Skip to contentSkip to conversation

__alloc_pages() failures reported due to fragmentation

PATCH Larry Woodman 3 participants 4 messages Nov 3, 2006

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

We have seen a couple of __alloc_pages() failures due to fragmentation, there is plenty of free memory but no large order pages available. I think the problem is in sock_alloc_send_pskb(), the gfp_mask includes __GFP_REPEAT but its never used/passed to the page allocator. Shouldnt the gfp_mask be passed to alloc_skb() ?

-------------------------------------------------------------------
struct sk_buff *sock_alloc_send_pskb()

{
      unsigned int gfp_mask;

...

      gfp_mask = sk->sk_allocation;
      if (gfp_mask & __GFP_WAIT)
              gfp_mask |= __GFP_REPEAT;
...
      skb = alloc_skb(header_len, sk->sk_allocation);

--------------------------------------------------------------------

net/core/sock.c renamed from net/core/sock.c.orig +0 -0
@@ -1154,7 +1154,7 @@ static struct sk_buff *sock_alloc_send_p
			goto failure;

		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
-			skb = alloc_skb(header_len, sk->sk_allocation);
+			skb = alloc_skb(header_len, gfp_mask);
			if (skb) {
				int npages;
				int i;
#1 lore raw

net/core/sock.c static struct sk_buff *sock_alloc_send_p · line 1160

Quoted 12 lines
net/core/sock.c renamed from net/core/sock.c.orig +1 -1
@@ -1154,7 +1154,7 @@ static struct sk_buff *sock_alloc_send_p
 			goto failure;
 
 		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
-			skb = alloc_skb(header_len, sk->sk_allocation);
+			skb = alloc_skb(header_len, gfp_mask);
 			if (skb) {
 				int npages;
 				int i;

Hi,

this is not actually right though... sk_allocation is very possible to have a restricting mask compared to the one passed in (say "no highmem" or even GFP_DMA) and you now discard this... probably better would be to calculate a set of "transient" flags that you then or into the sk_allocation mask at this time...

Greetings,
Arjan van de Ven

Signature · 2 lines
if you want to mail me at work (you don't), use arjan (at) linux.intel.com
Test the interaction between Linux and your BIOS via http://www.linuxfirmwarekit.org
#2 lore raw
Quoted 16 lines · Arjan van de Ven

net/core/sock.c static struct sk_buff *sock_alloc_send_p · line 1160

Quoted 13 lines
net/core/sock.c renamed from net/core/sock.c.orig +1 -1
@@ -1154,7 +1154,7 @@ static struct sk_buff *sock_alloc_send_p
 			goto failure;
 
 		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
-			skb = alloc_skb(header_len, sk->sk_allocation);
+			skb = alloc_skb(header_len, gfp_mask);
 			if (skb) {
 				int npages;
 				int i;

Hi,

Quoted 11 lines

this is not actually right though... sk_allocation is very possible to have a restricting mask compared to the one passed in (say "no highmem" or even GFP_DMA) and you now discard this... probably better would be to calculate a set of "transient" flags that you then or into the sk_allocation mask at this time...

Greetings,
Arjan van de Ven

Hi Arjan. Right but this just includes __GFP_REPEAT in the mask so we can defrag in __alloc_pages and only if GFP_WAIT was passed in origionally.

Larry

maintainer
#3 lore raw

From: Larry Woodman <[email protected]>
Date: Fri, 03 Nov 2006 07:39:44 -0500

Quoted 2 lines

Hi Arjan. Right but this just includes __GFP_REPEAT in the mask so we can defrag in __alloc_pages and only if GFP_WAIT was passed in origionally.

Indeed, quoting that small snippet of the patch was deceptive :-)

Arjan, gfp_mask is set to sk->sk_allocation, and we just add a bit into it conditionally.