bnx2x: Alloc 4k fragment for each rx ring buffer element

The driver allocates one page for each buffer on the rx ring, which is
too much on architectures like ppc64 and can cause unexpected allocation
failures when the system is under stress.  Now, we keep a memory pool
per queue, and if the architecture's PAGE_SIZE is greater than 4k, we
fragment pages and assign each 4k segment to a ring element, which
reduces the overall memory consumption on such architectures.  This
helps avoiding errors like the example below:

[bnx2x_alloc_rx_sge:435(eth1)]Can't alloc sge
[c00000037ffeb900] [d000000075eddeb4] .bnx2x_alloc_rx_sge+0x44/0x200 [bnx2x]
[c00000037ffeb9b0] [d000000075ee0b34] .bnx2x_fill_frag_skb+0x1ac/0x460 [bnx2x]
[c00000037ffebac0] [d000000075ee11f0] .bnx2x_tpa_stop+0x160/0x2e8 [bnx2x]
[c00000037ffebb90] [d000000075ee1560] .bnx2x_rx_int+0x1e8/0xc30 [bnx2x]
[c00000037ffebcd0] [d000000075ee2084] .bnx2x_poll+0xdc/0x3d8 [bnx2x] (unreliable)

Signed-off-by: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
Acked-by: Yuval Mintz <Yuval.Mintz@qlogic.com>
Reviewed-by: Lino Sanfilippo <LinoSanfilippo@gmx.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 28 insertions, 3 deletions

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index d7a71758e876..2b30081ec26d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -804,9 +804,13 @@ static inline void bnx2x_free_rx_sge(struct bnx2x *bp,
 	if (!page)
 		return;
 
-	dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(sw_buf, mapping),
-		       SGE_PAGES, DMA_FROM_DEVICE);
-	__free_pages(page, PAGES_PER_SGE_SHIFT);
+	/* Since many fragments can share the same page, make sure to
+	 * only unmap and free the page once.
+	 */
+	dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(sw_buf, mapping),
+			 SGE_PAGE_SIZE, DMA_FROM_DEVICE);
+
+	put_page(page);
 
 	sw_buf->page = NULL;
 	sge->addr_hi = 0;
@@ -964,6 +968,25 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid,
 	((u8 *)fw_lo)[1]  = mac[4];
 }
 
+static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp,
+					  struct bnx2x_alloc_pool *pool)
+{
+	if (!pool->page)
+		return;
+
+	/* Page was not fully fragmented.  Unmap unused space */
+	if (pool->offset < PAGE_SIZE) {
+		dma_addr_t dma = pool->dma + pool->offset;
+		int size = PAGE_SIZE - pool->offset;
+
+		dma_unmap_single(&bp->pdev->dev, dma, size, DMA_FROM_DEVICE);
+	}
+
+	put_page(pool->page);
+
+	pool->page = NULL;
+}
+
 static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp,
 					   struct bnx2x_fastpath *fp, int last)
 {
@@ -974,6 +997,8 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp,
 
 	for (i = 0; i < last; i++)
 		bnx2x_free_rx_sge(bp, fp, i);
+
+	bnx2x_free_rx_mem_pool(bp, &fp->page_pool);
 }
 
 static inline void bnx2x_set_next_page_rx_bd(struct bnx2x_fastpath *fp)