Claim pmd_supports_disable_iova_as_pa. Remove buf_iova access when
RTE_IOVA_AS_PA is not defined.
The patch simply replace buf_iova with buf_addr at IOVA as VA mode.
Some SIMD instructions in data path may be over used, further optimization
is expected.
Signed-off-by: Qi Zhang <qi.z.zh...@intel.com>
---
v2:
- fix title and commit log
- use rte_pktmbuf_iova
drivers/common/iavf/meson.build | 1 +
drivers/net/ice/ice_rxtx_common_avx.h | 24 ++++++++++++++++++++++++
drivers/net/ice/ice_rxtx_vec_avx2.c | 15 +++++----------
drivers/net/ice/ice_rxtx_vec_avx512.c | 20 ++++++++++----------
drivers/net/ice/ice_rxtx_vec_sse.c | 11 +++++++++--
drivers/net/ice/meson.build | 6 +++---
6 files changed, 52 insertions(+), 25 deletions(-)
diff --git a/drivers/common/iavf/meson.build b/drivers/common/iavf/meson.build
index 977652223b..af8a4983e0 100644
--- a/drivers/common/iavf/meson.build
+++ b/drivers/common/iavf/meson.build
@@ -6,3 +6,4 @@ sources = files('iavf_adminq.c', 'iavf_common.c', 'iavf_impl.c')
if cc.has_argument('-Wno-pointer-to-int-cast')
cflags += '-Wno-pointer-to-int-cast'
endif
+pmd_supports_disable_iova_as_pa = true
diff --git a/drivers/net/ice/ice_rxtx_common_avx.h
b/drivers/net/ice/ice_rxtx_common_avx.h
index 81e0db5dd3..e69e23997f 100644
--- a/drivers/net/ice/ice_rxtx_common_avx.h
+++ b/drivers/net/ice/ice_rxtx_common_avx.h
@@ -54,15 +54,23 @@ ice_rxq_rearm_common(struct ice_rx_queue *rxq, __rte_unused
bool avx512)
mb0 = rxep[0].mbuf;
mb1 = rxep[1].mbuf;
+#if RTE_IOVA_AS_PA
/* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */
RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
offsetof(struct rte_mbuf, buf_addr) + 8);
+#endif
vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
+#if RTE_IOVA_AS_PA
/* convert pa to dma_addr hdr/data */
dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1);
+#else
+ /* convert va to dma_addr hdr/data */
+ dma_addr0 = _mm_unpacklo_epi64(vaddr0, vaddr0);
+ dma_addr1 = _mm_unpacklo_epi64(vaddr1, vaddr1);
+#endif
/* add headroom to pa values */
dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
@@ -97,9 +105,11 @@ ice_rxq_rearm_common(struct ice_rx_queue *rxq, __rte_unused
bool avx512)
mb6 = rxep[6].mbuf;
mb7 = rxep[7].mbuf;
+#if RTE_IOVA_AS_PA
/* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */
RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
offsetof(struct rte_mbuf, buf_addr) +
8);
+#endif
vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
vaddr2 = _mm_loadu_si128((__m128i *)&mb2->buf_addr);
@@ -132,9 +142,15 @@ ice_rxq_rearm_common(struct ice_rx_queue *rxq,
__rte_unused bool avx512)
_mm512_inserti64x4(_mm512_castsi256_si512(vaddr4_5),
vaddr6_7, 1);
+#if RTE_IOVA_AS_PA
/* convert pa to dma_addr hdr/data */
dma_addr0_3 = _mm512_unpackhi_epi64(vaddr0_3, vaddr0_3);
dma_addr4_7 = _mm512_unpackhi_epi64(vaddr4_7, vaddr4_7);
+#else
+ /* convert va to dma_addr hdr/data */
+ dma_addr0_3 = _mm512_unpacklo_epi64(vaddr0_3, vaddr0_3);
+ dma_addr4_7 = _mm512_unpacklo_epi64(vaddr4_7, vaddr4_7);
+#endif
/* add headroom to pa values */
dma_addr0_3 = _mm512_add_epi64(dma_addr0_3, hdr_room);
@@ -161,9 +177,11 @@ ice_rxq_rearm_common(struct ice_rx_queue *rxq,
__rte_unused bool avx512)
mb2 = rxep[2].mbuf;
mb3 = rxep[3].mbuf;
+#if RTE_IOVA_AS_PA
/* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */
RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
offsetof(struct rte_mbuf, buf_addr) +
8);
+#endif
vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
vaddr2 = _mm_loadu_si128((__m128i *)&mb2->buf_addr);
@@ -180,9 +198,15 @@ ice_rxq_rearm_common(struct ice_rx_queue *rxq,
__rte_unused bool avx512)
_mm256_inserti128_si256(_mm256_castsi128_si256(vaddr2),
vaddr3, 1);
+#if RTE_IOVA_AS_PA
/* convert pa to dma_addr hdr/data */
dma_addr0_1 = _mm256_unpackhi_epi64(vaddr0_1, vaddr0_1);
dma_addr2_3 = _mm256_unpackhi_epi64(vaddr2_3, vaddr2_3);
+#else
+ /* convert va to dma_addr hdr/data */
+ dma_addr0_1 = _mm256_unpacklo_epi64(vaddr0_1, vaddr0_1);
+ dma_addr2_3 = _mm256_unpacklo_epi64(vaddr2_3, vaddr2_3);
+#endif
/* add headroom to pa values */
dma_addr0_1 = _mm256_add_epi64(dma_addr0_1, hdr_room);
diff --git a/drivers/net/ice/ice_rxtx_vec_avx2.c
b/drivers/net/ice/ice_rxtx_vec_avx2.c
index 31d6af42fd..fd13ff18f1 100644
--- a/drivers/net/ice/ice_rxtx_vec_avx2.c
+++ b/drivers/net/ice/ice_rxtx_vec_avx2.c
@@ -821,8 +821,7 @@ ice_vtx1(volatile struct ice_tx_desc *txdp,
if (offload)
ice_txd_enable_offload(pkt, &high_qw);
- __m128i descriptor = _mm_set_epi64x(high_qw,
- pkt->buf_iova + pkt->data_off);
+ __m128i descriptor = _mm_set_epi64x(high_qw, rte_pktmbuf_iova(pkt));
_mm_store_si128((__m128i *)txdp, descriptor);
}
@@ -868,16 +867,12 @@ ice_vtx(volatile struct ice_tx_desc *txdp,
__m256i desc2_3 =
_mm256_set_epi64x
- (hi_qw3,
- pkt[3]->buf_iova + pkt[3]->data_off,
- hi_qw2,
- pkt[2]->buf_iova + pkt[2]->data_off);
+ (hi_qw3, rte_pktmbuf_iova(pkt[3]),
+ hi_qw2, rte_pktmbuf_iova(pkt[2]));
__m256i desc0_1 =
_mm256_set_epi64x
- (hi_qw1,
- pkt[1]->buf_iova + pkt[1]->data_off,
- hi_qw0,
- pkt[0]->buf_iova + pkt[0]->data_off);
+ (hi_qw1, rte_pktmbuf_iova(pkt[1]),
+ hi_qw0, rte_pktmbuf_iova(pkt[0]));
_mm256_store_si256((void *)(txdp + 2), desc2_3);
_mm256_store_si256((void *)txdp, desc0_1);
}
diff --git a/drivers/net/ice/ice_rxtx_vec_avx512.c
b/drivers/net/ice/ice_rxtx_vec_avx512.c
index 5bfd5152df..7e388b7569 100644
--- a/drivers/net/ice/ice_rxtx_vec_avx512.c
+++ b/drivers/net/ice/ice_rxtx_vec_avx512.c
@@ -56,8 +56,13 @@ ice_rxq_rearm(struct ice_rx_queue *rxq)
}
}
+#if RTE_IOVA_AS_PA
const __m512i iova_offsets = _mm512_set1_epi64
(offsetof(struct rte_mbuf, buf_iova));
+#else
+ const __m512i iova_offsets = _mm512_set1_epi64
+ (offsetof(struct rte_mbuf, buf_addr));
+#endif
const __m512i headroom = _mm512_set1_epi64(RTE_PKTMBUF_HEADROOM);
#ifndef RTE_LIBRTE_ICE_16BYTE_RX_DESC
@@ -1092,8 +1097,7 @@ ice_vtx1(volatile struct ice_tx_desc *txdp,
if (do_offload)
ice_txd_enable_offload(pkt, &high_qw);
- __m128i descriptor = _mm_set_epi64x(high_qw,
- pkt->buf_iova + pkt->data_off);
+ __m128i descriptor = _mm_set_epi64x(high_qw, rte_pktmbuf_iova(pkt));
_mm_store_si128((__m128i *)txdp, descriptor);
}
@@ -1132,14 +1136,10 @@ ice_vtx(volatile struct ice_tx_desc *txdp, struct
rte_mbuf **pkt,
__m512i desc0_3 =
_mm512_set_epi64
- (hi_qw3,
- pkt[3]->buf_iova + pkt[3]->data_off,
- hi_qw2,
- pkt[2]->buf_iova + pkt[2]->data_off,
- hi_qw1,
- pkt[1]->buf_iova + pkt[1]->data_off,
- hi_qw0,
- pkt[0]->buf_iova + pkt[0]->data_off);
+ (hi_qw3, rte_pktmbuf_iova(pkt[3]),
+ hi_qw2, rte_pktmbuf_iova(pkt[2]),
+ hi_qw1, rte_pktmbuf_iova(pkt[1]),
+ hi_qw0, rte_pktmbuf_iova(pkt[0]));
_mm512_storeu_si512((void *)txdp, desc0_3);
}
diff --git a/drivers/net/ice/ice_rxtx_vec_sse.c
b/drivers/net/ice/ice_rxtx_vec_sse.c
index fd94cedde3..72dfd58308 100644
--- a/drivers/net/ice/ice_rxtx_vec_sse.c
+++ b/drivers/net/ice/ice_rxtx_vec_sse.c
@@ -68,15 +68,23 @@ ice_rxq_rearm(struct ice_rx_queue *rxq)
mb0 = rxep[0].mbuf;
mb1 = rxep[1].mbuf;
+#if RTE_IOVA_AS_PA
/* load buf_addr(lo 64bit) and buf_iova(hi 64bit) */
RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
offsetof(struct rte_mbuf, buf_addr) + 8);
+#endif
vaddr0 = _mm_loadu_si128((__m128i *)&mb0->buf_addr);
vaddr1 = _mm_loadu_si128((__m128i *)&mb1->buf_addr);
+#if RTE_IOVA_AS_PA
/* convert pa to dma_addr hdr/data */
dma_addr0 = _mm_unpackhi_epi64(vaddr0, vaddr0);
dma_addr1 = _mm_unpackhi_epi64(vaddr1, vaddr1);
+#else
+ /* convert va to dma_addr hdr/data */
+ dma_addr0 = _mm_unpacklo_epi64(vaddr0, vaddr0);
+ dma_addr1 = _mm_unpacklo_epi64(vaddr1, vaddr1);
+#endif
/* add headroom to pa values */
dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
@@ -671,8 +679,7 @@ ice_vtx1(volatile struct ice_tx_desc *txdp, struct rte_mbuf
*pkt,
((uint64_t)flags << ICE_TXD_QW1_CMD_S) |
((uint64_t)pkt->data_len << ICE_TXD_QW1_TX_BUF_SZ_S));
- __m128i descriptor = _mm_set_epi64x(high_qw,
- pkt->buf_iova + pkt->data_off);
+ __m128i descriptor = _mm_set_epi64x(high_qw, rte_pktmbuf_iova(pkt));
_mm_store_si128((__m128i *)txdp, descriptor);
}
diff --git a/drivers/net/ice/meson.build b/drivers/net/ice/meson.build
index 8efa533e0b..123b190f72 100644
--- a/drivers/net/ice/meson.build
+++ b/drivers/net/ice/meson.build
@@ -20,7 +20,6 @@ testpmd_sources = files('ice_testpmd.c')
deps += ['hash', 'net', 'common_iavf']
includes += include_directories('base', '../../common/iavf')
-iova_as_pa = dpdk_conf.get('RTE_IOVA_AS_PA')
if arch_subdir == 'x86'
sources += files('ice_rxtx_vec_sse.c')
@@ -35,7 +34,7 @@ if arch_subdir == 'x86'
if cc.get_define('__AVX2__', args: machine_args) != ''
cflags += ['-DCC_AVX2_SUPPORT']
sources += files('ice_rxtx_vec_avx2.c')
- elif iova_as_pa == 1 and cc.has_argument('-mavx2')
+ elif cc.has_argument('-mavx2')
cflags += ['-DCC_AVX2_SUPPORT']
ice_avx2_lib = static_library('ice_avx2_lib',
'ice_rxtx_vec_avx2.c',
@@ -56,7 +55,7 @@ if arch_subdir == 'x86'
cc.has_argument('-mavx512bw')
)
- if iova_as_pa == 1 and (ice_avx512_cpu_support == true or
ice_avx512_cc_support == true)
+ if ice_avx512_cpu_support == true or ice_avx512_cc_support == true
cflags += ['-DCC_AVX512_SUPPORT']
avx512_args = [cflags, '-mavx512f', '-mavx512bw']
if cc.has_argument('-march=skylake-avx512')
@@ -79,3 +78,4 @@ sources += files(
'ice_dcf_parent.c',
'ice_dcf_sched.c',
)
+pmd_supports_disable_iova_as_pa = true
--
2.31.1
