Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Kees Cook <keescook@chromium.org>
To:     "David S. Miller" <davem@davemloft.net>
Cc:     Kees Cook <keescook@chromium.org>,
        Eric Dumazet <edumazet@google.com>,
        Jakub Kicinski <kuba@kernel.org>,
        Paolo Abeni <pabeni@redhat.com>, netdev@vger.kernel.org,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Nick Desaulniers <ndesaulniers@google.com>,
        David Rientjes <rientjes@google.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Pavel Begunkov <asml.silence@gmail.com>,
        Menglong Dong <imagedong@tencent.com>,
        linux-kernel@vger.kernel.org, linux-hardening@vger.kernel.org
Subject: [PATCH v3][next] skbuff: Proactively round up to kmalloc bucket size
Date:   Tue, 18 Oct 2022 02:33:36 -0700
Message-Id: <20221018093005.give.246-kees@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Instead of discovering the kmalloc bucket size _after_ allocation, round
up proactively so the allocation is explicitly made for the full size,
allowing the compiler to correctly reason about the resulting size of
the buffer through the existing __alloc_size() hint.

This will allow for kernels built with CONFIG_UBSAN_BOUNDS or the
coming dynamic bounds checking under CONFIG_FORTIFY_SOURCE to gain
back the __alloc_size() hints that were temporarily reverted in commit
93dd04ab0b2b ("slab: remove __alloc_size attribute from __kmalloc_track_caller")

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: netdev@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
v3: refactor again to pass allocation size more cleanly to callers
v2: https://lore.kernel.org/lkml/20220923202822.2667581-4-keescook@chromium.org/
---
 net/core/skbuff.c | 41 ++++++++++++++++++++++-------------------
 1 file changed, 22 insertions(+), 19 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1d9719e72f9d..3ea1032d03ec 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -425,11 +425,12 @@ EXPORT_SYMBOL(napi_build_skb);
  * memory is free
  */
 static void *kmalloc_reserve(size_t size, gfp_t flags, int node,
-			     bool *pfmemalloc)
+			     bool *pfmemalloc, size_t *alloc_size)
 {
 	void *obj;
 	bool ret_pfmemalloc = false;
 
+	size = kmalloc_size_roundup(size);
 	/*
 	 * Try a regular allocation, when that fails and we're not entitled
 	 * to the reserves, fail.
@@ -448,6 +449,7 @@ static void *kmalloc_reserve(size_t size, gfp_t flags, int node,
 	if (pfmemalloc)
 		*pfmemalloc = ret_pfmemalloc;
 
+	*alloc_size = size;
 	return obj;
 }
 
@@ -479,7 +481,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 {
 	struct kmem_cache *cache;
 	struct sk_buff *skb;
-	unsigned int osize;
+	size_t alloc_size;
 	bool pfmemalloc;
 	u8 *data;
 
@@ -506,15 +508,15 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	 */
 	size = SKB_DATA_ALIGN(size);
 	size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
-	if (unlikely(!data))
-		goto nodata;
-	/* kmalloc(size) might give us more room than requested.
+	/* kmalloc(size) might give us more room than requested, so
+	 * allocate the true bucket size up front.
 	 * Put skb_shared_info exactly at the end of allocated zone,
 	 * to allow max possible filling before reallocation.
 	 */
-	osize = ksize(data);
-	size = SKB_WITH_OVERHEAD(osize);
+	data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc, &alloc_size);
+	if (unlikely(!data))
+		goto nodata;
+	size = SKB_WITH_OVERHEAD(alloc_size);
 	prefetchw(data + size);
 
 	/*
@@ -523,7 +525,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	 * the tail pointer in struct sk_buff!
 	 */
 	memset(skb, 0, offsetof(struct sk_buff, tail));
-	__build_skb_around(skb, data, osize);
+	__build_skb_around(skb, data, alloc_size);
 	skb->pfmemalloc = pfmemalloc;
 
 	if (flags & SKB_ALLOC_FCLONE) {
@@ -1816,6 +1818,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 {
 	int i, osize = skb_end_offset(skb);
 	int size = osize + nhead + ntail;
+	size_t alloc_size;
 	long off;
 	u8 *data;
 
@@ -1830,10 +1833,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 	if (skb_pfmemalloc(skb))
 		gfp_mask |= __GFP_MEMALLOC;
 	data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
-			       gfp_mask, NUMA_NO_NODE, NULL);
+			       gfp_mask, NUMA_NO_NODE, NULL, &alloc_size);
 	if (!data)
 		goto nodata;
-	size = SKB_WITH_OVERHEAD(ksize(data));
+	size = SKB_WITH_OVERHEAD(alloc_size);
 
 	/* Copy only real data... and, alas, header. This should be
 	 * optimized for the cases when header is void.
@@ -6169,19 +6172,19 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off,
 	int i;
 	int size = skb_end_offset(skb);
 	int new_hlen = headlen - off;
+	size_t alloc_size;
 	u8 *data;
 
 	size = SKB_DATA_ALIGN(size);
 
 	if (skb_pfmemalloc(skb))
 		gfp_mask |= __GFP_MEMALLOC;
-	data = kmalloc_reserve(size +
-			       SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
-			       gfp_mask, NUMA_NO_NODE, NULL);
+	data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+			       gfp_mask, NUMA_NO_NODE, NULL, &alloc_size);
 	if (!data)
 		return -ENOMEM;
 
-	size = SKB_WITH_OVERHEAD(ksize(data));
+	size = SKB_WITH_OVERHEAD(alloc_size);
 
 	/* Copy real data, and all frags */
 	skb_copy_from_linear_data_offset(skb, off, data, new_hlen);
@@ -6290,18 +6293,18 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
 	u8 *data;
 	const int nfrags = skb_shinfo(skb)->nr_frags;
 	struct skb_shared_info *shinfo;
+	size_t alloc_size;
 
 	size = SKB_DATA_ALIGN(size);
 
 	if (skb_pfmemalloc(skb))
 		gfp_mask |= __GFP_MEMALLOC;
-	data = kmalloc_reserve(size +
-			       SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
-			       gfp_mask, NUMA_NO_NODE, NULL);
+	data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+			       gfp_mask, NUMA_NO_NODE, NULL, &alloc_size);
 	if (!data)
 		return -ENOMEM;
 
-	size = SKB_WITH_OVERHEAD(ksize(data));
+	size = SKB_WITH_OVERHEAD(alloc_size);
 
 	memcpy((struct skb_shared_info *)(data + size),
 	       skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0]));
-- 
2.34.1