From 7e12beb8ca2ac98b2ec42e0ea4b76cdc93b58654 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 13 Feb 2023 20:34:43 +0800 Subject: migrate_pages: batch flushing TLB The TLB flushing will cost quite some CPU cycles during the folio migration in some situations. For example, when migrate a folio of a process with multiple active threads that run on multiple CPUs. After batching the _unmap and _move in migrate_pages(), the TLB flushing can be batched easily with the existing TLB flush batching mechanism. This patch implements that. We use the following test case to test the patch. On a 2-socket Intel server, - Run pmbench memory accessing benchmark - Run `migratepages` to migrate pages of pmbench between node 0 and node 1 back and forth. With the patch, the TLB flushing IPI reduces 99.1% during the test and the number of pages migrated successfully per second increases 291.7%. Haoxin helped to test the patchset on an ARM64 server with 128 cores, 2 NUMA nodes. Test results show that the page migration performance increases up to 78%. NOTE: TLB flushing is batched only for normal folios, not for THP folios. Because the overhead of TLB flushing for THP folios is much lower than that for normal folios (about 1/512 on x86 platform). Link: https://lkml.kernel.org/r/20230213123444.155149-9-ying.huang@intel.com Signed-off-by: "Huang, Ying" Tested-by: Xin Hao Reviewed-by: Zi Yan Reviewed-by: Xin Hao Cc: Yang Shi Cc: Baolin Wang Cc: Oscar Salvador Cc: Matthew Wilcox Cc: Bharata B Rao Cc: Alistair Popple Cc: Minchan Kim Cc: Mike Kravetz Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Andrew Morton --- mm/migrate.c | 5 ++++- mm/rmap.c | 20 +++++++++++++++++--- 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index 00713ccb6643..2fa420e4f68c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1248,7 +1248,7 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page /* Establish migration ptes */ VM_BUG_ON_FOLIO(folio_test_anon(src) && !folio_test_ksm(src) && !anon_vma, src); - try_to_migrate(src, 0); + try_to_migrate(src, TTU_BATCH_FLUSH); page_was_mapped = 1; } @@ -1806,6 +1806,9 @@ retry: stats->nr_thp_failed += thp_retry; stats->nr_failed_pages += nr_retry_pages; move: + /* Flush TLBs for all unmapped folios */ + try_to_unmap_flush(); + retry = 1; for (pass = 0; pass < NR_MAX_MIGRATE_PAGES_RETRY && (retry || large_retry); diff --git a/mm/rmap.c b/mm/rmap.c index 8287f2cc327d..15ae24585fc4 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1952,7 +1952,21 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, } else { flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); /* Nuke the page table entry. */ - pteval = ptep_clear_flush(vma, address, pvmw.pte); + if (should_defer_flush(mm, flags)) { + /* + * We clear the PTE but do not flush so potentially + * a remote CPU could still be writing to the folio. + * If the entry was previously clean then the + * architecture must guarantee that a clear->dirty + * transition on a cached TLB entry is written through + * and traps if the PTE is unmapped. + */ + pteval = ptep_get_and_clear(mm, address, pvmw.pte); + + set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); + } else { + pteval = ptep_clear_flush(vma, address, pvmw.pte); + } } /* Set the dirty flag on the folio now the pte is gone. */ @@ -2124,10 +2138,10 @@ void try_to_migrate(struct folio *folio, enum ttu_flags flags) /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and - * TTU_SPLIT_HUGE_PMD and TTU_SYNC flags. + * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | - TTU_SYNC))) + TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && -- cgit v1.2.3