From: Helin Zhang <helin.zhang@intel.com>
To: dev@dpdk.org
Subject: [dpdk-dev] [PATCH] i40e: Use one bit flag for all hardware detected RX packet errors
Date: Wed, 26 Nov 2014 14:07:12 +0800 [thread overview]
Message-ID: <1416982032-28519-1-git-send-email-helin.zhang@intel.com> (raw)
There were some bit flags of 0 for RX packet errors detected by hardware.
Actually only one bit of error flag is enough for all hardware detected
RX packet errors.
Signed-off-by: Helin Zhang <helin.zhang@intel.com>
---
lib/librte_mbuf/rte_mbuf.h | 6 +-----
lib/librte_pmd_i40e/i40e_rxtx.c | 31 +++----------------------------
2 files changed, 4 insertions(+), 33 deletions(-)
diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index 5899e5c..897fd26 100644
--- a/lib/librte_mbuf/rte_mbuf.h
+++ b/lib/librte_mbuf/rte_mbuf.h
@@ -80,11 +80,6 @@ extern "C" {
#define PKT_RX_FDIR (1ULL << 2) /**< RX packet with FDIR match indicate. */
#define PKT_RX_L4_CKSUM_BAD (1ULL << 3) /**< L4 cksum of RX pkt. is not OK. */
#define PKT_RX_IP_CKSUM_BAD (1ULL << 4) /**< IP cksum of RX pkt. is not OK. */
-#define PKT_RX_EIP_CKSUM_BAD (0ULL << 0) /**< External IP header checksum error. */
-#define PKT_RX_OVERSIZE (0ULL << 0) /**< Num of desc of an RX pkt oversize. */
-#define PKT_RX_HBUF_OVERFLOW (0ULL << 0) /**< Header buffer overflow. */
-#define PKT_RX_RECIP_ERR (0ULL << 0) /**< Hardware processing error. */
-#define PKT_RX_MAC_ERR (0ULL << 0) /**< MAC error. */
#define PKT_RX_IPV4_HDR (1ULL << 5) /**< RX packet with IPv4 header. */
#define PKT_RX_IPV4_HDR_EXT (1ULL << 6) /**< RX packet with extended IPv4 header. */
#define PKT_RX_IPV6_HDR (1ULL << 7) /**< RX packet with IPv6 header. */
@@ -95,6 +90,7 @@ extern "C" {
#define PKT_RX_TUNNEL_IPV6_HDR (1ULL << 12) /**< RX tunnel packet with IPv6 header. */
#define PKT_RX_FDIR_ID (1ULL << 13) /**< FD id reported if FDIR match. */
#define PKT_RX_FDIR_FLX (1ULL << 14) /**< Flexible bytes reported if FDIR match. */
+#define PKT_RX_ERR_HW (1ULL << 15) /**< RX packet error detected by hardware. */
#define PKT_TX_VLAN_PKT (1ULL << 55) /**< TX packet is a 802.1q VLAN packet. */
#define PKT_TX_IP_CKSUM (1ULL << 54) /**< IP cksum of TX pkt. computed by NIC. */
diff --git a/lib/librte_pmd_i40e/i40e_rxtx.c b/lib/librte_pmd_i40e/i40e_rxtx.c
index cce6911..3b2195d 100644
--- a/lib/librte_pmd_i40e/i40e_rxtx.c
+++ b/lib/librte_pmd_i40e/i40e_rxtx.c
@@ -115,35 +115,10 @@ i40e_rxd_status_to_pkt_flags(uint64_t qword)
static inline uint64_t
i40e_rxd_error_to_pkt_flags(uint64_t qword)
{
- uint64_t flags = 0;
- uint64_t error_bits = (qword >> I40E_RXD_QW1_ERROR_SHIFT);
-
-#define I40E_RX_ERR_BITS 0x3f
- if (likely((error_bits & I40E_RX_ERR_BITS) == 0))
- return flags;
- /* If RXE bit set, all other status bits are meaningless */
- if (unlikely(error_bits & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
- flags |= PKT_RX_MAC_ERR;
- return flags;
- }
-
- /* If RECIPE bit set, all other status indications should be ignored */
- if (unlikely(error_bits & (1 << I40E_RX_DESC_ERROR_RECIPE_SHIFT))) {
- flags |= PKT_RX_RECIP_ERR;
- return flags;
- }
- if (unlikely(error_bits & (1 << I40E_RX_DESC_ERROR_HBO_SHIFT)))
- flags |= PKT_RX_HBUF_OVERFLOW;
- if (unlikely(error_bits & (1 << I40E_RX_DESC_ERROR_IPE_SHIFT)))
- flags |= PKT_RX_IP_CKSUM_BAD;
- if (unlikely(error_bits & (1 << I40E_RX_DESC_ERROR_L4E_SHIFT)))
- flags |= PKT_RX_L4_CKSUM_BAD;
- if (unlikely(error_bits & (1 << I40E_RX_DESC_ERROR_EIPE_SHIFT)))
- flags |= PKT_RX_EIP_CKSUM_BAD;
- if (unlikely(error_bits & (1 << I40E_RX_DESC_ERROR_OVERSIZE_SHIFT)))
- flags |= PKT_RX_OVERSIZE;
+ if (unlikely(qword & I40E_RXD_QW1_ERROR_MASK))
+ return PKT_RX_ERR_HW;
- return flags;
+ return 0;
}
/* Translate pkt types to pkt flags */
--
1.8.1.4
next reply other threads:[~2014-11-26 5:56 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-26 6:07 Helin Zhang [this message]
2014-11-26 10:49 ` Ananyev, Konstantin
2014-11-26 11:22 ` Olivier MATZ
2014-11-26 13:38 ` Ananyev, Konstantin
2014-11-26 14:12 ` Olivier MATZ
2014-11-28 8:07 ` Zhang, Helin
2014-11-28 8:47 ` Olivier MATZ
2014-12-01 1:57 ` Zhang, Helin
2014-12-01 9:58 ` Olivier MATZ
2014-12-02 7:25 ` Zhang, Helin
2014-12-05 1:46 ` [dpdk-dev] [PATCH v2 0/2] fix of enabling all newly added error flags Helin Zhang
2014-12-05 1:46 ` [dpdk-dev] [PATCH v2 1/2] i40e: remove checking rxd flag which is not public Helin Zhang
2014-12-05 1:46 ` [dpdk-dev] [PATCH v2 2/2] mbuf: assign valid bit values for some RX and TX flags Helin Zhang
2014-12-05 10:49 ` Ananyev, Konstantin
2014-12-06 0:42 ` Zhang, Helin
2014-12-06 1:07 ` Zhang, Helin
2014-12-08 10:55 ` Ananyev, Konstantin
2014-12-09 2:29 ` Zhang, Helin
2014-12-06 1:33 ` [dpdk-dev] [PATCH v3] mbuf: fix of enabling all newly added RX error flags Helin Zhang
2014-12-08 10:44 ` Ananyev, Konstantin
2014-12-09 2:23 ` Zhang, Helin
2014-12-08 10:50 ` Thomas Monjalon
2014-12-09 2:14 ` Zhang, Helin
2014-12-09 6:22 ` Thomas Monjalon
2014-12-10 8:55 ` [dpdk-dev] [PATCH v4] " Helin Zhang
2014-12-10 9:35 ` Thomas Monjalon
2014-12-10 13:50 ` Zhang, Helin
2014-12-10 15:26 ` Thomas Monjalon
2014-12-10 22:29 ` Zhang, Helin
2014-12-11 11:16 ` Olivier MATZ
2014-12-12 1:27 ` Zhang, Helin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1416982032-28519-1-git-send-email-helin.zhang@intel.com \
--to=helin.zhang@intel.com \
--cc=dev@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).