diff mbox series

[net-next,v3,2/2] net: bpf: add a test for skb_segment in test_bpf module

Message ID 20180320232156.3455738-3-yhs@fb.com
State Changes Requested, archived
Delegated to: David Miller
Headers show
Series net: permit skb_segment on head_frag frag_list skb | expand

Commit Message

Yonghong Song March 20, 2018, 11:21 p.m. UTC
Without the previous commit,
"modprobe test_bpf" will have the following errors:
...
[   98.149165] ------------[ cut here ]------------
[   98.159362] kernel BUG at net/core/skbuff.c:3667!
[   98.169756] invalid opcode: 0000 [#1] SMP PTI
[   98.179370] Modules linked in:
[   98.179371]  test_bpf(+)
...
which triggers the bug the previous commit intends to fix.

The skbs are constructed to mimic what mlx5 may generate.
The packet size/header may not mimic real cases in production. But
the processing flow is similar.

Signed-off-by: Yonghong Song <yhs@fb.com>
---
 lib/test_bpf.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 70 insertions(+), 1 deletion(-)

Comments

Eric Dumazet March 21, 2018, 12:44 a.m. UTC | #1
On 03/20/2018 04:21 PM, Yonghong Song wrote:
> Without the previous commit,
> "modprobe test_bpf" will have the following errors:
> ...
> [   98.149165] ------------[ cut here ]------------
> [   98.159362] kernel BUG at net/core/skbuff.c:3667!
> [   98.169756] invalid opcode: 0000 [#1] SMP PTI
> [   98.179370] Modules linked in:
> [   98.179371]  test_bpf(+)
> ...
> which triggers the bug the previous commit intends to fix.
> 
> The skbs are constructed to mimic what mlx5 may generate.
> The packet size/header may not mimic real cases in production. But
> the processing flow is similar.
> 
> Signed-off-by: Yonghong Song <yhs@fb.com>
> ---
>  lib/test_bpf.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 70 insertions(+), 1 deletion(-)
> 
> diff --git a/lib/test_bpf.c b/lib/test_bpf.c
> index 2efb213..045d7d3 100644
> --- a/lib/test_bpf.c
> +++ b/lib/test_bpf.c
> @@ -6574,6 +6574,72 @@ static bool exclude_test(int test_id)
>  	return test_id < test_range[0] || test_id > test_range[1];
>  }
>  
> +static struct sk_buff *build_test_skb(void *page)
> +{
> +	u32 headroom = NET_SKB_PAD + NET_IP_ALIGN + ETH_HLEN;
> +	struct sk_buff *skb[2];
> +	int i, data_size = 8;
> +
> +	for (i = 0; i < 2; i++) {
> +		/* this will set skb[i]->head_frag */
> +		skb[i] = build_skb(page, headroom);
> +		if (!skb[i])
> +			return NULL;

You are using the same virtual address (page) for both skb ?

So we have 2 skbs having skb->head pointing to the same location ?

This is illegal.

Please use instead : skb = dev_alloc_skb(headroom + data_size)

> +
> +		skb_reserve(skb[i], headroom);
> +		skb_put(skb[i], data_size);
> +		skb[i]->protocol = htons(ETH_P_IP);
> +		skb_reset_network_header(skb[i]);
> +		skb_set_mac_header(skb[i], -ETH_HLEN);
> +
> +		skb_add_rx_frag(skb[i], 

skb_shinfo(skb[i])->nr_frags,

0 ?

> +				page, 0, 64, 64);

get_page(page) ?

> +		// skb: skb_headlen(skb[i]): 8, skb[i]->head_frag = 1
> +	}
> +
> +	/* setup shinfo */
> +	skb_shinfo(skb[0])->gso_size = 1448;
> +	skb_shinfo(skb[0])->gso_type = SKB_GSO_TCPV4;
> +	skb_shinfo(skb[0])->gso_type |= SKB_GSO_DODGY;
> +	skb_shinfo(skb[0])->gso_segs = 0;
> +	skb_shinfo(skb[0])->frag_list = skb[1];
> +
> +	/* adjust skb[0]'s len */
> +	skb[0]->len += skb[1]->len;
> +	skb[0]->data_len += skb[1]->data_len;
> +	skb[0]->truesize += skb[1]->truesize;
> +
> +	return skb[0];
> +}
> +
> +static __init int test_skb_segment(void)
> +{
> +	netdev_features_t features;
> +	struct sk_buff *skb;
> +	void *page;
> +	int ret = -1;
> +
> +	page = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
> +	if (!page) {
> +		pr_info("%s: failed to get_free_page!", __func__);
> +		return ret;
> +	}
> +
> +	features = NETIF_F_SG | NETIF_F_GSO_PARTIAL | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
> +	features |= NETIF_F_RXCSUM;
> +	skb = build_test_skb(page);
> +	if (!skb) {
> +		pr_info("%s: failed to build_test_skb", __func__);
> +	} else if (skb_segment(skb, features)) {
> +		ret = 0;
> +		pr_info("%s: success in skb_segment!", __func__);
> +	} else {
> +		pr_info("%s: failed in skb_segment!", __func__);
> +	}
> +	free_page((unsigned long)page);


Where are the skbs freed ?


> +	return ret;
> +}
> +
>  static __init int test_bpf(void)
>  {
>  	int i, err_cnt = 0, pass_cnt = 0;
> @@ -6632,8 +6698,11 @@ static int __init test_bpf_init(void)
>  		return ret;
>  
>  	ret = test_bpf();
> -
>  	destroy_bpf_tests();
> +	if (ret)
> +		return ret;
> +
> +	ret = test_skb_segment();
>  	return ret;
>  }
>  
>
Yonghong Song March 21, 2018, 5:15 a.m. UTC | #2
On 3/20/18 5:44 PM, Eric Dumazet wrote:
> 
> 
> On 03/20/2018 04:21 PM, Yonghong Song wrote:
>> Without the previous commit,
>> "modprobe test_bpf" will have the following errors:
>> ...
>> [   98.149165] ------------[ cut here ]------------
>> [   98.159362] kernel BUG at net/core/skbuff.c:3667!
>> [   98.169756] invalid opcode: 0000 [#1] SMP PTI
>> [   98.179370] Modules linked in:
>> [   98.179371]  test_bpf(+)
>> ...
>> which triggers the bug the previous commit intends to fix.
>>
>> The skbs are constructed to mimic what mlx5 may generate.
>> The packet size/header may not mimic real cases in production. But
>> the processing flow is similar.
>>
>> Signed-off-by: Yonghong Song <yhs@fb.com>
>> ---
>>   lib/test_bpf.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>>   1 file changed, 70 insertions(+), 1 deletion(-)
>>
>> diff --git a/lib/test_bpf.c b/lib/test_bpf.c
>> index 2efb213..045d7d3 100644
>> --- a/lib/test_bpf.c
>> +++ b/lib/test_bpf.c
>> @@ -6574,6 +6574,72 @@ static bool exclude_test(int test_id)
>>   	return test_id < test_range[0] || test_id > test_range[1];
>>   }
>>   
>> +static struct sk_buff *build_test_skb(void *page)
>> +{
>> +	u32 headroom = NET_SKB_PAD + NET_IP_ALIGN + ETH_HLEN;
>> +	struct sk_buff *skb[2];
>> +	int i, data_size = 8;
>> +
>> +	for (i = 0; i < 2; i++) {
>> +		/* this will set skb[i]->head_frag */
>> +		skb[i] = build_skb(page, headroom);
>> +		if (!skb[i])
>> +			return NULL;
> 
> You are using the same virtual address (page) for both skb ?
> 
> So we have 2 skbs having skb->head pointing to the same location ?

Thanks, Eric. This is purely due to my 'laziness' to make it work as I 
know that skb_segment does not really enforce this. I will address
all of your comments in the next revision.

> 
> This is illegal.
> 
> Please use instead : skb = dev_alloc_skb(headroom + data_size)
> 
>> +
>> +		skb_reserve(skb[i], headroom);
>> +		skb_put(skb[i], data_size);
>> +		skb[i]->protocol = htons(ETH_P_IP);
>> +		skb_reset_network_header(skb[i]);
>> +		skb_set_mac_header(skb[i], -ETH_HLEN);
>> +
>> +		skb_add_rx_frag(skb[i],
> 
> skb_shinfo(skb[i])->nr_frags,
> 
> 0 ?
> 
>> +				page, 0, 64, 64);
> 
> get_page(page) ?
> 
>> +		// skb: skb_headlen(skb[i]): 8, skb[i]->head_frag = 1
>> +	}
>> +
>> +	/* setup shinfo */
>> +	skb_shinfo(skb[0])->gso_size = 1448;
>> +	skb_shinfo(skb[0])->gso_type = SKB_GSO_TCPV4;
>> +	skb_shinfo(skb[0])->gso_type |= SKB_GSO_DODGY;
>> +	skb_shinfo(skb[0])->gso_segs = 0;
>> +	skb_shinfo(skb[0])->frag_list = skb[1];
>> +
>> +	/* adjust skb[0]'s len */
>> +	skb[0]->len += skb[1]->len;
>> +	skb[0]->data_len += skb[1]->data_len;
>> +	skb[0]->truesize += skb[1]->truesize;
>> +
>> +	return skb[0];
>> +}
>> +
>> +static __init int test_skb_segment(void)
>> +{
>> +	netdev_features_t features;
>> +	struct sk_buff *skb;
>> +	void *page;
>> +	int ret = -1;
>> +
>> +	page = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
>> +	if (!page) {
>> +		pr_info("%s: failed to get_free_page!", __func__);
>> +		return ret;
>> +	}
>> +
>> +	features = NETIF_F_SG | NETIF_F_GSO_PARTIAL | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
>> +	features |= NETIF_F_RXCSUM;
>> +	skb = build_test_skb(page);
>> +	if (!skb) {
>> +		pr_info("%s: failed to build_test_skb", __func__);
>> +	} else if (skb_segment(skb, features)) {
>> +		ret = 0;
>> +		pr_info("%s: success in skb_segment!", __func__);
>> +	} else {
>> +		pr_info("%s: failed in skb_segment!", __func__);
>> +	}
>> +	free_page((unsigned long)page);
> 
> 
> Where are the skbs freed ?
> 
> 
>> +	return ret;
>> +}
>> +
>>   static __init int test_bpf(void)
>>   {
>>   	int i, err_cnt = 0, pass_cnt = 0;
>> @@ -6632,8 +6698,11 @@ static int __init test_bpf_init(void)
>>   		return ret;
>>   
>>   	ret = test_bpf();
>> -
>>   	destroy_bpf_tests();
>> +	if (ret)
>> +		return ret;
>> +
>> +	ret = test_skb_segment();
>>   	return ret;
>>   }
>>   
>>
diff mbox series

Patch

diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 2efb213..045d7d3 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -6574,6 +6574,72 @@  static bool exclude_test(int test_id)
 	return test_id < test_range[0] || test_id > test_range[1];
 }
 
+static struct sk_buff *build_test_skb(void *page)
+{
+	u32 headroom = NET_SKB_PAD + NET_IP_ALIGN + ETH_HLEN;
+	struct sk_buff *skb[2];
+	int i, data_size = 8;
+
+	for (i = 0; i < 2; i++) {
+		/* this will set skb[i]->head_frag */
+		skb[i] = build_skb(page, headroom);
+		if (!skb[i])
+			return NULL;
+
+		skb_reserve(skb[i], headroom);
+		skb_put(skb[i], data_size);
+		skb[i]->protocol = htons(ETH_P_IP);
+		skb_reset_network_header(skb[i]);
+		skb_set_mac_header(skb[i], -ETH_HLEN);
+
+		skb_add_rx_frag(skb[i], skb_shinfo(skb[i])->nr_frags,
+				page, 0, 64, 64);
+		// skb: skb_headlen(skb[i]): 8, skb[i]->head_frag = 1
+	}
+
+	/* setup shinfo */
+	skb_shinfo(skb[0])->gso_size = 1448;
+	skb_shinfo(skb[0])->gso_type = SKB_GSO_TCPV4;
+	skb_shinfo(skb[0])->gso_type |= SKB_GSO_DODGY;
+	skb_shinfo(skb[0])->gso_segs = 0;
+	skb_shinfo(skb[0])->frag_list = skb[1];
+
+	/* adjust skb[0]'s len */
+	skb[0]->len += skb[1]->len;
+	skb[0]->data_len += skb[1]->data_len;
+	skb[0]->truesize += skb[1]->truesize;
+
+	return skb[0];
+}
+
+static __init int test_skb_segment(void)
+{
+	netdev_features_t features;
+	struct sk_buff *skb;
+	void *page;
+	int ret = -1;
+
+	page = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page) {
+		pr_info("%s: failed to get_free_page!", __func__);
+		return ret;
+	}
+
+	features = NETIF_F_SG | NETIF_F_GSO_PARTIAL | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	features |= NETIF_F_RXCSUM;
+	skb = build_test_skb(page);
+	if (!skb) {
+		pr_info("%s: failed to build_test_skb", __func__);
+	} else if (skb_segment(skb, features)) {
+		ret = 0;
+		pr_info("%s: success in skb_segment!", __func__);
+	} else {
+		pr_info("%s: failed in skb_segment!", __func__);
+	}
+	free_page((unsigned long)page);
+	return ret;
+}
+
 static __init int test_bpf(void)
 {
 	int i, err_cnt = 0, pass_cnt = 0;
@@ -6632,8 +6698,11 @@  static int __init test_bpf_init(void)
 		return ret;
 
 	ret = test_bpf();
-
 	destroy_bpf_tests();
+	if (ret)
+		return ret;
+
+	ret = test_skb_segment();
 	return ret;
 }