor - set destructor for a paged fragment
+ * @skb: buffer containing fragment to be initialised
+ * @i: paged fragment index to initialise
+ * @destroy: the destructor to use for this fragment
+ *
+ * Sets @destroy as the destructor to be called when all references to
+ * the frag @i in @skb (tracked over skb_clone, retransmit, pull-ups,
+ * etc) are released.
+ *
+ * When a destructor is set then reference counting is performed on
+ * @destroy->ref. When the ref reaches zero then @destroy->destroy
+ * will be called. The caller is responsible for holding and managing
+ * any other references (such a the struct page reference count).
+ *
+ * This function must be called before any use of skb_frag_ref() or
+ * skb_frag_unref().
+ */
+static inline void skb_frag_set_destructor(struct sk_buff *skb, int i,
+					   struct skb_frag_destructor *destroy)
+{
+	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+	frag->page.destructor = destroy;
+}
+
+/**
  * __skb_fill_page_desc - initialise a paged fragment in an skb
  * @skb: buffer containing fragment to be initialised
  * @i: paged fragment index to initialise
@@ -1178,6 +1210,7 @@  static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 	frag->page.p		  = page;
+	frag->page.destructor	  = NULL;
 	frag->page_offset	  = off;
 	skb_frag_size_set(frag, size);
 }
@@ -1704,6 +1737,9 @@  static inline struct page *skb_frag_page(const skb_frag_t *frag)
 	return frag->page.p;
 }
 
+extern void skb_frag_destructor_ref(struct skb_frag_destructor *destroy);
+extern void skb_frag_destructor_unref(struct skb_frag_destructor *destroy);
+
 /**
  * __skb_frag_ref - take an addition reference on a paged fragment.
  * @frag: the paged fragment
@@ -1712,6 +1748,10 @@  static inline struct page *skb_frag_page(const skb_frag_t *frag)
  */
 static inline void __skb_frag_ref(skb_frag_t *frag)
 {
+	if (unlikely(frag->page.destructor)) {
+		skb_frag_destructor_ref(frag->page.destructor);
+		return;
+	}
 	get_page(skb_frag_page(frag));
 }
 
@@ -1735,6 +1775,10 @@  static inline void skb_frag_ref(struct sk_buff *skb, int f)
  */
 static inline void __skb_frag_unref(skb_frag_t *frag)
 {
+	if (unlikely(frag->page.destructor)) {
+		skb_frag_destructor_unref(frag->page.destructor);
+		return;
+	}
 	put_page(skb_frag_page(frag));
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3c30ee4..8b46cad 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -303,6 +303,23 @@  struct sk_buff *dev_alloc_skb(unsigned int length)
 }
 EXPORT_SYMBOL(dev_alloc_skb);
 
+void skb_frag_destructor_ref(struct skb_frag_destructor *destroy)
+{
+	BUG_ON(destroy == NULL);
+	atomic_inc(&destroy->ref);
+}
+EXPORT_SYMBOL(skb_frag_destructor_ref);
+
+void skb_frag_destructor_unref(struct skb_frag_destructor *destroy)
+{
+	if (destroy == NULL)
+		return;
+
+	if (atomic_dec_and_test(&destroy->ref))
+		destroy->destroy(destroy->data);
+}
+EXPORT_SYMBOL(skb_frag_destructor_unref);
+
 static void skb_drop_list(struct sk_buff **listp)
 {
 	struct sk_buff *list = *listp;