@@ -1179,7 +1179,7 @@ static int migrate_page_unmap(new_page_t get_new_page, free_page_t put_new_page,
/* Establish migration ptes */
VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
page);
- try_to_migrate(folio, 0);
+ try_to_migrate(folio, TTU_BATCH_FLUSH);
page_was_mapped = 1;
}
@@ -1647,6 +1647,8 @@ static int migrate_pages_batch(struct list_head *from, new_page_t get_new_page,
nr_thp_failed += thp_retry;
nr_failed_pages += nr_retry_pages;
move:
+ try_to_unmap_flush();
+
retry = 1;
thp_retry = 1;
for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
@@ -1960,8 +1960,24 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
pteval = huge_ptep_clear_flush(vma, address, pvmw.pte);
} else {
flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
- /* Nuke the page table entry. */
- pteval = ptep_clear_flush(vma, address, pvmw.pte);
+ /*
+ * Nuke the page table entry.
+ */
+ 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. */
@@ -2128,10 +2144,10 @@ 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) &&
The TLB flushing will cost quite some CPU cycles during the page migration in some situations. For example, when migrate a page 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%. Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Cc: Zi Yan <ziy@nvidia.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Matthew Wilcox <willy@infradead.org> --- mm/migrate.c | 4 +++- mm/rmap.c | 24 ++++++++++++++++++++---- 2 files changed, 23 insertions(+), 5 deletions(-)