From 025e9fd9523f1a6595b1013b578f3d079a813ec7 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 2 Jun 2025 11:25:33 +0800 Subject: [PATCH] mm: mincore: use pte_batch_hint() to batch process large folios mainline inclusion from mainline-v6.16-rc1 commit 4df65651f7075481e44c03bb39855a38783d87ac category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IC8P47 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4df65651f7075481e44c03bb39855a38783d87ac -------------------------------- When I tested the mincore() syscall, I observed that it takes longer with 64K mTHP enabled on my Arm64 server. The reason is the mincore_pte_range() still checks each PTE individually, even when the PTEs are contiguous, which is not efficient. Thus we can use pte_batch_hint() to get the batch number of the present contiguous PTEs, which can improve the performance. I tested the mincore() syscall with 1G anonymous memory populated with 64K mTHP, and observed an obvious performance improvement: w/o patch w/ patch changes 6022us 549us +91% Moreover, I also tested mincore() with disabling mTHP/THP, and did not see any obvious regression for base pages. Link: https://lkml.kernel.org/r/99cb00ee626ceb6e788102ca36821815cd832237.1746697240.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Barry Song Reviewed-by: Dev Jain Acked-by: David Hildenbrand Cc: Dev Jain Cc: Ryan Roberts Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Wang Lian --- mm/mincore.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/mm/mincore.c b/mm/mincore.c index dad3622cc963..d56a2d379291 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -21,6 +21,7 @@ #include #include "swap.h" +#include "internal.h" static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -105,6 +106,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t *ptep; unsigned char *vec = walk->private; int nr = (end - addr) >> PAGE_SHIFT; + int step, i; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { @@ -118,16 +120,26 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, walk->action = ACTION_AGAIN; return 0; } - for (; addr != end; ptep++, addr += PAGE_SIZE) { + for (; addr != end; ptep += step, addr += step * PAGE_SIZE) { pte_t pte = ptep_get(ptep); + step = 1; /* We need to do cache lookup too for pte markers */ if (pte_none_mostly(pte)) __mincore_unmapped_range(addr, addr + PAGE_SIZE, vma, vec); - else if (pte_present(pte)) - *vec = 1; - else { /* pte is a swap entry */ + else if (pte_present(pte)) { + unsigned int batch = pte_batch_hint(ptep, pte); + + if (batch > 1) { + unsigned int max_nr = (end - addr) >> PAGE_SHIFT; + + step = min_t(unsigned int, batch, max_nr); + } + + for (i = 0; i < step; i++) + vec[i] = 1; + } else { /* pte is a swap entry */ swp_entry_t entry = pte_to_swp_entry(pte); if (non_swap_entry(entry)) { @@ -146,7 +158,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, #endif } } - vec++; + vec += step; } pte_unmap_unlock(ptep - 1, ptl); out: -- Gitee