net/af_xdp: fix umem size

Message ID 20200910090647.23789-1-ciara.loftus@intel.com (mailing list archive)
State Accepted, archived
Delegated to: Ferruh Yigit
Headers
Series net/af_xdp: fix umem size |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/iol-broadcom-Functional success Functional Testing PASS
ci/iol-broadcom-Performance success Performance Testing PASS
ci/travis-robot success Travis build: passed
ci/iol-intel-Functional success Functional Testing PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/Intel-compilation success Compilation OK
ci/iol-testing success Testing PASS

Commit Message

Loftus, Ciara Sept. 10, 2020, 9:06 a.m. UTC
  The kernel expects the start address of the UMEM to be page size aligned.
Since the mempool is not guaranteed to have such alignment, we have been
aligning the address to the start of the page the mempool is on. However
when passing the 'size' of the UMEM during it's creation we did not take
this into account. This commit adds the amount by which the address was
aligned to the size of the UMEM.

Bugzilla ID: 532
Fixes: d8a210774e1d ("net/af_xdp: support unaligned umem chunks")
Cc: stable@dpdk.org

Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
---
 drivers/net/af_xdp/rte_eth_af_xdp.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)
  

Comments

Ferruh Yigit Sept. 18, 2020, 5:29 p.m. UTC | #1
On 9/10/2020 10:06 AM, Ciara Loftus wrote:
> The kernel expects the start address of the UMEM to be page size aligned.
> Since the mempool is not guaranteed to have such alignment, we have been
> aligning the address to the start of the page the mempool is on. However
> when passing the 'size' of the UMEM during it's creation we did not take
> this into account. This commit adds the amount by which the address was
> aligned to the size of the UMEM.
> 
> Bugzilla ID: 532
> Fixes: d8a210774e1d ("net/af_xdp: support unaligned umem chunks")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>

Applied to dpdk-next-net/main, thanks.
  

Patch

diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c b/drivers/net/af_xdp/rte_eth_af_xdp.c
index 936d4a7d5f..22f2710e53 100644
--- a/drivers/net/af_xdp/rte_eth_af_xdp.c
+++ b/drivers/net/af_xdp/rte_eth_af_xdp.c
@@ -746,12 +746,17 @@  eth_link_update(struct rte_eth_dev *dev __rte_unused,
 }
 
 #if defined(XDP_UMEM_UNALIGNED_CHUNK_FLAG)
-static inline uint64_t get_base_addr(struct rte_mempool *mp)
+static inline uint64_t get_base_addr(struct rte_mempool *mp, uint64_t *align)
 {
 	struct rte_mempool_memhdr *memhdr;
+	uint64_t memhdr_addr, aligned_addr;
 
 	memhdr = STAILQ_FIRST(&mp->mem_list);
-	return (uint64_t)memhdr->addr & ~(getpagesize() - 1);
+	memhdr_addr = (uint64_t)memhdr->addr;
+	aligned_addr = memhdr_addr & ~(getpagesize() - 1);
+	*align = memhdr_addr - aligned_addr;
+
+	return aligned_addr;
 }
 
 static struct
@@ -766,6 +771,7 @@  xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals __rte_unused,
 		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG};
 	void *base_addr = NULL;
 	struct rte_mempool *mb_pool = rxq->mb_pool;
+	uint64_t umem_size, align = 0;
 
 	usr_config.frame_size = rte_mempool_calc_obj_size(mb_pool->elt_size,
 								mb_pool->flags,
@@ -782,12 +788,11 @@  xsk_umem_info *xdp_umem_configure(struct pmd_internals *internals __rte_unused,
 	}
 
 	umem->mb_pool = mb_pool;
-	base_addr = (void *)get_base_addr(mb_pool);
+	base_addr = (void *)get_base_addr(mb_pool, &align);
+	umem_size = mb_pool->populated_size * usr_config.frame_size + align;
 
-	ret = xsk_umem__create(&umem->umem, base_addr,
-			       mb_pool->populated_size * usr_config.frame_size,
-			       &umem->fq, &umem->cq,
-			       &usr_config);
+	ret = xsk_umem__create(&umem->umem, base_addr, umem_size,
+			       &umem->fq, &umem->cq, &usr_config);
 
 	if (ret) {
 		AF_XDP_LOG(ERR, "Failed to create umem");