| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1429293524-26897-1-git-send-email-krisman@linux.vnet.ibm.com>
Date: Fri, 17 Apr 2015 14:58:44 -0300
From: Gabriel Krisman Bertazi <krisman@...ux.vnet.ibm.com>
To: ariel.elior@...gic.com
Cc: netdev@...r.kernel.org, cascardo@...ux.vnet.ibm.com,
Gabriel Krisman Bertazi <krisman@...ux.vnet.ibm.com>
Subject: [PATCH] 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, 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@...ux.vnet.ibm.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 18 ++++++--
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 61 +++++++++++++++++--------
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 10 ++--
3 files changed, 65 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 4085c4b..292176a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -356,6 +356,8 @@ struct sw_tx_bd {
struct sw_rx_page {
struct page *page;
+ int len;
+ int offset;
DEFINE_DMA_UNMAP_ADDR(mapping);
};
@@ -381,9 +383,10 @@ union db_prod {
#define PAGES_PER_SGE_SHIFT 0
#define PAGES_PER_SGE (1 << PAGES_PER_SGE_SHIFT)
-#define SGE_PAGE_SIZE PAGE_SIZE
-#define SGE_PAGE_SHIFT PAGE_SHIFT
-#define SGE_PAGE_ALIGN(addr) PAGE_ALIGN((typeof(PAGE_SIZE))(addr))
+#define SGE_PAGE_SHIFT 12
+#define SGE_PAGE_SIZE (1 << SGE_PAGE_SHIFT)
+#define SGE_PAGE_MASK (~(SGE_PAGE_SIZE - 1))
+#define SGE_PAGE_ALIGN(addr) (((addr) + SGE_PAGE_SIZE - 1) & SGE_PAGE_MASK)
#define SGE_PAGES (SGE_PAGE_SIZE * PAGES_PER_SGE)
#define TPA_AGG_SIZE min_t(u32, (min_t(u32, 8, MAX_SKB_FRAGS) * \
SGE_PAGES), 0xffff)
@@ -1450,6 +1453,13 @@ enum {
SUB_MF_MODE_NPAR1_DOT_5,
};
+struct bnx2x_alloc_pool {
+ struct page *page;
+ dma_addr_t dma;
+ int len;
+ int offset;
+};
+
struct bnx2x {
/* Fields used in the tx and intr/napi performance paths
* are grouped together in the beginning of the structure
@@ -1562,6 +1572,8 @@ struct bnx2x {
__le16 *eq_cons_sb;
atomic_t eq_spq_left; /* COMMON_XXX ramrods credit */
+ struct bnx2x_alloc_pool page_pool;
+
/* Counter for marking that there is a STAT_QUERY ramrod pending */
u16 stats_pending;
/* Counter for completed statistics ramrods */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 0a9faa1..47cc31f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -544,30 +544,46 @@ static void bnx2x_set_gro_params(struct sk_buff *skb, u16 parsing_flags,
static int bnx2x_alloc_rx_sge(struct bnx2x *bp, struct bnx2x_fastpath *fp,
u16 index, gfp_t gfp_mask)
{
- struct page *page = alloc_pages(gfp_mask, PAGES_PER_SGE_SHIFT);
struct sw_rx_page *sw_buf = &fp->rx_page_ring[index];
struct eth_rx_sge *sge = &fp->rx_sge_ring[index];
+ struct page **page = &bp->page_pool.page;
dma_addr_t mapping;
- if (unlikely(page == NULL)) {
- BNX2X_ERR("Can't alloc sge\n");
- return -ENOMEM;
- }
+ if (!*page ||
+ (bp->page_pool.len - bp->page_pool.offset) < SGE_PAGE_SIZE) {
+ *page = alloc_pages(gfp_mask, PAGES_PER_SGE_SHIFT);
- mapping = dma_map_page(&bp->pdev->dev, page, 0,
- SGE_PAGES, DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
- __free_pages(page, PAGES_PER_SGE_SHIFT);
- BNX2X_ERR("Can't map sge\n");
- return -ENOMEM;
+ if (unlikely(!*page)) {
+ BNX2X_ERR("Can't alloc sge\n");
+ return -ENOMEM;
+ }
+ bp->page_pool.dma = dma_map_page(&bp->pdev->dev, *page, 0,
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(&bp->pdev->dev,
+ bp->page_pool.dma))) {
+ __free_pages(*page, PAGES_PER_SGE_SHIFT);
+ BNX2X_ERR("Can't map sge\n");
+ return -ENOMEM;
+ }
+
+ bp->page_pool.offset = 0;
+ bp->page_pool.len = PAGE_SIZE;
+ } else {
+ get_page(bp->page_pool.page);
}
- sw_buf->page = page;
+ sw_buf->page = *page;
+ sw_buf->len = SGE_PAGE_SIZE;
+ sw_buf->offset = bp->page_pool.offset;
+
+ mapping = bp->page_pool.dma + sw_buf->offset;
dma_unmap_addr_set(sw_buf, mapping, mapping);
sge->addr_hi = cpu_to_le32(U64_HI(mapping));
sge->addr_lo = cpu_to_le32(U64_LO(mapping));
+ bp->page_pool.offset += SGE_PAGE_SIZE;
+
return 0;
}
@@ -628,21 +644,30 @@ static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp,
bnx2x_fp_qstats(bp, fp)->rx_skb_alloc_failed++;
return err;
}
+ if (old_rx_pg.offset + old_rx_pg.len >= PAGE_SIZE) {
+ /* Unmap the page as we finished passing it to
+ * the stack
+ */
+ old_rx_pg.mapping = old_rx_pg.mapping -
+ old_rx_pg.offset;
+ dma_unmap_page(&bp->pdev->dev,
+ dma_unmap_addr(&old_rx_pg, mapping),
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ }
- /* Unmap the page as we're going to pass it to the stack */
- dma_unmap_page(&bp->pdev->dev,
- dma_unmap_addr(&old_rx_pg, mapping),
- SGE_PAGES, DMA_FROM_DEVICE);
/* Add one frag and update the appropriate fields in the skb */
if (fp->mode == TPA_MODE_LRO)
- skb_fill_page_desc(skb, j, old_rx_pg.page, 0, frag_len);
+ skb_fill_page_desc(skb, j, old_rx_pg.page,
+ old_rx_pg.offset, frag_len);
else { /* GRO */
int rem;
int offset = 0;
for (rem = frag_len; rem > 0; rem -= gro_size) {
int len = rem > gro_size ? gro_size : rem;
skb_fill_page_desc(skb, frag_id++,
- old_rx_pg.page, offset, len);
+ old_rx_pg.page,
+ old_rx_pg.offset + offset,
+ len);
if (offset)
get_page(old_rx_pg.page);
offset += len;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index adcacda..80a54ac 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -799,14 +799,18 @@ static inline void bnx2x_free_rx_sge(struct bnx2x *bp,
struct sw_rx_page *sw_buf = &fp->rx_page_ring[index];
struct page *page = sw_buf->page;
struct eth_rx_sge *sge = &fp->rx_sge_ring[index];
+ dma_addr_t dma;
/* Skip "next page" elements */
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);
+ if (sw_buf->offset + sw_buf->len >= PAGE_SIZE) {
+ dma = sw_buf->mapping - sw_buf->offset;
+ dma_unmap_page(&bp->pdev->dev, dma,
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ }
+ put_page(page);
sw_buf->page = NULL;
sge->addr_hi = 0;
--
2.1.0
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists