Re: [PATCH v2 03/16] skbuff: Proactively round up to kmalloc bucket size

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Fri, Sep 23, 2022 at 01:28:09PM -0700, Kees Cook wrote:
> 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")
> 
> Additionally tries to normalize size variables to u32 from int. Most
> interfaces are using "int", but notably __alloc_skb uses unsigned int.
> 
> Also fix some reverse Christmas tree and comments while touching nearby
> code.

Something in this patch is breaking things -- I've refactored it again
to avoid overwriting the incoming size argument, and instead add a
dedicated outgoing size variable. Here's what will be v3 ...

---
 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 974bbbbe7138..9b5a9fb69d9d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -346,11 +346,12 @@ 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.
@@ -369,6 +370,7 @@ static void *kmalloc_reserve(size_t size, gfp_t flags, int node,
 	if (pfmemalloc)
 		*pfmemalloc = ret_pfmemalloc;
 
+	*alloc_size = size;
 	return obj;
 }
 
@@ -400,7 +402,7 @@ 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;
 
@@ -427,15 +429,15 @@ 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);
 
 	/*
@@ -444,7 +446,7 @@ 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) {
@@ -1709,6 +1711,7 @@ 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;
 
@@ -1723,10 +1726,10 @@ 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.
@@ -6063,19 +6066,19 @@ 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);
@@ -6184,18 +6187,18 @@ 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


-- 
Kees Cook



[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [NTFS 3]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [NTFS 3]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux