summaryrefslogtreecommitdiff
path: root/mm/rmap.c
diff options
context:
space:
mode:
authorHuang Ying <ying.huang@intel.com>2023-02-13 20:34:43 +0800
committerAndrew Morton <akpm@linux-foundation.org>2023-02-16 20:43:54 -0800
commit7e12beb8ca2ac98b2ec42e0ea4b76cdc93b58654 (patch)
tree694ad429670e3e57ca95c76029b7ff386dc64e07 /mm/rmap.c
parentebe75e4751063dce6f61b579b43de86dcf7b7462 (diff)
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" <ying.huang@intel.com> Tested-by: Xin Hao <xhao@linux.alibaba.com> Reviewed-by: Zi Yan <ziy@nvidia.com> Reviewed-by: Xin Hao <xhao@linux.alibaba.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> Cc: Bharata B Rao <bharata@amd.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/rmap.c')
-rw-r--r--mm/rmap.c20
1 files changed, 17 insertions, 3 deletions
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) &&