[PATCH v2] common/mlx5: fix high SMMU TLB miss with mempool alignment

[Xingui Yang]

From: Shuaisong Yang <yangshuaisong at h-partners.com>

On Kunpeng SoC with mlx CX7, dpdk-l3fwd with intra-NUMA core pinning
under SMMU nonstrict/strict mode shows about 30% performance degradation
compared to cross-NUMA pinning. With SMMU disabled or passthrough mode,
intra-NUMA performs as expected (slightly better than cross-NUMA).

CX7 in NUMA1
NUMA node0 CPU(s):    0-39
NUMA node1 CPU(s):    40-79

intra-NUMA:
dpdk-l3fwd -l 40-55 -n 4 -a 0000:17:00.1,mprq_en=1 -- -p 0x1 -P \
   --config='(0,0,40),(0,1,41),(0,2,42),(0,3,43),(0,4,44),\
             (0,5,45),(0,6,46),(0,7,47),(0,8,48),(0,9,49),\
             (0,10,50),(0,11,51),(0,12,52),(0,13,53),\
             (0,14,54),(0,15,55)' \
   --rx-queue-size=4096 --tx-queue-size=4096 --rx-burst=64

cross-NUMA:
dpdk-l3fwd -l 11-26 -n 4 -a 0000:17:00.1,mprq_en=1 -- -p 0x1 -P \
   --config='(0,0,11),(0,1,12),(0,2,13),(0,3,14),(0,4,15),\
             (0,5,16),(0,6,17),(0,7,18),(0,8,19),(0,9,20),\
             (0,10,21),(0,11,22),(0,12,23),(0,13,24),\
             (0,14,25),(0,15,26)' \
   --rx-queue-size=4096 --tx-queue-size=4096 --rx-burst=64

The root cause is that under SMMU enabled mode, the mempool allocated
for intra-NUMA pinning is aligned to system page size instead of
hugepage size, while cross-NUMA pinning correctly uses hugepage size
alignment. This causes high TLB miss rates under SMMU.

Align all memory ranges to hugepage boundaries during mempool
registration to ensure hugepage_sz alignment, thereby reducing TLB
misses and fixing the intra-NUMA performance degradation.

Fixes: 690b2a88c2f7 ("common/mlx5: add mempool registration facilities")
Cc: stable at dpdk.org

Signed-off-by: Shuaisong Yang <yangshuaisong at h-partners.com>
Signed-off-by: Xingui Yang <yangxingui at huawei.com>
---
v2:
- Address review comments from Slava:
  - Call rte_mem_virt2memseg_list() in a single point inside the loop.
  - Skip the alignment block when hugepage_sz equals rte_mem_page_size(),
    since mlx5_mempool_get_chunks() has already done the alignment.
  - Skip the alignment for external memory with early goto, since ranges
    are already aligned to the correct page size.
---
 .mailmap                             |  1 +
 drivers/common/mlx5/mlx5_common_mr.c | 72 +++++++++++++++++++---------
 2 files changed, 51 insertions(+), 22 deletions(-)

diff --git a/.mailmap b/.mailmap
index fcb3d1bb3f..c8ba648d3c 100644
--- a/.mailmap
+++ b/.mailmap
@@ -1999,3 +1999,4 @@ Zongyu Wu <wuzongyu1 at huawei.com>
 Zorik Machulsky <zorik at amazon.com>
 Zyta Szpak <zyta at marvell.com> <zr at semihalf.com>
 Zyta Szpak <zyta at marvell.com> <zyta.szpak at semihalf.com>
+Shuaisong Yang <yangshuaisong at h-partners.com>
diff --git a/drivers/common/mlx5/mlx5_common_mr.c b/drivers/common/mlx5/mlx5_common_mr.c
index aa2d5e88a4..f9e1ec7468 100644
--- a/drivers/common/mlx5/mlx5_common_mr.c
+++ b/drivers/common/mlx5/mlx5_common_mr.c
@@ -1524,7 +1524,11 @@ mlx5_get_mempool_ranges(struct rte_mempool *mp, bool is_extmem,
  * @param[in] is_extmem
  *   Whether the pool is contains only external pinned buffers.
  * @param[out] out
- *   Receives memory ranges to register, aligned to the system page size.
+ *   Receives memory ranges to register. For non-external memory, ranges
+ *   are aligned to the hugepage size if all ranges are on hugepages
+ *   of the same size, otherwise aligned to the system page size.
+ *   For external memory, ranges are kept as returned by
+ *   mlx5_get_mempool_ranges() (already aligned to the page size).
  *   The caller must release them with free().
  * @param[out] out_n
  *   Receives the number of @p out items.
@@ -1541,7 +1545,8 @@ mlx5_mempool_reg_analyze(struct rte_mempool *mp, bool is_extmem,
 {
 	struct mlx5_range *ranges = NULL;
 	unsigned int i, ranges_n = 0;
-	struct rte_memseg_list *msl;
+	bool same_hugepage_sz = true;
+	uint64_t hugepage_sz = 0;
 
 	if (mlx5_get_mempool_ranges(mp, is_extmem, &ranges, &ranges_n) < 0) {
 		DRV_LOG(ERR, "Cannot get address ranges for mempool %s",
@@ -1550,34 +1555,57 @@ mlx5_mempool_reg_analyze(struct rte_mempool *mp, bool is_extmem,
 	}
 	/* Check if the hugepage of the pool can be shared. */
 	*share_hugepage = false;
-	msl = rte_mem_virt2memseg_list((void *)ranges[0].start);
-	if (msl != NULL) {
-		uint64_t hugepage_sz = 0;
+	if (is_extmem)
+		goto out;
+	/* Check that all ranges are on pages of the same size. */
+	for (i = 0; i < ranges_n; i++) {
+		struct rte_memseg_list *range_msl =
+			rte_mem_virt2memseg_list((void *)ranges[i].start);
+
+		if (range_msl == NULL) {
+			same_hugepage_sz = false;
+			break;
+		}
+		if (hugepage_sz == 0) {
+			hugepage_sz = range_msl->page_sz;
+		} else if (range_msl->page_sz != hugepage_sz) {
+			same_hugepage_sz = false;
+			break;
+		}
+	}
+	/*
+	 * Align ranges to the hugepage boundaries and merge adjacent ones.
+	 * If the entire pool fits in a single hugepage, the MR for this
+	 * hugepage can be shared across mempools.
+	 */
+	if (same_hugepage_sz && hugepage_sz > rte_mem_page_size()) {
+		unsigned int orig_ranges_n = ranges_n;
 
-		/* Check that all ranges are on pages of the same size. */
 		for (i = 0; i < ranges_n; i++) {
-			if (hugepage_sz != 0 && hugepage_sz != msl->page_sz)
-				break;
-			hugepage_sz = msl->page_sz;
+			ranges[i].start = RTE_ALIGN_FLOOR(ranges[i].start,
+							  hugepage_sz);
+			ranges[i].end = RTE_ALIGN_CEIL(ranges[i].end,
+							hugepage_sz);
 		}
-		if (i == ranges_n) {
-			/*
-			 * If the entire pool is within one hugepage,
-			 * combine all ranges into one of the hugepage size.
-			 */
-			uintptr_t reg_start = ranges[0].start;
-			uintptr_t reg_end = ranges[ranges_n - 1].end;
-			uintptr_t hugepage_start =
-				RTE_ALIGN_FLOOR(reg_start, hugepage_sz);
-			uintptr_t hugepage_end = hugepage_start + hugepage_sz;
-			if (reg_end < hugepage_end) {
-				ranges[0].start = hugepage_start;
+		ranges_n = 1;
+		for (i = 1; i < orig_ranges_n; i++) {
+			if (ranges[ranges_n - 1].end >= ranges[i].start)
+				ranges[ranges_n - 1].end =
+					RTE_MAX(ranges[ranges_n - 1].end,
+						ranges[i].end);
+			else
+				ranges[ranges_n++] = ranges[i];
+		}
+		if (ranges_n == 1) {
+			uintptr_t hugepage_end = ranges[0].start + hugepage_sz;
+
+			if (ranges[0].end <= hugepage_end) {
 				ranges[0].end = hugepage_end;
-				ranges_n = 1;
 				*share_hugepage = true;
 			}
 		}
 	}
+out:
 	*out = ranges;
 	*out_n = ranges_n;
 	return 0;
-- 
2.43.0