Message ID | 20201111091112.12606-1-murphyx.yang@intel.com |
---|---|
State | Superseded |
Delegated to: | Qi Zhang |
Headers | show |
Series |
|
Related | show |
Context | Check | Description |
---|---|---|
ci/iol-intel-Functional | success | Functional Testing PASS |
ci/iol-mellanox-Performance | success | Performance Testing PASS |
ci/travis-robot | success | Travis build: passed |
ci/iol-testing | success | Testing PASS |
ci/iol-intel-Performance | success | Performance Testing PASS |
ci/iol-broadcom-Functional | success | Functional Testing PASS |
ci/iol-broadcom-Performance | success | Performance Testing PASS |
ci/Intel-compilation | success | Compilation OK |
ci/checkpatch | success | coding style OK |
Hi, murphy > -----Original Message----- > From: Murphy Yang <murphyx.yang@intel.com> > Sent: Wednesday, November 11, 2020 5:11 PM > To: dev@dpdk.org > Cc: Yang, Qiming <qiming.yang@intel.com>; Yang, SteveX > <stevex.yang@intel.com>; Xing, Beilei <beilei.xing@intel.com>; Guo, Jia > <jia.guo@intel.com>; Yang, MurphyX <murphyx.yang@intel.com> > Subject: [PATCH] net/i40e: fix incorrect checksum flag of L4 checksum > > When send tunneled packet that inner L4 checksum value is correct, the > test_pmd output log shows 'ol_flags' value is > 'PKT_RX_L4_CKSUM_UNKNOWN', but expected value is > 'PKT_RX_L4_CKSUM_GOOD'. > > Add the 'PKT_RX_L4_CKSUM_GOOD' to 'l3_l4e_flags' for sse and > 'l3_l4_flags_shuf' for avx2 to ensure that the 'ol_flags' can match correct flags. > Seems that 'PKT_RX_L4_CKSUM_GOOD' is previous there but not set correctly, so maybe it should not say " Add the 'PKT_RX_L4_CKSUM_GOOD' to 'l3_l4e_flags' .... " Add more, could you please to check if the other rx vec path also need it, such as vec_altivec and vec_neon? > Fixes: 9966a00a0688 ("net/i40e: enable bad checksum flags in vector Rx") > Fixes: dafadd73762e ("net/i40e: add AVX2 Rx function") > > Signed-off-by: Murphy Yang <murphyx.yang@intel.com> > --- > drivers/net/i40e/i40e_rxtx_vec_avx2.c | 40 ++++++++++++++++----------- > drivers/net/i40e/i40e_rxtx_vec_sse.c | 20 ++++++++------ > 2 files changed, 35 insertions(+), 25 deletions(-) > > diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx2.c > b/drivers/net/i40e/i40e_rxtx_vec_avx2.c > index 7a558fc73a..fe6ec7deef 100644 > --- a/drivers/net/i40e/i40e_rxtx_vec_avx2.c > +++ b/drivers/net/i40e/i40e_rxtx_vec_avx2.c > @@ -342,24 +342,32 @@ _recv_raw_pkts_vec_avx2(struct i40e_rx_queue > *rxq, struct rte_mbuf **rx_pkts, > */ > const __m256i l3_l4_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, 0, 0, 0, > 0, > /* shift right 1 bit to make sure it not exceed 255 */ > - (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD) >> 1, > - (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_EIP_CKSUM_BAD) >> 1, > - (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_L4_CKSUM_BAD) >> 1, > - PKT_RX_IP_CKSUM_BAD >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_L4_CKSUM_GOOD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | > + PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | > + PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_GOOD | > + PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_GOOD | > + PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_L4_CKSUM_GOOD | > PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_L4_CKSUM_GOOD | > PKT_RX_IP_CKSUM_GOOD) >> 1, > /* second 128-bits */ > 0, 0, 0, 0, 0, 0, 0, 0, > - (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD) >> 1, > - (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_EIP_CKSUM_BAD) >> 1, > - (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_L4_CKSUM_BAD) >> 1, > - PKT_RX_IP_CKSUM_BAD >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_L4_CKSUM_GOOD) >> 1); > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | > + PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | > + PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_GOOD | > + PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_GOOD | > + PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_L4_CKSUM_GOOD | > PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_L4_CKSUM_GOOD | > PKT_RX_IP_CKSUM_GOOD) >> 1); > Could you double check if it is reasonable that the " PKT_RX_EIP_CKSUM_BAD" is always be set, but no " PKT_RX_EIP_CKSUM_GOOD "? > const __m256i cksum_mask = _mm256_set1_epi32( > PKT_RX_IP_CKSUM_GOOD | > PKT_RX_IP_CKSUM_BAD | diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c > b/drivers/net/i40e/i40e_rxtx_vec_sse.c > index 4b2b6a28fc..0bcb48e24e 100644 > --- a/drivers/net/i40e/i40e_rxtx_vec_sse.c > +++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c > @@ -254,16 +254,18 @@ desc_to_olflags_v(struct i40e_rx_queue *rxq, > volatile union i40e_rx_desc *rxdp, > > const __m128i l3_l4e_flags = _mm_set_epi8(0, 0, 0, 0, 0, 0, 0, 0, > /* shift right 1 bit to make sure it not exceed 255 */ > - (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_EIP_CKSUM_BAD | > - PKT_RX_L4_CKSUM_BAD) >> 1, > - (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_EIP_CKSUM_BAD) >> 1, > - (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_L4_CKSUM_BAD) >> 1, > - PKT_RX_IP_CKSUM_BAD >> 1, > - (PKT_RX_IP_CKSUM_GOOD | > PKT_RX_L4_CKSUM_GOOD) >> 1); > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_BAD | > + PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_GOOD | > + PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_EIP_CKSUM_BAD | > PKT_RX_L4_CKSUM_GOOD | > + PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_L4_CKSUM_BAD | > PKT_RX_IP_CKSUM_GOOD) >> 1, > + (PKT_RX_L4_CKSUM_GOOD | > PKT_RX_IP_CKSUM_BAD) >> 1, > + (PKT_RX_L4_CKSUM_GOOD | > PKT_RX_IP_CKSUM_GOOD) >> 1); > > /* Unpack "status" from quadword 1, bits 0:32 */ > vlan0 = _mm_unpackhi_epi32(descs[0], descs[1]); > -- > 2.17.1
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx2.c b/drivers/net/i40e/i40e_rxtx_vec_avx2.c index 7a558fc73a..fe6ec7deef 100644 --- a/drivers/net/i40e/i40e_rxtx_vec_avx2.c +++ b/drivers/net/i40e/i40e_rxtx_vec_avx2.c @@ -342,24 +342,32 @@ _recv_raw_pkts_vec_avx2(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts, */ const __m256i l3_l4_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, 0, 0, 0, 0, /* shift right 1 bit to make sure it not exceed 255 */ - (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD) >> 1, - (PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1, - (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1, - PKT_RX_IP_CKSUM_BAD >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | + PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | + PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD | + PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD | + PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1, /* second 128-bits */ 0, 0, 0, 0, 0, 0, 0, 0, - (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD) >> 1, - (PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1, - (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1, - PKT_RX_IP_CKSUM_BAD >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> 1); + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | + PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | + PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD | + PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD | + PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1); const __m256i cksum_mask = _mm256_set1_epi32( PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD | diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c b/drivers/net/i40e/i40e_rxtx_vec_sse.c index 4b2b6a28fc..0bcb48e24e 100644 --- a/drivers/net/i40e/i40e_rxtx_vec_sse.c +++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c @@ -254,16 +254,18 @@ desc_to_olflags_v(struct i40e_rx_queue *rxq, volatile union i40e_rx_desc *rxdp, const __m128i l3_l4e_flags = _mm_set_epi8(0, 0, 0, 0, 0, 0, 0, 0, /* shift right 1 bit to make sure it not exceed 255 */ - (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD | - PKT_RX_L4_CKSUM_BAD) >> 1, - (PKT_RX_EIP_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_EIP_CKSUM_BAD) >> 1, - (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD) >> 1, - PKT_RX_IP_CKSUM_BAD >> 1, - (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD) >> 1); + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD | + PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD | + PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD | + PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1, + (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1, + (PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1); /* Unpack "status" from quadword 1, bits 0:32 */ vlan0 = _mm_unpackhi_epi32(descs[0], descs[1]);
When send tunneled packet that inner L4 checksum value is correct, the test_pmd output log shows 'ol_flags' value is 'PKT_RX_L4_CKSUM_UNKNOWN', but expected value is 'PKT_RX_L4_CKSUM_GOOD'. Add the 'PKT_RX_L4_CKSUM_GOOD' to 'l3_l4e_flags' for sse and 'l3_l4_flags_shuf' for avx2 to ensure that the 'ol_flags' can match correct flags. Fixes: 9966a00a0688 ("net/i40e: enable bad checksum flags in vector Rx") Fixes: dafadd73762e ("net/i40e: add AVX2 Rx function") Signed-off-by: Murphy Yang <murphyx.yang@intel.com> --- drivers/net/i40e/i40e_rxtx_vec_avx2.c | 40 ++++++++++++++++----------- drivers/net/i40e/i40e_rxtx_vec_sse.c | 20 ++++++++------ 2 files changed, 35 insertions(+), 25 deletions(-)