[PATCH v2 3/3] drivers/net: add diagnostics macros to make code portable

[Andre Muezerie <andremue@linux.microsoft.com>]

It was a common pattern to have "GCC diagnostic ignored" pragmas
sprinkled over the code and only activate these pragmas for certain
compilers (gcc and clang). Clang supports GCC's pragma for
compatibility with existing source code, so #pragma GCC diagnostic
and #pragma clang diagnostic are synonyms for Clang
(https://clang.llvm.org/docs/UsersManual.html).

Now that effort is being made to make the code compatible with MSVC
these expressions would become more complex. It makes sense to hide
this complexity behind macros. This makes maintenance easier as these
macros are defined in a single place. As a plus the code becomes
more readable as well.

Signed-off-by: Andre Muezerie <andremue@linux.microsoft.com>
---
 drivers/net/axgbe/axgbe_rxtx.h                |  9 ------
 drivers/net/cpfl/cpfl_rxtx_vec_common.h       |  4 ---
 drivers/net/dpaa2/dpaa2_rxtx.c                | 16 ++--------
 drivers/net/fm10k/fm10k_rxtx_vec.c            | 19 +++++++++---
 drivers/net/hns3/hns3_rxtx_vec_neon.h         |  2 --
 .../net/i40e/i40e_recycle_mbufs_vec_common.c  |  2 --
 drivers/net/i40e/i40e_rxtx_common_avx.h       | 10 ++++---
 drivers/net/i40e/i40e_rxtx_vec_altivec.c      |  2 --
 drivers/net/i40e/i40e_rxtx_vec_avx2.c         | 16 +++++++---
 drivers/net/i40e/i40e_rxtx_vec_avx512.c       | 16 +++++++---
 drivers/net/i40e/i40e_rxtx_vec_common.h       |  4 ---
 drivers/net/i40e/i40e_rxtx_vec_neon.c         |  3 --
 drivers/net/i40e/i40e_rxtx_vec_sse.c          | 22 +++++++++++---
 drivers/net/iavf/iavf_rxtx_vec_avx2.c         | 21 +++++++++----
 drivers/net/iavf/iavf_rxtx_vec_avx512.c       | 27 +++++++++++++----
 drivers/net/iavf/iavf_rxtx_vec_common.h       | 10 ++++---
 drivers/net/iavf/iavf_rxtx_vec_sse.c          | 30 +++++++++++++++----
 drivers/net/ice/ice_rxtx_common_avx.h         | 10 ++++---
 drivers/net/ice/ice_rxtx_vec_avx2.c           | 16 +++++++---
 drivers/net/ice/ice_rxtx_vec_avx512.c         | 16 +++++++---
 drivers/net/ice/ice_rxtx_vec_common.h         |  4 ---
 drivers/net/ice/ice_rxtx_vec_sse.c            | 22 +++++++++++---
 drivers/net/idpf/idpf_rxtx_vec_common.h       |  4 ---
 .../ixgbe/ixgbe_recycle_mbufs_vec_common.c    |  2 --
 drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c       |  2 --
 drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c        | 19 +++++++++---
 drivers/net/mlx5/mlx5_flow.c                  |  6 ++--
 drivers/net/mlx5/mlx5_rxtx_vec_altivec.h      |  5 ----
 drivers/net/mlx5/mlx5_rxtx_vec_neon.h         |  2 --
 drivers/net/mlx5/mlx5_rxtx_vec_sse.h          |  4 ---
 drivers/net/tap/tap_flow.c                    |  6 ++--
 drivers/net/virtio/virtio_rxtx_simple.c       |  4 ---
 32 files changed, 204 insertions(+), 131 deletions(-)

diff --git a/drivers/net/axgbe/axgbe_rxtx.h b/drivers/net/axgbe/axgbe_rxtx.h
index a326ba9ac8..f5f74a0a39 100644
--- a/drivers/net/axgbe/axgbe_rxtx.h
+++ b/drivers/net/axgbe/axgbe_rxtx.h
@@ -6,15 +6,6 @@
 #ifndef _AXGBE_RXTX_H_
 #define _AXGBE_RXTX_H_
 
-/* to suppress gcc warnings related to descriptor casting*/
-#ifdef RTE_TOOLCHAIN_GCC
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
-#ifdef RTE_TOOLCHAIN_CLANG
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 /* Descriptor related defines */
 #define AXGBE_MAX_RING_DESC		4096 /*should be power of 2*/
 #define AXGBE_TX_DESC_MIN_FREE		(AXGBE_MAX_RING_DESC >> 3)
diff --git a/drivers/net/cpfl/cpfl_rxtx_vec_common.h b/drivers/net/cpfl/cpfl_rxtx_vec_common.h
index 479e1ddcb9..5b98f86932 100644
--- a/drivers/net/cpfl/cpfl_rxtx_vec_common.h
+++ b/drivers/net/cpfl/cpfl_rxtx_vec_common.h
@@ -11,10 +11,6 @@
 #include "cpfl_ethdev.h"
 #include "cpfl_rxtx.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 #define CPFL_SCALAR_PATH		0
 #define CPFL_VECTOR_PATH		1
 #define CPFL_RX_NO_VECTOR_FLAGS (		\
diff --git a/drivers/net/dpaa2/dpaa2_rxtx.c b/drivers/net/dpaa2/dpaa2_rxtx.c
index e3b6c7e460..21c306fd94 100644
--- a/drivers/net/dpaa2/dpaa2_rxtx.c
+++ b/drivers/net/dpaa2/dpaa2_rxtx.c
@@ -1962,14 +1962,6 @@ dpaa2_dev_tx_ordered(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
 	return num_tx;
 }
 
-#if defined(RTE_TOOLCHAIN_GCC)
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#elif defined(RTE_TOOLCHAIN_CLANG)
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Wcast-qual"
-#endif
-
 /* This function loopbacks all the received packets.*/
 uint16_t
 dpaa2_dev_loopback_rx(void *queue,
@@ -2083,7 +2075,10 @@ dpaa2_dev_loopback_rx(void *queue,
 			if (unlikely((status & QBMAN_DQ_STAT_VALIDFRAME) == 0))
 				continue;
 		}
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		fd[num_rx] = (struct qbman_fd *)qbman_result_DQ_fd(dq_storage);
+__rte_diagnostic_pop
 
 		dq_storage++;
 		num_rx++;
@@ -2118,8 +2113,3 @@ dpaa2_dev_loopback_rx(void *queue,
 
 	return 0;
 }
-#if defined(RTE_TOOLCHAIN_GCC)
-#pragma GCC diagnostic pop
-#elif defined(RTE_TOOLCHAIN_CLANG)
-#pragma clang diagnostic pop
-#endif
diff --git a/drivers/net/fm10k/fm10k_rxtx_vec.c b/drivers/net/fm10k/fm10k_rxtx_vec.c
index 68acaca75b..3d534a91ac 100644
--- a/drivers/net/fm10k/fm10k_rxtx_vec.c
+++ b/drivers/net/fm10k/fm10k_rxtx_vec.c
@@ -11,10 +11,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static void
 fm10k_reset_tx_queue(struct fm10k_tx_queue *txq);
 
@@ -270,8 +266,11 @@ fm10k_rxq_rearm(struct fm10k_rx_queue *rxq)
 		/* Clean up all the HW/SW ring content */
 		for (i = 0; i < RTE_FM10K_RXQ_REARM_THRESH; i++) {
 			mb_alloc[i] = &rxq->fake_mbuf;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 			_mm_store_si128((__m128i *)&rxdp[i].q,
 						dma_addr0);
+__rte_diagnostic_pop
 		}
 
 		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
@@ -316,8 +315,11 @@ fm10k_rxq_rearm(struct fm10k_rx_queue *rxq)
 		dma_addr1 = _mm_and_si128(dma_addr1, hba_msk);
 
 		/* flush desc with pa dma_addr */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm_store_si128((__m128i *)&rxdp++->q, dma_addr0);
 		_mm_store_si128((__m128i *)&rxdp++->q, dma_addr1);
+__rte_diagnostic_pop
 
 		/* enforce 512B alignment on default Rx virtual addresses */
 		mb0->data_off = (uint16_t)(RTE_PTR_ALIGN((char *)mb0->buf_addr
@@ -465,7 +467,10 @@ fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 
 		/* Read desc statuses backwards to avoid race condition */
 		/* A.1 load desc[3] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs0[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+__rte_diagnostic_pop
 		rte_compiler_barrier();
 
 		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
@@ -477,11 +482,14 @@ fm10k_recv_raw_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 #endif
 
 		/* A.1 load desc[2-0] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs0[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
 		descs0[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs0[0] = _mm_loadu_si128((__m128i *)(rxdp));
+__rte_diagnostic_pop
 
 #if defined(RTE_ARCH_X86_64)
 		/* B.2 copy 2 mbuf point into rx_pkts  */
@@ -736,7 +744,10 @@ vtx1(volatile struct fm10k_tx_desc *txdp,
 	__m128i descriptor = _mm_set_epi64x(flags << 56 |
 			(uint64_t)pkt->vlan_tci << 16 | (uint64_t)pkt->data_len,
 			MBUF_DMA_ADDR(pkt));
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static inline void
diff --git a/drivers/net/hns3/hns3_rxtx_vec_neon.h b/drivers/net/hns3/hns3_rxtx_vec_neon.h
index bbb5478015..5297087085 100644
--- a/drivers/net/hns3/hns3_rxtx_vec_neon.h
+++ b/drivers/net/hns3/hns3_rxtx_vec_neon.h
@@ -9,8 +9,6 @@
 
 #include <arm_neon.h>
 
-#pragma GCC diagnostic ignored "-Wcast-qual"
-
 static inline void
 hns3_vec_tx(volatile struct hns3_desc *desc, struct rte_mbuf *pkt)
 {
diff --git a/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c b/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c
index 14424c9921..6eafe51e3d 100644
--- a/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c
+++ b/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c
@@ -10,8 +10,6 @@
 #include "i40e_ethdev.h"
 #include "i40e_rxtx.h"
 
-#pragma GCC diagnostic ignored "-Wcast-qual"
-
 void
 i40e_recycle_rx_descriptors_refill_vec(void *rx_queue, uint16_t nb_mbufs)
 {
diff --git a/drivers/net/i40e/i40e_rxtx_common_avx.h b/drivers/net/i40e/i40e_rxtx_common_avx.h
index 85958d6c81..97e3ab6845 100644
--- a/drivers/net/i40e/i40e_rxtx_common_avx.h
+++ b/drivers/net/i40e/i40e_rxtx_common_avx.h
@@ -11,10 +11,6 @@
 #include "i40e_ethdev.h"
 #include "i40e_rxtx.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 #ifdef __AVX2__
 static __rte_always_inline void
 i40e_rxq_rearm_common(struct i40e_rx_queue *rxq, __rte_unused bool avx512)
@@ -36,8 +32,11 @@ i40e_rxq_rearm_common(struct i40e_rx_queue *rxq, __rte_unused bool avx512)
 			dma_addr0 = _mm_setzero_si128();
 			for (i = 0; i < RTE_I40E_DESCS_PER_LOOP; i++) {
 				rxep[i].mbuf = &rxq->fake_mbuf;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				_mm_store_si128((__m128i *)&rxdp[i].read,
 						dma_addr0);
+__rte_diagnostic_pop
 			}
 		}
 		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
@@ -72,8 +71,11 @@ i40e_rxq_rearm_common(struct i40e_rx_queue *rxq, __rte_unused bool avx512)
 		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
 
 		/* flush desc with pa dma_addr */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+__rte_diagnostic_pop
 	}
 #else
 #ifdef __AVX512VL__
diff --git a/drivers/net/i40e/i40e_rxtx_vec_altivec.c b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
index b6b0d38ec1..02d930a7f2 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_altivec.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_altivec.c
@@ -15,8 +15,6 @@
 
 #include <rte_altivec.h>
 
-#pragma GCC diagnostic ignored "-Wcast-qual"
-
 static inline void
 i40e_rxq_rearm(struct i40e_rx_queue *rxq)
 {
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx2.c b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
index 19cf0ac718..90a1d4661a 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
@@ -15,10 +15,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static __rte_always_inline void
 i40e_rxq_rearm(struct i40e_rx_queue *rxq)
 {
@@ -39,8 +35,11 @@ desc_fdir_processing_32b(volatile union i40e_rx_desc *rxdp,
 			 const uint32_t desc_idx)
 {
 	/* 32B desc path: load rxdp.wb.qword2 for EXT_STATUS and FLEXBH_STAT */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	__m128i *rxdp_desc_0 = (void *)(&rxdp[desc_idx + 0].wb.qword2);
 	__m128i *rxdp_desc_1 = (void *)(&rxdp[desc_idx + 1].wb.qword2);
+__rte_diagnostic_pop
 	const __m128i desc_qw2_0 = _mm_load_si128(rxdp_desc_0);
 	const __m128i desc_qw2_1 = _mm_load_si128(rxdp_desc_1);
 
@@ -276,6 +275,8 @@ _recv_raw_pkts_vec_avx2(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 				_mm256_loadu_si256((void *)&sw_ring[i + 4]));
 #endif
 
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		const __m128i raw_desc7 = _mm_load_si128((void *)(rxdp + 7));
 		rte_compiler_barrier();
 		const __m128i raw_desc6 = _mm_load_si128((void *)(rxdp + 6));
@@ -291,6 +292,7 @@ _recv_raw_pkts_vec_avx2(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		const __m128i raw_desc1 = _mm_load_si128((void *)(rxdp + 1));
 		rte_compiler_barrier();
 		const __m128i raw_desc0 = _mm_load_si128((void *)(rxdp + 0));
+__rte_diagnostic_pop
 
 		const __m256i raw_desc6_7 = _mm256_inserti128_si256(
 				_mm256_castsi128_si256(raw_desc6), raw_desc7, 1);
@@ -695,7 +697,10 @@ vtx1(volatile struct i40e_tx_desc *txdp,
 
 	__m128i descriptor = _mm_set_epi64x(high_qw,
 				pkt->buf_iova + pkt->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static inline void
@@ -728,8 +733,11 @@ vtx(volatile struct i40e_tx_desc *txdp,
 		__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);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm256_store_si256((void *)(txdp + 2), desc2_3);
 		_mm256_store_si256((void *)txdp, desc0_1);
+__rte_diagnostic_pop
 	}
 
 	/* do any last ones */
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx512.c b/drivers/net/i40e/i40e_rxtx_vec_avx512.c
index 3b2750221b..b77989074f 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx512.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx512.c
@@ -15,10 +15,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 #define RTE_I40E_DESCS_PER_LOOP_AVX 8
 
 static __rte_always_inline void
@@ -41,8 +37,11 @@ desc_fdir_processing_32b(volatile union i40e_rx_desc *rxdp,
 			 const uint32_t desc_idx)
 {
 	/* 32B desc path: load rxdp.wb.qword2 for EXT_STATUS and FLEXBH_STAT */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	__m128i *rxdp_desc_0 = (void *)(&rxdp[desc_idx + 0].wb.qword2);
 	__m128i *rxdp_desc_1 = (void *)(&rxdp[desc_idx + 1].wb.qword2);
+__rte_diagnostic_pop
 	const __m128i desc_qw2_0 = _mm_load_si128(rxdp_desc_0);
 	const __m128i desc_qw2_1 = _mm_load_si128(rxdp_desc_1);
 
@@ -263,6 +262,8 @@ _recv_raw_pkts_vec_avx512(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		__m256i raw_desc0_1, raw_desc2_3, raw_desc4_5, raw_desc6_7;
 
 		/* load in descriptors, in reverse order */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		const __m128i raw_desc7 =
 			_mm_load_si128((void *)(rxdp + 7));
 		rte_compiler_barrier();
@@ -286,6 +287,7 @@ _recv_raw_pkts_vec_avx512(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		rte_compiler_barrier();
 		const __m128i raw_desc0 =
 			_mm_load_si128((void *)(rxdp + 0));
+__rte_diagnostic_pop
 
 		raw_desc6_7 =
 			_mm256_inserti128_si256
@@ -875,7 +877,10 @@ vtx1(volatile struct i40e_tx_desc *txdp, struct rte_mbuf *pkt, uint64_t flags)
 
 	__m128i descriptor = _mm_set_epi64x(high_qw,
 				pkt->buf_iova + pkt->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static inline void
@@ -909,7 +914,10 @@ vtx(volatile struct i40e_tx_desc *txdp,
 			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);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm512_storeu_si512((void *)txdp, desc0_3);
+__rte_diagnostic_pop
 	}
 
 	/* do any last ones */
diff --git a/drivers/net/i40e/i40e_rxtx_vec_common.h b/drivers/net/i40e/i40e_rxtx_vec_common.h
index 8b745630e4..ec59a68f9d 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_common.h
+++ b/drivers/net/i40e/i40e_rxtx_vec_common.h
@@ -11,10 +11,6 @@
 #include "i40e_ethdev.h"
 #include "i40e_rxtx.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static inline uint16_t
 reassemble_packets(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_bufs,
 		   uint16_t nb_bufs, uint8_t *split_flags)
diff --git a/drivers/net/i40e/i40e_rxtx_vec_neon.c b/drivers/net/i40e/i40e_rxtx_vec_neon.c
index e1c5c7041b..f056f40dee 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_neon.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_neon.c
@@ -16,9 +16,6 @@
 #include "i40e_rxtx.h"
 #include "i40e_rxtx_vec_common.h"
 
-
-#pragma GCC diagnostic ignored "-Wcast-qual"
-
 static inline void
 i40e_rxq_rearm(struct i40e_rx_queue *rxq)
 {
diff --git a/drivers/net/i40e/i40e_rxtx_vec_sse.c b/drivers/net/i40e/i40e_rxtx_vec_sse.c
index ad560d2b6b..8a5537bcf2 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_sse.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_sse.c
@@ -14,10 +14,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static inline void
 i40e_rxq_rearm(struct i40e_rx_queue *rxq)
 {
@@ -41,8 +37,11 @@ i40e_rxq_rearm(struct i40e_rx_queue *rxq)
 			dma_addr0 = _mm_setzero_si128();
 			for (i = 0; i < RTE_I40E_DESCS_PER_LOOP; i++) {
 				rxep[i].mbuf = &rxq->fake_mbuf;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				_mm_store_si128((__m128i *)&rxdp[i].read,
 						dma_addr0);
+__rte_diagnostic_pop
 			}
 		}
 		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
@@ -72,8 +71,11 @@ i40e_rxq_rearm(struct i40e_rx_queue *rxq)
 		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
 
 		/* flush desc with pa dma_addr */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+__rte_diagnostic_pop
 	}
 
 	rxq->rxrearm_start += RTE_I40E_RXQ_REARM_THRESH;
@@ -97,10 +99,13 @@ descs_to_fdir_32b(volatile union i40e_rx_desc *rxdp, struct rte_mbuf **rx_pkt)
 {
 	/* 32B descriptors: Load 2nd half of descriptors for FDIR ID data */
 	__m128i desc0_qw23, desc1_qw23, desc2_qw23, desc3_qw23;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	desc0_qw23 = _mm_loadu_si128((__m128i *)&(rxdp + 0)->wb.qword2);
 	desc1_qw23 = _mm_loadu_si128((__m128i *)&(rxdp + 1)->wb.qword2);
 	desc2_qw23 = _mm_loadu_si128((__m128i *)&(rxdp + 2)->wb.qword2);
 	desc3_qw23 = _mm_loadu_si128((__m128i *)&(rxdp + 3)->wb.qword2);
+__rte_diagnostic_pop
 
 	/* FDIR ID data: move last u32 of each desc to 4 u32 lanes */
 	__m128i v_unpack_01, v_unpack_23;
@@ -462,7 +467,10 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
 		/* Read desc statuses backwards to avoid race condition */
 		/* A.1 load desc[3] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+__rte_diagnostic_pop
 		rte_compiler_barrier();
 
 		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
@@ -474,11 +482,14 @@ _recv_raw_pkts_vec(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 #endif
 
 		/* A.1 load desc[2-0] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
+__rte_diagnostic_pop
 
 #if defined(RTE_ARCH_X86_64)
 		/* B.2 copy 2 mbuf point into rx_pkts  */
@@ -681,7 +692,10 @@ vtx1(volatile struct i40e_tx_desc *txdp,
 
 	__m128i descriptor = _mm_set_epi64x(high_qw,
 				pkt->buf_iova + pkt->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static inline void
diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx2.c b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
index 49d41af953..f5503d9dae 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx2.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
@@ -6,10 +6,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static __rte_always_inline void
 iavf_rxq_rearm(struct iavf_rx_queue *rxq)
 {
@@ -193,6 +189,8 @@ _iavf_recv_raw_pkts_vec_avx2(struct iavf_rx_queue *rxq,
 			 _mm256_loadu_si256((void *)&sw_ring[i + 4]));
 #endif
 
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		const __m128i raw_desc7 = _mm_load_si128((void *)(rxdp + 7));
 		rte_compiler_barrier();
 		const __m128i raw_desc6 = _mm_load_si128((void *)(rxdp + 6));
@@ -208,6 +206,7 @@ _iavf_recv_raw_pkts_vec_avx2(struct iavf_rx_queue *rxq,
 		const __m128i raw_desc1 = _mm_load_si128((void *)(rxdp + 1));
 		rte_compiler_barrier();
 		const __m128i raw_desc0 = _mm_load_si128((void *)(rxdp + 0));
+__rte_diagnostic_pop
 
 		const __m256i raw_desc6_7 =
 			_mm256_inserti128_si256(_mm256_castsi128_si256(raw_desc6), raw_desc7, 1);
@@ -509,7 +508,7 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq,
 			0, rxq->mbuf_initializer);
 	struct rte_mbuf **sw_ring = &rxq->sw_ring[rxq->rx_tail];
 	volatile union iavf_rx_flex_desc *rxdp =
-		(union iavf_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
+		(volatile union iavf_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
 
 	rte_prefetch0(rxdp);
 
@@ -742,6 +741,8 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq,
 
 		__m256i raw_desc0_1, raw_desc2_3, raw_desc4_5, raw_desc6_7;
 
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		const __m128i raw_desc7 =
 			_mm_load_si128((void *)(rxdp + 7));
 		rte_compiler_barrier();
@@ -765,6 +766,7 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq,
 		rte_compiler_barrier();
 		const __m128i raw_desc0 =
 			_mm_load_si128((void *)(rxdp + 0));
+__rte_diagnostic_pop
 
 		raw_desc6_7 =
 			_mm256_inserti128_si256
@@ -959,6 +961,8 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq,
 				offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP ||
 			    rxq->rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
 				/* load bottom half of every 32B desc */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				const __m128i raw_desc_bh7 =
 					_mm_load_si128
 						((void *)(&rxdp[7].wb.status_error1));
@@ -990,6 +994,7 @@ _iavf_recv_raw_pkts_vec_avx2_flex_rxd(struct iavf_rx_queue *rxq,
 				const __m128i raw_desc_bh0 =
 					_mm_load_si128
 						((void *)(&rxdp[0].wb.status_error1));
+__rte_diagnostic_pop
 
 				__m256i raw_desc_bh6_7 =
 					_mm256_inserti128_si256
@@ -1664,7 +1669,10 @@ iavf_vtx1(volatile struct iavf_tx_desc *txdp,
 
 	__m128i descriptor = _mm_set_epi64x(high_qw,
 				pkt->buf_iova + pkt->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static __rte_always_inline void
@@ -1719,8 +1727,11 @@ iavf_vtx(volatile struct iavf_tx_desc *txdp,
 				 pkt[1]->buf_iova + pkt[1]->data_off,
 				 hi_qw0,
 				 pkt[0]->buf_iova + pkt[0]->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm256_store_si256((void *)(txdp + 2), desc2_3);
 		_mm256_store_si256((void *)txdp, desc0_1);
+__rte_diagnostic_pop
 	}
 
 	/* do any last ones */
diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx512.c b/drivers/net/iavf/iavf_rxtx_vec_avx512.c
index d6a861bf80..04894debc8 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx512.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx512.c
@@ -6,10 +6,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 #define IAVF_DESCS_PER_LOOP_AVX 8
 #define PKTLEN_SHIFT 10
 
@@ -164,6 +160,8 @@ _iavf_recv_raw_pkts_vec_avx512(struct iavf_rx_queue *rxq,
 #endif
 
 		__m512i raw_desc0_3, raw_desc4_7;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		const __m128i raw_desc7 =
 			_mm_load_si128((void *)(rxdp + 7));
 		rte_compiler_barrier();
@@ -187,6 +185,7 @@ _iavf_recv_raw_pkts_vec_avx512(struct iavf_rx_queue *rxq,
 		rte_compiler_barrier();
 		const __m128i raw_desc0 =
 			_mm_load_si128((void *)(rxdp + 0));
+__rte_diagnostic_pop
 
 		raw_desc4_7 = _mm512_broadcast_i32x4(raw_desc4);
 		raw_desc4_7 = _mm512_inserti32x4(raw_desc4_7, raw_desc5, 1);
@@ -600,7 +599,7 @@ _iavf_recv_raw_pkts_vec_avx512_flex_rxd(struct iavf_rx_queue *rxq,
 						    rxq->mbuf_initializer);
 	struct rte_mbuf **sw_ring = &rxq->sw_ring[rxq->rx_tail];
 	volatile union iavf_rx_flex_desc *rxdp =
-		(union iavf_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
+		(volatile union iavf_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
 
 	rte_prefetch0(rxdp);
 
@@ -733,6 +732,8 @@ _iavf_recv_raw_pkts_vec_avx512_flex_rxd(struct iavf_rx_queue *rxq,
 
 		__m512i raw_desc0_3, raw_desc4_7;
 
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		const __m128i raw_desc7 =
 			_mm_load_si128((void *)(rxdp + 7));
 		rte_compiler_barrier();
@@ -756,6 +757,7 @@ _iavf_recv_raw_pkts_vec_avx512_flex_rxd(struct iavf_rx_queue *rxq,
 		rte_compiler_barrier();
 		const __m128i raw_desc0 =
 			_mm_load_si128((void *)(rxdp + 0));
+__rte_diagnostic_pop
 
 		raw_desc4_7 = _mm512_broadcast_i32x4(raw_desc4);
 		raw_desc4_7 = _mm512_inserti32x4(raw_desc4_7, raw_desc5, 1);
@@ -1111,6 +1113,8 @@ _iavf_recv_raw_pkts_vec_avx512_flex_rxd(struct iavf_rx_queue *rxq,
 				offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP ||
 			    rxq->rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
 				/* load bottom half of every 32B desc */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				const __m128i raw_desc_bh7 =
 					_mm_load_si128
 						((void *)(&rxdp[7].wb.status_error1));
@@ -1142,6 +1146,7 @@ _iavf_recv_raw_pkts_vec_avx512_flex_rxd(struct iavf_rx_queue *rxq,
 				const __m128i raw_desc_bh0 =
 					_mm_load_si128
 						((void *)(&rxdp[0].wb.status_error1));
+__rte_diagnostic_pop
 
 				__m256i raw_desc_bh6_7 =
 					_mm256_inserti128_si256
@@ -1983,7 +1988,10 @@ iavf_vtx1(volatile struct iavf_tx_desc *txdp,
 
 	__m128i descriptor = _mm_set_epi64x(high_qw,
 					    pkt->buf_iova + pkt->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_storeu_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 #define IAVF_TX_LEN_MASK 0xAA
@@ -2037,7 +2045,10 @@ iavf_vtx(volatile struct iavf_tx_desc *txdp,
 				 pkt[1]->buf_iova + pkt[1]->data_off,
 				 hi_qw0,
 				 pkt[0]->buf_iova + pkt[0]->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm512_storeu_si512((void *)txdp, desc0_3);
+__rte_diagnostic_pop
 	}
 
 	/* do any last ones */
@@ -2225,7 +2236,10 @@ ctx_vtx1(volatile struct iavf_tx_desc *txdp, struct rte_mbuf *pkt,
 	__m256i ctx_data_desc = _mm256_set_epi64x(high_data_qw, pkt->buf_iova + pkt->data_off,
 							high_ctx_qw, low_ctx_qw);
 
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm256_storeu_si256((__m256i *)txdp, ctx_data_desc);
+__rte_diagnostic_pop
 }
 
 static __rte_always_inline void
@@ -2300,7 +2314,10 @@ ctx_vtx(volatile struct iavf_tx_desc *txdp,
 						hi_ctx_qw1, low_ctx_qw1,
 						hi_data_qw0, pkt[0]->buf_iova + pkt[0]->data_off,
 						hi_ctx_qw0, low_ctx_qw0);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm512_storeu_si512((void *)txdp, desc0_3);
+__rte_diagnostic_pop
 	}
 
 	if (nb_pkts)
diff --git a/drivers/net/iavf/iavf_rxtx_vec_common.h b/drivers/net/iavf/iavf_rxtx_vec_common.h
index 5c5220048d..690e0749e4 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_common.h
+++ b/drivers/net/iavf/iavf_rxtx_vec_common.h
@@ -11,10 +11,6 @@
 #include "iavf.h"
 #include "iavf_rxtx.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static __rte_always_inline uint16_t
 reassemble_packets(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_bufs,
 		   uint16_t nb_bufs, uint8_t *split_flags)
@@ -422,8 +418,11 @@ iavf_rxq_rearm_common(struct iavf_rx_queue *rxq, __rte_unused bool avx512)
 			dma_addr0 = _mm_setzero_si128();
 			for (i = 0; i < IAVF_VPMD_DESCS_PER_LOOP; i++) {
 				rxp[i] = &rxq->fake_mbuf;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				_mm_store_si128((__m128i *)&rxdp[i].read,
 						dma_addr0);
+__rte_diagnostic_pop
 			}
 		}
 		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
@@ -458,8 +457,11 @@ iavf_rxq_rearm_common(struct iavf_rx_queue *rxq, __rte_unused bool avx512)
 		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
 
 		/* flush desc with pa dma_addr */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+__rte_diagnostic_pop
 	}
 #else
 #ifdef CC_AVX512_SUPPORT
diff --git a/drivers/net/iavf/iavf_rxtx_vec_sse.c b/drivers/net/iavf/iavf_rxtx_vec_sse.c
index 0db6fa8bd4..373df0c935 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_sse.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_sse.c
@@ -12,10 +12,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static inline void
 iavf_rxq_rearm(struct iavf_rx_queue *rxq)
 {
@@ -38,8 +34,11 @@ iavf_rxq_rearm(struct iavf_rx_queue *rxq)
 			dma_addr0 = _mm_setzero_si128();
 			for (i = 0; i < IAVF_VPMD_DESCS_PER_LOOP; i++) {
 				rxp[i] = &rxq->fake_mbuf;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				_mm_store_si128((__m128i *)&rxdp[i].read,
 						dma_addr0);
+__rte_diagnostic_pop
 			}
 		}
 		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
@@ -69,8 +68,11 @@ iavf_rxq_rearm(struct iavf_rx_queue *rxq)
 		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
 
 		/* flush desc with pa dma_addr */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+__rte_diagnostic_pop
 	}
 
 	rxq->rxrearm_start += rxq->rx_free_thresh;
@@ -578,7 +580,10 @@ _recv_raw_pkts_vec(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
 		/* Read desc statuses backwards to avoid race condition */
 		/* A.1 load desc[3] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+__rte_diagnostic_pop
 		rte_compiler_barrier();
 
 		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
@@ -590,11 +595,14 @@ _recv_raw_pkts_vec(struct iavf_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 #endif
 
 		/* A.1 load desc[2-0] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
+__rte_diagnostic_pop
 
 #if defined(RTE_ARCH_X86_64)
 		/* B.2 copy 2 mbuf point into rx_pkts  */
@@ -783,7 +791,7 @@ _recv_raw_pkts_vec_flex_rxd(struct iavf_rx_queue *rxq,
 	/* Just the act of getting into the function from the application is
 	 * going to cost about 7 cycles
 	 */
-	rxdp = (union iavf_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
+	rxdp = (volatile union iavf_rx_flex_desc *)rxq->rx_ring + rxq->rx_tail;
 
 	rte_prefetch0(rxdp);
 
@@ -864,7 +872,10 @@ _recv_raw_pkts_vec_flex_rxd(struct iavf_rx_queue *rxq,
 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
 		/* Read desc statuses backwards to avoid race condition */
 		/* A.1 load desc[3] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+__rte_diagnostic_pop
 		rte_compiler_barrier();
 
 		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
@@ -876,11 +887,14 @@ _recv_raw_pkts_vec_flex_rxd(struct iavf_rx_queue *rxq,
 #endif
 
 		/* A.1 load desc[2-0] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
+__rte_diagnostic_pop
 
 #if defined(RTE_ARCH_X86_64)
 		/* B.2 copy 2 mbuf point into rx_pkts  */
@@ -927,6 +941,8 @@ _recv_raw_pkts_vec_flex_rxd(struct iavf_rx_queue *rxq,
 			offloads & RTE_ETH_RX_OFFLOAD_TIMESTAMP ||
 			rxq->rx_flags & IAVF_RX_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
 			/* load bottom half of every 32B desc */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 			descs_bh[3] = _mm_load_si128
 					((void *)(&rxdp[3].wb.status_error1));
 			rte_compiler_barrier();
@@ -938,6 +954,7 @@ _recv_raw_pkts_vec_flex_rxd(struct iavf_rx_queue *rxq,
 			rte_compiler_barrier();
 			descs_bh[0] = _mm_load_si128
 					((void *)(&rxdp[0].wb.status_error1));
+__rte_diagnostic_pop
 		}
 
 		if (offloads & RTE_ETH_RX_OFFLOAD_RSS_HASH) {
@@ -1349,7 +1366,10 @@ vtx1(volatile struct iavf_tx_desc *txdp, struct rte_mbuf *pkt, uint64_t flags)
 
 	__m128i descriptor = _mm_set_epi64x(high_qw,
 					    pkt->buf_iova + pkt->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static inline void
diff --git a/drivers/net/ice/ice_rxtx_common_avx.h b/drivers/net/ice/ice_rxtx_common_avx.h
index dacb87dcb0..b9cb1f5279 100644
--- a/drivers/net/ice/ice_rxtx_common_avx.h
+++ b/drivers/net/ice/ice_rxtx_common_avx.h
@@ -7,10 +7,6 @@
 
 #include "ice_rxtx.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 #ifdef __AVX2__
 static __rte_always_inline void
 ice_rxq_rearm_common(struct ice_rx_queue *rxq, __rte_unused bool avx512)
@@ -33,8 +29,11 @@ ice_rxq_rearm_common(struct ice_rx_queue *rxq, __rte_unused bool avx512)
 			dma_addr0 = _mm_setzero_si128();
 			for (i = 0; i < ICE_DESCS_PER_LOOP; i++) {
 				rxep[i].mbuf = &rxq->fake_mbuf;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				_mm_store_si128((__m128i *)&rxdp[i].read,
 						dma_addr0);
+__rte_diagnostic_pop
 			}
 		}
 		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
@@ -77,8 +76,11 @@ ice_rxq_rearm_common(struct ice_rx_queue *rxq, __rte_unused bool avx512)
 		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
 
 		/* flush desc with pa dma_addr */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+__rte_diagnostic_pop
 	}
 #else
 #ifdef __AVX512VL__
diff --git a/drivers/net/ice/ice_rxtx_vec_avx2.c b/drivers/net/ice/ice_rxtx_vec_avx2.c
index d6e88dbb29..6c6a810a15 100644
--- a/drivers/net/ice/ice_rxtx_vec_avx2.c
+++ b/drivers/net/ice/ice_rxtx_vec_avx2.c
@@ -7,10 +7,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static __rte_always_inline void
 ice_rxq_rearm(struct ice_rx_queue *rxq)
 {
@@ -254,6 +250,8 @@ _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 			 _mm256_loadu_si256((void *)&sw_ring[i + 4]));
 #endif
 
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		const __m128i raw_desc7 = _mm_load_si128((void *)(rxdp + 7));
 		rte_compiler_barrier();
 		const __m128i raw_desc6 = _mm_load_si128((void *)(rxdp + 6));
@@ -269,6 +267,7 @@ _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		const __m128i raw_desc1 = _mm_load_si128((void *)(rxdp + 1));
 		rte_compiler_barrier();
 		const __m128i raw_desc0 = _mm_load_si128((void *)(rxdp + 0));
+__rte_diagnostic_pop
 
 		const __m256i raw_desc6_7 =
 			_mm256_inserti128_si256(_mm256_castsi128_si256(raw_desc6), raw_desc7, 1);
@@ -444,6 +443,8 @@ _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 			if (rxq->vsi->adapter->pf.dev_data->dev_conf.rxmode.offloads &
 					RTE_ETH_RX_OFFLOAD_RSS_HASH) {
 				/* load bottom half of every 32B desc */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				const __m128i raw_desc_bh7 =
 					_mm_load_si128
 						((void *)(&rxdp[7].wb.status_error1));
@@ -475,6 +476,7 @@ _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 				const __m128i raw_desc_bh0 =
 					_mm_load_si128
 						((void *)(&rxdp[0].wb.status_error1));
+__rte_diagnostic_pop
 
 				__m256i raw_desc_bh6_7 =
 					_mm256_inserti128_si256
@@ -790,7 +792,10 @@ ice_vtx1(volatile struct ice_tx_desc *txdp,
 		ice_txd_enable_offload(pkt, &high_qw);
 
 	__m128i descriptor = _mm_set_epi64x(high_qw, rte_pktmbuf_iova(pkt));
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static __rte_always_inline void
@@ -841,8 +846,11 @@ ice_vtx(volatile struct ice_tx_desc *txdp,
 			_mm256_set_epi64x
 				(hi_qw1, rte_pktmbuf_iova(pkt[1]),
 				 hi_qw0, rte_pktmbuf_iova(pkt[0]));
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm256_store_si256((void *)(txdp + 2), desc2_3);
 		_mm256_store_si256((void *)txdp, desc0_1);
+__rte_diagnostic_pop
 	}
 
 	/* do any last ones */
diff --git a/drivers/net/ice/ice_rxtx_vec_avx512.c b/drivers/net/ice/ice_rxtx_vec_avx512.c
index add095ef06..5a774550dc 100644
--- a/drivers/net/ice/ice_rxtx_vec_avx512.c
+++ b/drivers/net/ice/ice_rxtx_vec_avx512.c
@@ -7,10 +7,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 #define ICE_DESCS_PER_LOOP_AVX 8
 
 static __rte_always_inline void
@@ -243,6 +239,8 @@ _ice_recv_raw_pkts_vec_avx512(struct ice_rx_queue *rxq,
 		__m256i raw_desc0_1, raw_desc2_3, raw_desc4_5, raw_desc6_7;
 
 		/* load in descriptors, in reverse order */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		const __m128i raw_desc7 =
 			_mm_load_si128((void *)(rxdp + 7));
 		rte_compiler_barrier();
@@ -266,6 +264,7 @@ _ice_recv_raw_pkts_vec_avx512(struct ice_rx_queue *rxq,
 		rte_compiler_barrier();
 		const __m128i raw_desc0 =
 			_mm_load_si128((void *)(rxdp + 0));
+__rte_diagnostic_pop
 
 		raw_desc6_7 =
 			_mm256_inserti128_si256
@@ -474,6 +473,8 @@ _ice_recv_raw_pkts_vec_avx512(struct ice_rx_queue *rxq,
 			if (rxq->vsi->adapter->pf.dev_data->dev_conf.rxmode.offloads &
 					RTE_ETH_RX_OFFLOAD_RSS_HASH) {
 				/* load bottom half of every 32B desc */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				const __m128i raw_desc_bh7 =
 					_mm_load_si128
 						((void *)(&rxdp[7].wb.status_error1));
@@ -505,6 +506,7 @@ _ice_recv_raw_pkts_vec_avx512(struct ice_rx_queue *rxq,
 				const __m128i raw_desc_bh0 =
 					_mm_load_si128
 						((void *)(&rxdp[0].wb.status_error1));
+__rte_diagnostic_pop
 
 				__m256i raw_desc_bh6_7 =
 					_mm256_inserti128_si256
@@ -987,7 +989,10 @@ ice_vtx1(volatile struct ice_tx_desc *txdp,
 		ice_txd_enable_offload(pkt, &high_qw);
 
 	__m128i descriptor = _mm_set_epi64x(high_qw, rte_pktmbuf_iova(pkt));
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static __rte_always_inline void
@@ -1029,7 +1034,10 @@ ice_vtx(volatile struct ice_tx_desc *txdp, struct rte_mbuf **pkt,
 				 hi_qw2, rte_pktmbuf_iova(pkt[2]),
 				 hi_qw1, rte_pktmbuf_iova(pkt[1]),
 				 hi_qw0, rte_pktmbuf_iova(pkt[0]));
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm512_storeu_si512((void *)txdp, desc0_3);
+__rte_diagnostic_pop
 	}
 
 	/* do any last ones */
diff --git a/drivers/net/ice/ice_rxtx_vec_common.h b/drivers/net/ice/ice_rxtx_vec_common.h
index 4b73465af5..45147decff 100644
--- a/drivers/net/ice/ice_rxtx_vec_common.h
+++ b/drivers/net/ice/ice_rxtx_vec_common.h
@@ -7,10 +7,6 @@
 
 #include "ice_rxtx.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static inline uint16_t
 ice_rx_reassemble_packets(struct ice_rx_queue *rxq, struct rte_mbuf **rx_bufs,
 			  uint16_t nb_bufs, uint8_t *split_flags)
diff --git a/drivers/net/ice/ice_rxtx_vec_sse.c b/drivers/net/ice/ice_rxtx_vec_sse.c
index c01d8ede29..f2991cee1a 100644
--- a/drivers/net/ice/ice_rxtx_vec_sse.c
+++ b/drivers/net/ice/ice_rxtx_vec_sse.c
@@ -6,10 +6,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static inline __m128i
 ice_flex_rxd_to_fdir_flags_vec(const __m128i fdir_id0_3)
 {
@@ -52,8 +48,11 @@ ice_rxq_rearm(struct ice_rx_queue *rxq)
 			dma_addr0 = _mm_setzero_si128();
 			for (i = 0; i < ICE_DESCS_PER_LOOP; i++) {
 				rxep[i].mbuf = &rxq->fake_mbuf;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				_mm_store_si128((__m128i *)&rxdp[i].read,
 						dma_addr0);
+__rte_diagnostic_pop
 			}
 		}
 		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
@@ -91,8 +90,11 @@ ice_rxq_rearm(struct ice_rx_queue *rxq)
 		dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
 
 		/* flush desc with pa dma_addr */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+__rte_diagnostic_pop
 	}
 
 	rxq->rxrearm_start += ICE_RXQ_REARM_THRESH;
@@ -425,7 +427,10 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		mbp1 = _mm_loadu_si128((__m128i *)&sw_ring[pos]);
 		/* Read desc statuses backwards to avoid race condition */
 		/* A.1 load desc[3] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+__rte_diagnostic_pop
 		rte_compiler_barrier();
 
 		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
@@ -437,11 +442,14 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 #endif
 
 		/* A.1 load desc[2-0] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
+__rte_diagnostic_pop
 
 #if defined(RTE_ARCH_X86_64)
 		/* B.2 copy 2 mbuf point into rx_pkts  */
@@ -489,6 +497,8 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		if (rxq->vsi->adapter->pf.dev_data->dev_conf.rxmode.offloads &
 				RTE_ETH_RX_OFFLOAD_RSS_HASH) {
 			/* load bottom half of every 32B desc */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 			const __m128i raw_desc_bh3 =
 				_mm_load_si128
 					((void *)(&rxdp[3].wb.status_error1));
@@ -504,6 +514,7 @@ _ice_recv_raw_pkts_vec(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 			const __m128i raw_desc_bh0 =
 				_mm_load_si128
 					((void *)(&rxdp[0].wb.status_error1));
+__rte_diagnostic_pop
 
 			/**
 			 * to shift the 32b RSS hash value to the
@@ -680,7 +691,10 @@ ice_vtx1(volatile struct ice_tx_desc *txdp, struct rte_mbuf *pkt,
 		 ((uint64_t)pkt->data_len << ICE_TXD_QW1_TX_BUF_SZ_S));
 
 	__m128i descriptor = _mm_set_epi64x(high_qw, rte_pktmbuf_iova(pkt));
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)txdp, descriptor);
+__rte_diagnostic_pop
 }
 
 static inline void
diff --git a/drivers/net/idpf/idpf_rxtx_vec_common.h b/drivers/net/idpf/idpf_rxtx_vec_common.h
index 2787d27616..002c1e6948 100644
--- a/drivers/net/idpf/idpf_rxtx_vec_common.h
+++ b/drivers/net/idpf/idpf_rxtx_vec_common.h
@@ -11,10 +11,6 @@
 #include "idpf_ethdev.h"
 #include "idpf_rxtx.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 #define IDPF_SCALAR_PATH		0
 #define IDPF_VECTOR_PATH		1
 #define IDPF_RX_NO_VECTOR_FLAGS (		\
diff --git a/drivers/net/ixgbe/ixgbe_recycle_mbufs_vec_common.c b/drivers/net/ixgbe/ixgbe_recycle_mbufs_vec_common.c
index d451562269..92a89f8def 100644
--- a/drivers/net/ixgbe/ixgbe_recycle_mbufs_vec_common.c
+++ b/drivers/net/ixgbe/ixgbe_recycle_mbufs_vec_common.c
@@ -8,8 +8,6 @@
 #include "ixgbe_ethdev.h"
 #include "ixgbe_rxtx.h"
 
-#pragma GCC diagnostic ignored "-Wcast-qual"
-
 void
 ixgbe_recycle_rx_descriptors_refill_vec(void *rx_queue, uint16_t nb_mbufs)
 {
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
index 952b032eb6..4e7a64b39f 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c
@@ -11,8 +11,6 @@
 #include "ixgbe_rxtx.h"
 #include "ixgbe_rxtx_vec_common.h"
 
-#pragma GCC diagnostic ignored "-Wcast-qual"
-
 static inline void
 ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq)
 {
diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
index a77370cdb7..8e4048a32f 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx_vec_sse.c
@@ -12,10 +12,6 @@
 
 #include <rte_vect.h>
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 static inline void
 ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq)
 {
@@ -41,8 +37,11 @@ ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq)
 			dma_addr0 = _mm_setzero_si128();
 			for (i = 0; i < RTE_IXGBE_DESCS_PER_LOOP; i++) {
 				rxep[i].mbuf = &rxq->fake_mbuf;
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 				_mm_store_si128((__m128i *)&rxdp[i].read,
 						dma_addr0);
+__rte_diagnostic_pop
 			}
 		}
 		rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
@@ -76,8 +75,11 @@ ixgbe_rxq_rearm(struct ixgbe_rx_queue *rxq)
 		dma_addr1 =  _mm_and_si128(dma_addr1, hba_msk);
 
 		/* flush desc with pa dma_addr */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr0);
 		_mm_store_si128((__m128i *)&rxdp++->read, dma_addr1);
+__rte_diagnostic_pop
 	}
 
 	rxq->rxrearm_start += RTE_IXGBE_RXQ_REARM_THRESH;
@@ -466,7 +468,10 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 
 		/* Read desc statuses backwards to avoid race condition */
 		/* A.1 load desc[3] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[3] = _mm_loadu_si128((__m128i *)(rxdp + 3));
+__rte_diagnostic_pop
 		rte_compiler_barrier();
 
 		/* B.2 copy 2 64 bit or 4 32 bit mbuf point into rx_pkts */
@@ -478,11 +483,14 @@ _recv_raw_pkts_vec(struct ixgbe_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 #endif
 
 		/* A.1 load desc[2-0] */
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 		descs[2] = _mm_loadu_si128((__m128i *)(rxdp + 2));
 		rte_compiler_barrier();
 		descs[1] = _mm_loadu_si128((__m128i *)(rxdp + 1));
 		rte_compiler_barrier();
 		descs[0] = _mm_loadu_si128((__m128i *)(rxdp));
+__rte_diagnostic_pop
 
 #if defined(RTE_ARCH_X86_64)
 		/* B.2 copy 2 mbuf point into rx_pkts  */
@@ -676,7 +684,10 @@ vtx1(volatile union ixgbe_adv_tx_desc *txdp,
 	__m128i descriptor = _mm_set_epi64x((uint64_t)pkt->pkt_len << 46 |
 			flags | pkt->data_len,
 			pkt->buf_iova + pkt->data_off);
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	_mm_store_si128((__m128i *)&txdp->read, descriptor);
+__rte_diagnostic_pop
 }
 
 static inline void
diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
index 16ddd05448..0a89d2c414 100644
--- a/drivers/net/mlx5/mlx5_flow.c
+++ b/drivers/net/mlx5/mlx5_flow.c
@@ -7287,10 +7287,10 @@ flow_tunnel_from_rule(const struct mlx5_flow *flow)
 {
 	struct mlx5_flow_tunnel *tunnel;
 
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wcast-qual"
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 	tunnel = (typeof(tunnel))flow->tunnel;
-#pragma GCC diagnostic pop
+__rte_diagnostic_pop
 
 	return tunnel;
 }
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h b/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
index 240987d03d..b37483bcca 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_altivec.h
@@ -25,11 +25,6 @@
 #include "mlx5_rxtx_vec.h"
 #include "mlx5_autoconf.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#pragma GCC diagnostic ignored "-Wstrict-aliasing"
-#endif
-
 /**
  * Store free buffers to RX SW ring.
  *
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
index dc1d30753d..e7deacc1fb 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
@@ -25,8 +25,6 @@
 #include "mlx5_rxtx_vec.h"
 #include "mlx5_autoconf.h"
 
-#pragma GCC diagnostic ignored "-Wcast-qual"
-
 /**
  * Store free buffers to RX SW ring.
  *
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
index 81a177fce7..55c23dac80 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
@@ -24,10 +24,6 @@
 #include "mlx5_rxtx_vec.h"
 #include "mlx5_autoconf.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 /**
  * Store free buffers to RX SW ring.
  *
diff --git a/drivers/net/tap/tap_flow.c b/drivers/net/tap/tap_flow.c
index c0e44bb1a7..373b773e2d 100644
--- a/drivers/net/tap/tap_flow.c
+++ b/drivers/net/tap/tap_flow.c
@@ -23,10 +23,10 @@
 
 #ifdef HAVE_BPF_RSS
 /* Workaround for warning in bpftool generated skeleton code */
-#pragma GCC diagnostic push
-#pragma GCC diagnostic ignored "-Wcast-qual"
+__rte_diagnostic_push
+__rte_diagnostic_ignored_wcast_qual
 #include "tap_rss.skel.h"
-#pragma GCC diagnostic pop
+__rte_diagnostic_pop
 #endif
 
 #define ISOLATE_HANDLE 1
diff --git a/drivers/net/virtio/virtio_rxtx_simple.c b/drivers/net/virtio/virtio_rxtx_simple.c
index 438256970d..439e00a7e1 100644
--- a/drivers/net/virtio/virtio_rxtx_simple.c
+++ b/drivers/net/virtio/virtio_rxtx_simple.c
@@ -23,10 +23,6 @@
 
 #include "virtio_rxtx_simple.h"
 
-#ifndef __INTEL_COMPILER
-#pragma GCC diagnostic ignored "-Wcast-qual"
-#endif
-
 int __rte_cold
 virtio_rxq_vec_setup(struct virtnet_rx *rxq)
 {
-- 
2.47.0.vfs.0.3