From 72e315f7a750281b4410ac30d8930f735459e72d Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 3 Oct 2023 02:27:47 -0700 Subject: mempolicy: mmap_lock is not needed while migrating folios mbind(2) holds down_write of current task's mmap_lock throughout (exclusive because it needs to set the new mempolicy on the vmas); migrate_pages(2) holds down_read of pid's mmap_lock throughout. They both hold mmap_lock across the internal migrate_pages(), under which all new page allocations (huge or small) are made. I'm nervous about it; and migrate_pages() certainly does not need mmap_lock itself. It's done this way for mbind(2), because its page allocator is vma_alloc_folio() or alloc_hugetlb_folio_vma(), both of which depend on vma and address. Now that we have alloc_pages_mpol(), depending on (refcounted) memory policy and interleave index, mbind(2) can be modified to use that or alloc_hugetlb_folio_nodemask(), and then not need mmap_lock across the internal migrate_pages() at all: add alloc_migration_target_by_mpol() to replace mbind's new_page(). (After that change, alloc_hugetlb_folio_vma() is used by nothing but a userfaultfd function: move it out of hugetlb.h and into the #ifdef.) migrate_pages(2) has chosen its target node before migrating, so can continue to use the standard alloc_migration_target(); but let it take and drop mmap_lock just around migrate_to_node()'s queue_pages_range(): neither the node-to-node calculations nor the page migrations need it. It seems unlikely, but it is conceivable that some userspace depends on the kernel's mmap_lock exclusion here, instead of doing its own locking: more likely in a testsuite than in real life. It is also possible, of course, that some pages on the list will be munmapped by another thread before they are migrated, or a newer memory policy applied to the range by that time: but such races could happen before, as soon as mmap_lock was dropped, so it does not appear to be a concern. Link: https://lkml.kernel.org/r/21e564e8-269f-6a89-7ee2-fd612831c289@google.com Signed-off-by: Hugh Dickins Cc: Andi Kleen Cc: Christoph Lameter Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Huang, Ying" Cc: Kefeng Wang Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Mike Kravetz Cc: Nhat Pham Cc: Sidhartha Kumar Cc: Suren Baghdasaryan Cc: Tejun heo Cc: Vishal Moola (Oracle) Cc: Yang Shi Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/hugetlb.c | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dd8065e36038..1169ef2f2176 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2630,24 +2630,6 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } -/* mempolicy aware migration callback */ -struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address) -{ - struct mempolicy *mpol; - nodemask_t *nodemask; - struct folio *folio; - gfp_t gfp_mask; - int node; - - gfp_mask = htlb_alloc_mask(h); - node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask); - mpol_cond_put(mpol); - - return folio; -} - /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. @@ -6559,6 +6541,26 @@ out_mutex: } #ifdef CONFIG_USERFAULTFD +/* + * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte(). + */ +static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) +{ + struct mempolicy *mpol; + nodemask_t *nodemask; + struct folio *folio; + gfp_t gfp_mask; + int node; + + gfp_mask = htlb_alloc_mask(h); + node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); + folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask); + mpol_cond_put(mpol); + + return folio; +} + /* * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. -- cgit v1.2.3