From: David Hildenbrand david@redhat.com

mainline inclusion from mainline-v6.7-rc1 commit fd63908706f79c963946a77b7f352db5431deed5 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Patch series "Anon rmap cleanups".

Some cleanups around rmap for anon pages. I'm working on more cleanups also around file rmap -- also to handle the "compound" parameter internally only and to let hugetlb use page_add_file_rmap(), but these changes make sense separately.

This patch (of 6):

That comment was added in commit 5dbe0af47f8a ("mm: fix kernel BUG at mm/rmap.c:1017!") to document why we can see vma->vm_end getting adjusted concurrently due to a VMA split.

However, the optimized locking code was changed again in bf181b9f9d8 ("mm anon rmap: replace same_anon_vma linked list with an interval tree.").

... and later, the comment was changed in commit 0503ea8f5ba7 ("mm/mmap: remove __vma_adjust()") to talk about "vma_merge" although the original issue was with VMA splitting.

Let's just remove that comment. Nowadays, it's outdated, imprecise and confusing.

Link: https://lkml.kernel.org/r/20230913125113.313322-1-david@redhat.com Link: https://lkml.kernel.org/r/20230913125113.313322-2-david@redhat.com Signed-off-by: David Hildenbrand david@redhat.com Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Muchun Song muchun.song@linux.dev Cc: Matthew Wilcox willy@infradead.org Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit fd63908706f79c963946a77b7f352db5431deed5) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- mm/rmap.c | 2 -- 1 file changed, 2 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c index 770f5d25046a..eecffdc578a8 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1279,7 +1279,6 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);

if (likely(!folio_test_ksm(folio))) { - /* address might be in next vma when migration races vma_merge */ if (first) __page_set_anon_rmap(folio, page, vma, address, !!(flags & RMAP_EXCLUSIVE)); @@ -2600,7 +2599,6 @@ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma,

BUG_ON(!folio_test_locked(folio)); BUG_ON(!anon_vma); - /* address might be in next vma when migration races vma_merge */ first = atomic_inc_and_test(&folio->_entire_mapcount); VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page);

From: David Hildenbrand david@redhat.com

mainline inclusion from mainline-v6.7-rc1 commit c5c540034747dfe450f64d1151081a6080daa8f9 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Let's handle it in the caller; no need for the "first" check based on the mapcount.

We really only end up with !anon pages in page_add_anon_rmap() via do_swap_page(), where we hold the folio lock. So races are not possible. Add a VM_WARN_ON_FOLIO() to make sure that we really hold the folio lock.

In the future, we might want to let do_swap_page() use folio_add_new_anon_rmap() on new pages instead: however, we might have to pass then whether the folio is exclusive or not. So keep it in there for now.

For hugetlb we never expect to have a non-anon page in hugepage_add_anon_rmap(). Remove that code, along with some other checks that are either not required or were checked in hugepage_add_new_anon_rmap() already.

Link: https://lkml.kernel.org/r/20230913125113.313322-4-david@redhat.com Signed-off-by: David Hildenbrand david@redhat.com Cc: Matthew Wilcox willy@infradead.org Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Muchun Song muchun.song@linux.dev Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit c5c540034747dfe450f64d1151081a6080daa8f9) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- mm/rmap.c | 23 ++++++++--------------- 1 file changed, 8 insertions(+), 15 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c index 2e732ea8d6ce..56fac8547afc 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1169,9 +1169,6 @@ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma,

BUG_ON(!anon_vma);

- if (folio_test_anon(folio)) - return; - /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! @@ -1273,12 +1270,12 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, if (nr) __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);

- if (likely(!folio_test_ksm(folio))) { - if (first) - __folio_set_anon(folio, vma, address, - !!(flags & RMAP_EXCLUSIVE)); - else - __page_check_anon_rmap(folio, page, vma, address); + if (unlikely(!folio_test_anon(folio))) { + VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); + __folio_set_anon(folio, vma, address, + !!(flags & RMAP_EXCLUSIVE)); + } else if (likely(!folio_test_ksm(folio))) { + __page_check_anon_rmap(folio, page, vma, address); } if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(page); @@ -2592,17 +2589,13 @@ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { struct folio *folio = page_folio(page); - struct anon_vma *anon_vma = vma->anon_vma; int first;

- BUG_ON(!folio_test_locked(folio)); - BUG_ON(!anon_vma); + VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); + first = atomic_inc_and_test(&folio->_entire_mapcount); VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); - if (first) - __folio_set_anon(folio, vma, address, - !!(flags & RMAP_EXCLUSIVE)); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(page); }

From: David Hildenbrand david@redhat.com

mainline inclusion from mainline-v6.7-rc1 commit 132b180f06a74ddfc526709928036db3b7a1cf6d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Let's sanity-check PageAnonExclusive vs. mapcount in page_add_anon_rmap() and hugepage_add_anon_rmap() after setting PageAnonExclusive simply by re-reading the mapcounts.

We can stop initializing the "first" variable in page_add_anon_rmap() and no longer need an atomic_inc_and_test() in hugepage_add_anon_rmap().

While at it, switch to VM_WARN_ON_FOLIO().

[david@redhat.com: update check for doubly-mapped page] Link: https://lkml.kernel.org/r/d8e5a093-2e22-c14b-7e64-6da280398d9f@redhat.com Link: https://lkml.kernel.org/r/20230913125113.313322-6-david@redhat.com Signed-off-by: David Hildenbrand david@redhat.com Cc: Matthew Wilcox willy@infradead.org Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Muchun Song muchun.song@linux.dev Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit 132b180f06a74ddfc526709928036db3b7a1cf6d) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- mm/rmap.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c index bbc3ae731741..ddf4485c500a 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1233,7 +1233,7 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, atomic_t *mapped = &folio->_nr_pages_mapped; int nr = 0, nr_pmdmapped = 0; bool compound = flags & RMAP_COMPOUND; - bool first = true; + bool first;

/* Is page being mapped by PTE? Is this its first map to be added? */ if (likely(!compound)) { @@ -1262,9 +1262,6 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, } }

- VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); - VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); - if (nr_pmdmapped) __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr_pmdmapped); if (nr) @@ -1286,6 +1283,10 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, } if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(page); + /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ + VM_WARN_ON_FOLIO((atomic_read(&page->_mapcount) > 0 || + (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) && + PageAnonExclusive(page), folio);

/* * For large folio, only mlock it if it's fully mapped to VMA. It's @@ -2596,15 +2597,14 @@ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { struct folio *folio = page_folio(page); - int first;

VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);

- first = atomic_inc_and_test(&folio->_entire_mapcount); - VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); - VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); + atomic_inc(&folio->_entire_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(page); + VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && + PageAnonExclusive(page), folio); }

void hugepage_add_new_anon_rmap(struct folio *folio,

From: David Hildenbrand david@redhat.com

mainline inclusion from mainline-v6.7-rc1 commit 5ca432896a4ce6d69fffc3298b24c0dd9bdb871f category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Patch series "mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()".

Convert page_move_anon_rmap() to folio_move_anon_rmap(), letting the callers handle PageAnonExclusive. I'm including cleanup patch #3 because it fits into the picture and can be done cleaner by the conversion.

This patch (of 3):

Let's move it into the caller: there is a difference between whether an anon folio can only be mapped by one process (e.g., into one VMA), and whether it is truly exclusive (e.g., no references -- including GUP -- from other processes).

Further, for large folios the page might not actually be pointing at the head page of the folio, so it better be handled in the caller. This is a preparation for converting page_move_anon_rmap() to consume a folio.

Link: https://lkml.kernel.org/r/20231002142949.235104-1-david@redhat.com Link: https://lkml.kernel.org/r/20231002142949.235104-2-david@redhat.com Signed-off-by: David Hildenbrand david@redhat.com Reviewed-by: Suren Baghdasaryan surenb@google.com Reviewed-by: Vishal Moola (Oracle) vishal.moola@gmail.com Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Muchun Song muchun.song@linux.dev Cc: Matthew Wilcox willy@infradead.org Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit 5ca432896a4ce6d69fffc3298b24c0dd9bdb871f) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- mm/huge_memory.c | 1 + mm/hugetlb.c | 4 +++- mm/memory.c | 1 + mm/rmap.c | 1 - 4 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b4910247ddb8..a8c3da95b844 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1352,6 +1352,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) pmd_t entry;

page_move_anon_rmap(page, vma); + SetPageAnonExclusive(page); folio_unlock(folio); reuse: if (unlikely(unshare)) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 96696f5e268d..72669c9b2855 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5825,8 +5825,10 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, * owner and can reuse this page. */ if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) { - if (!PageAnonExclusive(&old_folio->page)) + if (!PageAnonExclusive(&old_folio->page)) { page_move_anon_rmap(&old_folio->page, vma); + SetPageAnonExclusive(&old_folio->page); + } if (likely(!unshare)) set_huge_ptep_writable(vma, haddr, ptep);

diff --git a/mm/memory.c b/mm/memory.c index 22e0150acec4..c2fc2536091a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3478,6 +3478,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * sunglasses. Hit it. */ page_move_anon_rmap(vmf->page, vma); + SetPageAnonExclusive(vmf->page); folio_unlock(folio); reuse: if (unlikely(unshare)) { diff --git a/mm/rmap.c b/mm/rmap.c index 3aafa49745db..45ee5cbe7d90 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1152,7 +1152,6 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); - SetPageAnonExclusive(page); }

/**

From: David Hildenbrand david@redhat.com

mainline inclusion from mainline-v6.7-rc1 commit dec078cc2181fccf8b134406b86aaacc19f7163f category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Let's clean up do_wp_page() a bit, removing two labels and making it a easier to read.

wp_can_reuse_anon_folio() now only operates on the whole folio. Move the SetPageAnonExclusive() out into do_wp_page(). No need to do this under page lock -- the page table lock is sufficient.

Link: https://lkml.kernel.org/r/20231002142949.235104-4-david@redhat.com Signed-off-by: David Hildenbrand david@redhat.com Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Muchun Song muchun.song@linux.dev Cc: Suren Baghdasaryan surenb@google.com Cc: Matthew Wilcox willy@infradead.org Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit dec078cc2181fccf8b134406b86aaacc19f7163f) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- mm/memory.c | 88 +++++++++++++++++++++++++++-------------------------- 1 file changed, 45 insertions(+), 43 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c index 037cc393813c..9c0946634671 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3369,6 +3369,44 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf, struct folio *folio) return ret; }

+static bool wp_can_reuse_anon_folio(struct folio *folio, + struct vm_area_struct *vma) +{ + /* + * We have to verify under folio lock: these early checks are + * just an optimization to avoid locking the folio and freeing + * the swapcache if there is little hope that we can reuse. + * + * KSM doesn't necessarily raise the folio refcount. + */ + if (folio_test_ksm(folio) || folio_ref_count(folio) > 3) + return false; + if (!folio_test_lru(folio)) + /* + * We cannot easily detect+handle references from + * remote LRU caches or references to LRU folios. + */ + lru_add_drain(); + if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) + return false; + if (!folio_trylock(folio)) + return false; + if (folio_test_swapcache(folio)) + folio_free_swap(folio); + if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { + folio_unlock(folio); + return false; + } + /* + * Ok, we've got the only folio reference from our mapping + * and the folio is locked, it's dark out, and we're wearing + * sunglasses. Hit it. + */ + folio_move_anon_rmap(folio, vma); + folio_unlock(folio); + return true; +} + /* * This routine handles present pages, when * * users try to write to a shared page (FAULT_FLAG_WRITE) @@ -3438,49 +3476,14 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) /* * Private mapping: create an exclusive anonymous page copy if reuse * is impossible. We might miss VM_WRITE for FOLL_FORCE handling. + * + * If we encounter a page that is marked exclusive, we must reuse + * the page without further checks. */ - if (folio && folio_test_anon(folio)) { - /* - * If the page is exclusive to this process we must reuse the - * page without further checks. - */ - if (PageAnonExclusive(vmf->page)) - goto reuse; - - /* - * We have to verify under folio lock: these early checks are - * just an optimization to avoid locking the folio and freeing - * the swapcache if there is little hope that we can reuse. - * - * KSM doesn't necessarily raise the folio refcount. - */ - if (folio_test_ksm(folio) || folio_ref_count(folio) > 3) - goto copy; - if (!folio_test_lru(folio)) - /* - * We cannot easily detect+handle references from - * remote LRU caches or references to LRU folios. - */ - lru_add_drain(); - if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio)) - goto copy; - if (!folio_trylock(folio)) - goto copy; - if (folio_test_swapcache(folio)) - folio_free_swap(folio); - if (folio_test_ksm(folio) || folio_ref_count(folio) != 1) { - folio_unlock(folio); - goto copy; - } - /* - * Ok, we've got the only folio reference from our mapping - * and the folio is locked, it's dark out, and we're wearing - * sunglasses. Hit it. - */ - folio_move_anon_rmap(folio, vma); - SetPageAnonExclusive(vmf->page); - folio_unlock(folio); -reuse: + if (folio && folio_test_anon(folio) && + (PageAnonExclusive(vmf->page) || wp_can_reuse_anon_folio(folio, vma))) { + if (!PageAnonExclusive(vmf->page)) + SetPageAnonExclusive(vmf->page); if (unlikely(unshare)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; @@ -3488,7 +3491,6 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) wp_page_reuse(vmf, folio); return 0; } -copy: /* * Ok, we need to copy. Oh, well.. */

From: Ryan Roberts ryan.roberts@arm.com

mainline inclusion from mainline-v6.7-rc2 commit afccb0804fc74ac2f6737af6a139632606cb461d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Commit c33c794828f2 ("mm: ptep_get() conversion") converted all (non-arch) call sites to use ptep_get() instead of doing a direct dereference of the pte. Full rationale can be found in that commit's log.

Since then, three new call sites have snuck in, which directly dereference the pte, so let's fix those up.

Unfortunately there is no reliable automated mechanism to catch these; I'm relying on a combination of Coccinelle (which throws up a lot of false positives) and some compiler magic to force a compiler error on dereference (While this approach finds dereferences, it also yields a non-booting kernel so can't be committed).

Link: https://lkml.kernel.org/r/20231114154945.490401-1-ryan.roberts@arm.com Signed-off-by: Ryan Roberts ryan.roberts@arm.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit afccb0804fc74ac2f6737af6a139632606cb461d) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- mm/filemap.c | 2 +- mm/ksm.c | 2 +- mm/userfaultfd.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c index da44ba00526f..d2aad2ff2892 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3483,7 +3483,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ - if (!pte_none(vmf->pte[count])) + if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip;

count++; diff --git a/mm/ksm.c b/mm/ksm.c index dba6a2eb1a3c..da8416e2debe 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -455,7 +455,7 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex page = pfn_swap_entry_to_page(entry); } /* return 1 if the page is an normal ksm page or KSM-placed zero page */ - ret = (page && PageKsm(page)) || is_ksm_zero_pte(*pte); + ret = (page && PageKsm(page)) || is_ksm_zero_pte(ptent); pte_unmap_unlock(pte, ptl); return ret; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 32fa1a22c85a..f9bcf2a4f169 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -313,7 +313,7 @@ static int mfill_atomic_pte_poison(pmd_t *dst_pmd,

ret = -EEXIST; /* Refuse to overwrite any PTE, even a PTE marker (e.g. UFFD WP). */ - if (!pte_none(*dst_pte)) + if (!pte_none(ptep_get(dst_pte))) goto out_unlock;

set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);

From: Ryan Roberts ryan.roberts@arm.com

mainline inclusion from mainline-v6.8-rc1 commit 7dc7c5ef6463111991002f24c0aea08afe86f2cc category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Patch series "Multi-size THP for anonymous memory", v9.

A series to implement multi-size THP (mTHP) for anonymous memory (previously called "small-sized THP" and "large anonymous folios").

The objective of this is to improve performance by allocating larger chunks of memory during anonymous page faults:

1) Since SW (the kernel) is dealing with larger chunks of memory than base pages, there are efficiency savings to be had; fewer page faults, batched PTE and RMAP manipulation, reduced lru list, etc. In short, we reduce kernel overhead. This should benefit all architectures. 2) Since we are now mapping physically contiguous chunks of memory, we can take advantage of HW TLB compression techniques. A reduction in TLB pressure speeds up kernel and user space. arm64 systems have 2 mechanisms to coalesce TLB entries; "the contiguous bit" (architectural) and HPA (uarch).

This version incorporates David's feedback on the core patches (#3, #4) and adds some RB and TB tags (see change log for details).

By default, the existing behaviour (and performance) is maintained. The user must explicitly enable multi-size THP to see the performance benefit. This is done via a new sysfs interface (as recommended by David Hildenbrand - thanks to David for the suggestion)! This interface is inspired by the existing per-hugepage-size sysfs interface used by hugetlb, provides full backwards compatibility with the existing PMD-size THP interface, and provides a base for future extensibility. See [9] for detailed discussion of the interface.

This series is based on mm-unstable (715b67adf4c8).

Prerequisites =============

I'm removing this section on the basis that I don't believe what we were previously calling prerequisites are really prerequisites anymore. We originally defined them when mTHP was a compile-time feature. There is now a runtime control to opt-in to mTHP; when disabled, correctness and performance are as before. When enabled, the code is still correct/robust, but in the absence of the one remaining item (compaction) there may be a performance impact in some corners. See the old list in the v8 cover letter at [8]. And a longer explanation of my thinking here [10].

SUMMARY: I don't think we should hold this series up, waiting for the items on the prerequisites list. I believe this series should be ready now so hopefully can be added to mm-unstable for some testing, then fingers crossed for v6.8.

Testing =======

The series includes patches for mm selftests to enlighten the cow and khugepaged tests to explicitly test with multi-size THP, in the same way that PMD-sized THP is tested. The new tests all pass, and no regressions are observed in the mm selftest suite. I've also run my usual kernel compilation and java script benchmarks without any issues.

Refer to my performance numbers posted with v6 [6]. (These are for multi-size THP only - they do not include the arm64 contpte follow-on series).

John Hubbard at Nvidia has indicated dramatic 10x performance improvements for some workloads at [11]. (Observed using v6 of this series as well as the arm64 contpte series).

Kefeng Wang at Huawei has also indicated he sees improvements at [12] although there are some latency regressions also.

I've also checked that there is no regression in the write fault path when mTHP is disabled using a microbenchmark. I ran it for a baseline kernel, as well as v8 and v9. I repeated on Ampere Altra (bare metal) and Apple M2 (VM):

| | m2 vm | altra | |--------------|---------------------|---------------------| | kernel | mean | std_rel | mean | std_rel | |--------------|----------|----------|----------|----------| | baseline | 0.000% | 0.341% | 0.000% | 3.581% | | anonfolio-v8 | 0.005% | 0.272% | 5.068% | 1.128% | | anonfolio-v9 | -0.013% | 0.442% | 0.107% | 1.788% |

There is no measurable difference on M2, but altra has a slow down in v8 which is fixed in v9 by moving the THP order check to be inline within thp_vma_allowable_orders(), as suggested by David.

This patch (of 10):

In preparation for the introduction of anonymous multi-size THP, we would like to be able to split them when they have unmapped subpages, in order to free those unused pages under memory pressure. So remove the artificial requirement that the large folio needed to be at least PMD-sized.

Link: https://lkml.kernel.org/r/20231207161211.2374093-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20231207161211.2374093-2-ryan.roberts@arm.com Signed-off-by: Ryan Roberts ryan.roberts@arm.com Reviewed-by: Yu Zhao yuzhao@google.com Reviewed-by: Yin Fengwei fengwei.yin@intel.com Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Reviewed-by: David Hildenbrand david@redhat.com Reviewed-by: Barry Song v-songbaohua@oppo.com Tested-by: Kefeng Wang wangkefeng.wang@huawei.com Tested-by: John Hubbard jhubbard@nvidia.com Cc: Alistair Popple apopple@nvidia.com Cc: Anshuman Khandual anshuman.khandual@arm.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: David Rientjes rientjes@google.com Cc: "Huang, Ying" ying.huang@intel.com Cc: Hugh Dickins hughd@google.com Cc: Itaru Kitayama itaru.kitayama@gmail.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Luis Chamberlain mcgrof@kernel.org Cc: Vlastimil Babka vbabka@suse.cz Cc: Yang Shi shy828301@gmail.com Cc: Zi Yan ziy@nvidia.com Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit 7dc7c5ef6463111991002f24c0aea08afe86f2cc) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- mm/rmap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c index 2984dbffd391..25656f22d444 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1488,11 +1488,11 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, __lruvec_stat_mod_folio(folio, idx, -nr);

/* - * Queue anon THP for deferred split if at least one + * Queue anon large folio for deferred split if at least one * page of the folio is unmapped and at least one page * is still mapped. */ - if (folio_test_pmd_mappable(folio) && folio_test_anon(folio)) + if (folio_test_large(folio) && folio_test_anon(folio)) if (!compound || nr < nr_pmdmapped) deferred_split_folio(folio); }

From: Ryan Roberts ryan.roberts@arm.com

mainline inclusion from mainline-v6.8-rc1 commit 3485b88390b0af9e05dc2c3f57e9936f41e159a0 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

In preparation for adding support for anonymous multi-size THP, introduce new sysfs structure that will be used to control the new behaviours. A new directory is added under transparent_hugepage for each supported THP size, and contains an `enabled` file, which can be set to "inherit" (to inherit the global setting), "always", "madvise" or "never". For now, the kernel still only supports PMD-sized anonymous THP, so only 1 directory is populated.

The first half of the change converts transhuge_vma_suitable() and hugepage_vma_check() so that they take a bitfield of orders for which the user wants to determine support, and the functions filter out all the orders that can't be supported, given the current sysfs configuration and the VMA dimensions. The resulting functions are renamed to thp_vma_suitable_orders() and thp_vma_allowable_orders() respectively. Convenience functions that take a single, unencoded order and return a boolean are also defined as thp_vma_suitable_order() and thp_vma_allowable_order().

The second half of the change implements the new sysfs interface. It has been done so that each supported THP size has a `struct thpsize`, which describes the relevant metadata and is itself a kobject. This is pretty minimal for now, but should make it easy to add new per-thpsize files to the interface if needed in future (e.g. per-size defrag). Rather than keep the `enabled` state directly in the struct thpsize, I've elected to directly encode it into huge_anon_orders_[always|madvise|inherit] bitfields since this reduces the amount of work required in thp_vma_allowable_orders() which is called for every page fault.

See Documentation/admin-guide/mm/transhuge.rst, as modified by this commit, for details of how the new sysfs interface works.

[ryan.roberts@arm.com: fix build warning when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20231211125320.3997543-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20231207161211.2374093-4-ryan.roberts@arm.com Signed-off-by: Ryan Roberts ryan.roberts@arm.com Reviewed-by: Barry Song v-songbaohua@oppo.com Tested-by: Kefeng Wang wangkefeng.wang@huawei.com Tested-by: John Hubbard jhubbard@nvidia.com Acked-by: David Hildenbrand david@redhat.com Cc: Alistair Popple apopple@nvidia.com Cc: Anshuman Khandual anshuman.khandual@arm.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: David Rientjes rientjes@google.com Cc: "Huang, Ying" ying.huang@intel.com Cc: Hugh Dickins hughd@google.com Cc: Itaru Kitayama itaru.kitayama@gmail.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Luis Chamberlain mcgrof@kernel.org Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Vlastimil Babka vbabka@suse.cz Cc: Yang Shi shy828301@gmail.com Cc: Yin Fengwei fengwei.yin@intel.com Cc: Yu Zhao yuzhao@google.com Cc: Zi Yan ziy@nvidia.com Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit 3485b88390b0af9e05dc2c3f57e9936f41e159a0) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- Documentation/admin-guide/mm/transhuge.rst | 97 +++++++-- Documentation/filesystems/proc.rst | 6 +- fs/proc/task_mmu.c | 3 +- include/linux/huge_mm.h | 181 +++++++++++++--- mm/huge_memory.c | 231 ++++++++++++++++++--- mm/khugepaged.c | 20 +- mm/memory.c | 6 +- mm/page_vma_mapped.c | 3 +- 8 files changed, 459 insertions(+), 88 deletions(-)

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index b0cc8243e093..04eb45a2f940 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -45,10 +45,25 @@ components: the two is using hugepages just because of the fact the TLB miss is going to run faster.

+Modern kernels support "multi-size THP" (mTHP), which introduces the +ability to allocate memory in blocks that are bigger than a base page +but smaller than traditional PMD-size (as described above), in +increments of a power-of-2 number of pages. mTHP can back anonymous +memory (for example 16K, 32K, 64K, etc). These THPs continue to be +PTE-mapped, but in many cases can still provide similar benefits to +those outlined above: Page faults are significantly reduced (by a +factor of e.g. 4, 8, 16, etc), but latency spikes are much less +prominent because the size of each page isn't as huge as the PMD-sized +variant and there is less memory to clear in each page fault. Some +architectures also employ TLB compression mechanisms to squeeze more +entries in when a set of PTEs are virtually and physically contiguous +and approporiately aligned. In this case, TLB misses will occur less +often. + THP can be enabled system wide or restricted to certain tasks or even memory ranges inside task's address space. Unless THP is completely disabled, there is ``khugepaged`` daemon that scans memory and -collapses sequences of basic pages into huge pages. +collapses sequences of basic pages into PMD-sized huge pages.

The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>` interface and using madvise(2) and prctl(2) system calls. @@ -95,12 +110,40 @@ Global THP controls Transparent Hugepage Support for anonymous memory can be entirely disabled (mostly for debugging purposes) or only enabled inside MADV_HUGEPAGE regions (to avoid the risk of consuming more memory resources) or enabled -system wide. This can be achieved with one of:: +system wide. This can be achieved per-supported-THP-size with one of:: + + echo always >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled + echo madvise >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled + echo never >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled + +where <size> is the hugepage size being addressed, the available sizes +for which vary by system. + +For example:: + + echo always >/sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled + +Alternatively it is possible to specify that a given hugepage size +will inherit the top-level "enabled" value:: + + echo inherit >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled + +For example:: + + echo inherit >/sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled + +The top-level setting (for use with "inherit") can be set by issuing +one of the following commands::

echo always >/sys/kernel/mm/transparent_hugepage/enabled echo madvise >/sys/kernel/mm/transparent_hugepage/enabled echo never >/sys/kernel/mm/transparent_hugepage/enabled

+By default, PMD-sized hugepages have enabled="inherit" and all other +hugepage sizes have enabled="never". If enabling multiple hugepage +sizes, the kernel will select the most appropriate enabled size for a +given allocation. + It's also possible to limit defrag efforts in the VM to generate anonymous hugepages in case they're not immediately free to madvise regions or to never try to defrag memory and simply fallback to regular @@ -146,25 +189,34 @@ madvise never should be self-explanatory.

-By default kernel tries to use huge zero page on read page fault to -anonymous mapping. It's possible to disable huge zero page by writing 0 -or enable it back by writing 1:: +By default kernel tries to use huge, PMD-mappable zero page on read +page fault to anonymous mapping. It's possible to disable huge zero +page by writing 0 or enable it back by writing 1::

echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page

-Some userspace (such as a test program, or an optimized memory allocation -library) may want to know the size (in bytes) of a transparent hugepage:: +Some userspace (such as a test program, or an optimized memory +allocation library) may want to know the size (in bytes) of a +PMD-mappable transparent hugepage::

cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size

-khugepaged will be automatically started when -transparent_hugepage/enabled is set to "always" or "madvise, and it'll -be automatically shutdown if it's set to "never". +khugepaged will be automatically started when one or more hugepage +sizes are enabled (either by directly setting "always" or "madvise", +or by setting "inherit" while the top-level enabled is set to "always" +or "madvise"), and it'll be automatically shutdown when the last +hugepage size is disabled (either by directly setting "never", or by +setting "inherit" while the top-level enabled is set to "never").

Khugepaged controls -------------------

+.. note:: + khugepaged currently only searches for opportunities to collapse to + PMD-sized THP and no attempt is made to collapse to other THP + sizes. + khugepaged runs usually at low frequency so while one may not want to invoke defrag algorithms synchronously during the page faults, it should be worth invoking defrag at least in khugepaged. However it's @@ -282,19 +334,26 @@ force Need of application restart ===========================

-The transparent_hugepage/enabled values and tmpfs mount option only affect -future behavior. So to make them effective you need to restart any -application that could have been using hugepages. This also applies to the -regions registered in khugepaged. +The transparent_hugepage/enabled and +transparent_hugepage/hugepages-<size>kB/enabled values and tmpfs mount +option only affect future behavior. So to make them effective you need +to restart any application that could have been using hugepages. This +also applies to the regions registered in khugepaged.

Monitoring usage ================

-The number of anonymous transparent huge pages currently used by the +.. note:: + Currently the below counters only record events relating to + PMD-sized THP. Events relating to other THP sizes are not included. + +The number of PMD-sized anonymous transparent huge pages currently used by the system is available by reading the AnonHugePages field in ``/proc/meminfo``. -To identify what applications are using anonymous transparent huge pages, -it is necessary to read ``/proc/PID/smaps`` and count the AnonHugePages fields -for each mapping. +To identify what applications are using PMD-sized anonymous transparent huge +pages, it is necessary to read ``/proc/PID/smaps`` and count the AnonHugePages +fields for each mapping. (Note that AnonHugePages only applies to traditional +PMD-sized THP for historical reasons and should have been called +AnonHugePmdMapped).

The number of file transparent huge pages mapped to userspace is available by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``. @@ -413,7 +472,7 @@ for huge pages. Optimizing the applications ===========================

-To be guaranteed that the kernel will map a 2M page immediately in any +To be guaranteed that the kernel will map a THP immediately in any memory region, the mmap region has to be hugepage naturally aligned. posix_memalign() can provide that guarantee.

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 56d9ba24bd14..09a07f7d6bda 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -532,9 +532,9 @@ replaced by copy-on-write) part of the underlying shmem object out on swap. does not take into account swapped out page of underlying shmem objects. "Locked" indicates whether the mapping is locked in memory or not.

-"THPeligible" indicates whether the mapping is eligible for allocating THP -pages as well as the THP is PMD mappable or not - 1 if true, 0 otherwise. -It just shows the current status. +"THPeligible" indicates whether the mapping is eligible for allocating +naturally aligned THP pages of any currently enabled size. 1 if true, 0 +otherwise.

"VmFlags" field deserves a separate description. This member represents the kernel flags associated with the particular virtual memory area in two letter diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index fac21bcba8a6..639eb70634f4 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -869,7 +869,8 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false);

seq_printf(m, "THPeligible: %8u\n", - hugepage_vma_check(vma, vma->vm_flags, true, false, true)); + !!thp_vma_allowable_orders(vma, vma->vm_flags, true, false, + true, THP_ORDERS_ALL));

if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fa0350b0812a..609c153bae57 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -67,6 +67,24 @@ extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)

+/* + * Mask of all large folio orders supported for anonymous THP. + */ +#define THP_ORDERS_ALL_ANON BIT(PMD_ORDER) + +/* + * Mask of all large folio orders supported for file THP. + */ +#define THP_ORDERS_ALL_FILE (BIT(PMD_ORDER) | BIT(PUD_ORDER)) + +/* + * Mask of all large folio orders supported for THP. + */ +#define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE) + +#define thp_vma_allowable_order(vma, vm_flags, smaps, in_pf, enforce_sysfs, order) \ + (!!thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, enforce_sysfs, BIT(order))) + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) @@ -77,45 +95,105 @@ extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1))

extern unsigned long transparent_hugepage_flags; +extern unsigned long huge_anon_orders_always; +extern unsigned long huge_anon_orders_madvise; +extern unsigned long huge_anon_orders_inherit;

-#define hugepage_flags_enabled() \ - (transparent_hugepage_flags & \ - ((1<<TRANSPARENT_HUGEPAGE_FLAG) | \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))) -#define hugepage_flags_always() \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_FLAG)) +static inline bool hugepage_global_enabled(void) +{ + return transparent_hugepage_flags & + ((1<<TRANSPARENT_HUGEPAGE_FLAG) | + (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)); +} + +static inline bool hugepage_global_always(void) +{ + return transparent_hugepage_flags & + (1<<TRANSPARENT_HUGEPAGE_FLAG); +} + +static inline bool hugepage_flags_enabled(void) +{ + /* + * We cover both the anon and the file-backed case here; we must return + * true if globally enabled, even when all anon sizes are set to never. + * So we don't need to look at huge_anon_orders_inherit. + */ + return hugepage_global_enabled() || + huge_anon_orders_always || + huge_anon_orders_madvise; +} + +static inline int highest_order(unsigned long orders) +{ + return fls_long(orders) - 1; +} + +static inline int next_order(unsigned long *orders, int prev) +{ + *orders &= ~BIT(prev); + return highest_order(*orders); +}

/* * Do the below checks: * - For file vma, check if the linear page offset of vma is - * HPAGE_PMD_NR aligned within the file. The hugepage is - * guaranteed to be hugepage-aligned within the file, but we must - * check that the PMD-aligned addresses in the VMA map to - * PMD-aligned offsets within the file, else the hugepage will - * not be PMD-mappable. - * - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE + * order-aligned within the file. The hugepage is + * guaranteed to be order-aligned within the file, but we must + * check that the order-aligned addresses in the VMA map to + * order-aligned offsets within the file, else the hugepage will + * not be mappable. + * - For all vmas, check if the haddr is in an aligned hugepage * area. */ -static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long addr) +static inline bool thp_vma_suitable_order(struct vm_area_struct *vma, + unsigned long addr, int order) { + unsigned long hpage_size = PAGE_SIZE << order; unsigned long haddr;

/* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, - HPAGE_PMD_NR)) + hpage_size >> PAGE_SHIFT)) return false; }

- haddr = addr & HPAGE_PMD_MASK; + haddr = ALIGN_DOWN(addr, hpage_size);

- if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + if (haddr < vma->vm_start || haddr + hpage_size > vma->vm_end) return false; return true; }

+/* + * Filter the bitfield of input orders to the ones suitable for use in the vma. + * See thp_vma_suitable_order(). + * All orders that pass the checks are returned as a bitfield. + */ +static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, + unsigned long addr, unsigned long orders) +{ + int order; + + /* + * Iterate over orders, highest to lowest, removing orders that don't + * meet alignment requirements from the set. Exit loop at first order + * that meets requirements, since all lower orders must also meet + * requirements. + */ + + order = highest_order(orders); + + while (orders) { + if (thp_vma_suitable_order(vma, addr, order)) + break; + order = next_order(&orders, order); + } + + return orders; +} + static inline bool file_thp_enabled(struct vm_area_struct *vma) { struct inode *inode; @@ -130,8 +208,52 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma) !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); }

-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, - bool smaps, bool in_pf, bool enforce_sysfs); +unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, + unsigned long vm_flags, bool smaps, + bool in_pf, bool enforce_sysfs, + unsigned long orders); + +/** + * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma + * @vma: the vm area to check + * @vm_flags: use these vm_flags instead of vma->vm_flags + * @smaps: whether answer will be used for smaps file + * @in_pf: whether answer will be used by page fault handler + * @enforce_sysfs: whether sysfs config should be taken into account + * @orders: bitfield of all orders to consider + * + * Calculates the intersection of the requested hugepage orders and the allowed + * hugepage orders for the provided vma. Permitted orders are encoded as a set + * bit at the corresponding bit position (bit-2 corresponds to order-2, bit-3 + * corresponds to order-3, etc). Order-0 is never considered a hugepage order. + * + * Return: bitfield of orders allowed for hugepage in the vma. 0 if no hugepage + * orders are allowed. + */ +static inline +unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, + unsigned long vm_flags, bool smaps, + bool in_pf, bool enforce_sysfs, + unsigned long orders) +{ + /* Optimization to check if required orders are enabled early. */ + if (enforce_sysfs && vma_is_anonymous(vma)) { + unsigned long mask = READ_ONCE(huge_anon_orders_always); + + if (vm_flags & VM_HUGEPAGE) + mask |= READ_ONCE(huge_anon_orders_madvise); + if (hugepage_global_always() || + ((vm_flags & VM_HUGEPAGE) && hugepage_global_enabled())) + mask |= READ_ONCE(huge_anon_orders_inherit); + + orders &= mask; + if (!orders) + return 0; + } + + return __thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, + enforce_sysfs, orders); +}

#define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -267,17 +389,24 @@ static inline bool folio_test_pmd_mappable(struct folio *folio) return false; }

-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long addr) +static inline bool thp_vma_suitable_order(struct vm_area_struct *vma, + unsigned long addr, int order) { return false; }

-static inline bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs) +static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, + unsigned long addr, unsigned long orders) { - return false; + return 0; +} + +static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, + unsigned long vm_flags, bool smaps, + bool in_pf, bool enforce_sysfs, + unsigned long orders) +{ + return 0; }

static inline void folio_prep_large_rmappable(struct folio *folio) {} diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 580272958102..5a2131be4540 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -70,12 +70,23 @@ static struct shrinker deferred_split_shrinker; static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; +unsigned long huge_anon_orders_always __read_mostly; +unsigned long huge_anon_orders_madvise __read_mostly; +unsigned long huge_anon_orders_inherit __read_mostly; + +unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, + unsigned long vm_flags, bool smaps, + bool in_pf, bool enforce_sysfs, + unsigned long orders) +{ + /* Check the intersection of requested and supported orders. */ + orders &= vma_is_anonymous(vma) ? + THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE; + if (!orders) + return 0;

-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, - bool smaps, bool in_pf, bool enforce_sysfs) -{ if (!vma->vm_mm) /* vdso */ - return false; + return 0;

/* * Explicitly disabled through madvise or prctl, or some @@ -84,16 +95,16 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, * */ if ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return false; + return 0; /* * If the hardware/firmware marked hugepage support disabled. */ if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) - return false; + return 0;

/* khugepaged doesn't collapse DAX vma, but page fault is fine. */ if (vma_is_dax(vma)) - return in_pf; + return in_pf ? orders : 0;

/* * khugepaged special VMA and hugetlb VMA. @@ -101,17 +112,29 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, * VM_MIXEDMAP set. */ if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED)) - return false; + return 0;

/* - * Check alignment for file vma and size for both file and anon vma. + * Check alignment for file vma and size for both file and anon vma by + * filtering out the unsuitable orders. * * Skip the check for page fault. Huge fault does the check in fault - * handlers. And this check is not suitable for huge PUD fault. + * handlers. */ - if (!in_pf && - !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE))) - return false; + if (!in_pf) { + int order = highest_order(orders); + unsigned long addr; + + while (orders) { + addr = vma->vm_end - (PAGE_SIZE << order); + if (thp_vma_suitable_order(vma, addr, order)) + break; + order = next_order(&orders, order); + } + + if (!orders) + return 0; + }

/* * Enabled via shmem mount options or sysfs settings. @@ -120,29 +143,33 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, */ if (!in_pf && shmem_file(vma->vm_file)) return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff, - !enforce_sysfs, vma->vm_mm, vm_flags); - - /* Enforce sysfs THP requirements as necessary */ - if (enforce_sysfs && - (!hugepage_flags_enabled() || (!(vm_flags & VM_HUGEPAGE) && - !hugepage_flags_always()))) - return false; + !enforce_sysfs, vma->vm_mm, vm_flags) + ? orders : 0;

if (!vma_is_anonymous(vma)) { + /* + * Enforce sysfs THP requirements as necessary. Anonymous vmas + * were already handled in thp_vma_allowable_orders(). + */ + if (enforce_sysfs && + (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) && + !hugepage_global_always()))) + return 0; + /* * Trust that ->huge_fault() handlers know what they are doing * in fault path. */ if (((in_pf || smaps)) && vma->vm_ops->huge_fault) - return true; + return orders; /* Only regular file is valid in collapse path */ if (((!in_pf || smaps)) && file_thp_enabled(vma)) - return true; - return false; + return orders; + return 0; }

if (vma_is_temporary_stack(vma)) - return false; + return 0;

/* * THPeligible bit of smaps should show 1 for proper VMAs even @@ -152,9 +179,9 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, * the first page fault. */ if (!vma->anon_vma) - return (smaps || in_pf); + return (smaps || in_pf) ? orders : 0;

- return true; + return orders; }

static bool get_huge_zero_page(void) @@ -412,9 +439,136 @@ static const struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, };

+static void hugepage_exit_sysfs(struct kobject *hugepage_kobj); +static void thpsize_release(struct kobject *kobj); +static DEFINE_SPINLOCK(huge_anon_orders_lock); +static LIST_HEAD(thpsize_list); + +struct thpsize { + struct kobject kobj; + struct list_head node; + int order; +}; + +#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) + +static ssize_t thpsize_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int order = to_thpsize(kobj)->order; + const char *output; + + if (test_bit(order, &huge_anon_orders_always)) + output = "[always] inherit madvise never"; + else if (test_bit(order, &huge_anon_orders_inherit)) + output = "always [inherit] madvise never"; + else if (test_bit(order, &huge_anon_orders_madvise)) + output = "always inherit [madvise] never"; + else + output = "always inherit madvise [never]"; + + return sysfs_emit(buf, "%s\n", output); +} + +static ssize_t thpsize_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int order = to_thpsize(kobj)->order; + ssize_t ret = count; + + if (sysfs_streq(buf, "always")) { + spin_lock(&huge_anon_orders_lock); + clear_bit(order, &huge_anon_orders_inherit); + clear_bit(order, &huge_anon_orders_madvise); + set_bit(order, &huge_anon_orders_always); + spin_unlock(&huge_anon_orders_lock); + } else if (sysfs_streq(buf, "inherit")) { + spin_lock(&huge_anon_orders_lock); + clear_bit(order, &huge_anon_orders_always); + clear_bit(order, &huge_anon_orders_madvise); + set_bit(order, &huge_anon_orders_inherit); + spin_unlock(&huge_anon_orders_lock); + } else if (sysfs_streq(buf, "madvise")) { + spin_lock(&huge_anon_orders_lock); + clear_bit(order, &huge_anon_orders_always); + clear_bit(order, &huge_anon_orders_inherit); + set_bit(order, &huge_anon_orders_madvise); + spin_unlock(&huge_anon_orders_lock); + } else if (sysfs_streq(buf, "never")) { + spin_lock(&huge_anon_orders_lock); + clear_bit(order, &huge_anon_orders_always); + clear_bit(order, &huge_anon_orders_inherit); + clear_bit(order, &huge_anon_orders_madvise); + spin_unlock(&huge_anon_orders_lock); + } else + ret = -EINVAL; + + return ret; +} + +static struct kobj_attribute thpsize_enabled_attr = + __ATTR(enabled, 0644, thpsize_enabled_show, thpsize_enabled_store); + +static struct attribute *thpsize_attrs[] = { + &thpsize_enabled_attr.attr, + NULL, +}; + +static const struct attribute_group thpsize_attr_group = { + .attrs = thpsize_attrs, +}; + +static const struct kobj_type thpsize_ktype = { + .release = &thpsize_release, + .sysfs_ops = &kobj_sysfs_ops, +}; + +static struct thpsize *thpsize_create(int order, struct kobject *parent) +{ + unsigned long size = (PAGE_SIZE << order) / SZ_1K; + struct thpsize *thpsize; + int ret; + + thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL); + if (!thpsize) + return ERR_PTR(-ENOMEM); + + ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent, + "hugepages-%lukB", size); + if (ret) { + kfree(thpsize); + return ERR_PTR(ret); + } + + ret = sysfs_create_group(&thpsize->kobj, &thpsize_attr_group); + if (ret) { + kobject_put(&thpsize->kobj); + return ERR_PTR(ret); + } + + thpsize->order = order; + return thpsize; +} + +static void thpsize_release(struct kobject *kobj) +{ + kfree(to_thpsize(kobj)); +} + static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) { int err; + struct thpsize *thpsize; + unsigned long orders; + int order; + + /* + * Default to setting PMD-sized THP to inherit the global setting and + * disable all other sizes. powerpc's PMD_ORDER isn't a compile-time + * constant so we have to do this here. + */ + huge_anon_orders_inherit = BIT(PMD_ORDER);

*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); if (unlikely(!*hugepage_kobj)) { @@ -434,8 +588,24 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) goto remove_hp_group; }

+ orders = THP_ORDERS_ALL_ANON; + order = highest_order(orders); + while (orders) { + thpsize = thpsize_create(order, *hugepage_kobj); + if (IS_ERR(thpsize)) { + pr_err("failed to create thpsize for order %d\n", order); + err = PTR_ERR(thpsize); + goto remove_all; + } + list_add(&thpsize->node, &thpsize_list); + order = next_order(&orders, order); + } + return 0;

+remove_all: + hugepage_exit_sysfs(*hugepage_kobj); + return err; remove_hp_group: sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group); delete_obj: @@ -445,6 +615,13 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)

static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj) { + struct thpsize *thpsize, *tmp; + + list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) { + list_del(&thpsize->node); + kobject_put(&thpsize->kobj); + } + sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group); sysfs_remove_group(hugepage_kobj, &hugepage_attr_group); kobject_put(hugepage_kobj); @@ -785,7 +962,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK;

- if (!transhuge_vma_suitable(vma, haddr)) + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return VM_FAULT_FALLBACK; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 50babcbf11ce..b0a7af8f81b3 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -453,7 +453,8 @@ void khugepaged_enter_vma(struct vm_area_struct *vma, { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_flags_enabled()) { - if (hugepage_vma_check(vma, vm_flags, false, false, true)) + if (thp_vma_allowable_order(vma, vm_flags, false, false, true, + PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } @@ -930,16 +931,16 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, if (!vma) return SCAN_VMA_NULL;

- if (!transhuge_vma_suitable(vma, address)) + if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; - if (!hugepage_vma_check(vma, vma->vm_flags, false, false, - cc->is_khugepaged)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, + cc->is_khugepaged, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * - * hugepage_vma_check may return true for qualified file + * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) @@ -1521,7 +1522,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ - if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false, + PMD_ORDER)) return SCAN_VMA_CHECK;

/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ @@ -2401,7 +2403,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, progress++; break; } - if (!hugepage_vma_check(vma, vma->vm_flags, false, false, true)) { + if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, + true, PMD_ORDER)) { skip: progress++; continue; @@ -2738,7 +2741,8 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,

*prev = vma;

- if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false, + PMD_ORDER)) return -EINVAL;

if (task_in_dynamic_pool(current)) diff --git a/mm/memory.c b/mm/memory.c index 9c0946634671..2b1fde55ee66 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4315,7 +4315,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) pmd_t entry; vm_fault_t ret = VM_FAULT_FALLBACK;

- if (!transhuge_vma_suitable(vma, haddr)) + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret;

page = compound_head(page); @@ -5111,7 +5111,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && - hugepage_vma_check(vma, vm_flags, false, true, true) && + thp_vma_allowable_order(vma, vm_flags, false, true, true, PUD_ORDER) && !task_in_dynamic_pool(current)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) @@ -5146,7 +5146,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, goto retry_pud;

if (pmd_none(*vmf.pmd) && - hugepage_vma_check(vma, vm_flags, false, true, true) && + thp_vma_allowable_order(vma, vm_flags, false, true, true, PMD_ORDER) && !task_in_dynamic_pool(current)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index e0b368e545ed..74d2de15fb5e 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -268,7 +268,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) * cleared *pmd but not decremented compound_mapcount(). */ if ((pvmw->flags & PVMW_SYNC) && - transhuge_vma_suitable(vma, pvmw->address) && + thp_vma_suitable_order(vma, pvmw->address, + PMD_ORDER) && (pvmw->nr_pages >= HPAGE_PMD_NR)) { spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);

From: Ryan Roberts ryan.roberts@arm.com

mainline inclusion from mainline-v6.8-rc1 commit b6aab3384cafba151c53d3b5f7e1f8d073aadf03 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Previously, the saved thp settings would be restored upon a signal or at the natural end of the test suite. But there are some tests that directly call exit() upon failure. In this case, the thp settings were not being restored, which could then influence other tests.

Fix this by installing an atexit() handler to do the actual restore. The signal handler can now just call exit() and the atexit handler is invoked.

Link: https://lkml.kernel.org/r/20231207161211.2374093-6-ryan.roberts@arm.com Signed-off-by: Ryan Roberts ryan.roberts@arm.com Reviewed-by: Alistair Popple apopple@nvidia.com Reviewed-by: David Hildenbrand david@redhat.com Tested-by: Kefeng Wang wangkefeng.wang@huawei.com Tested-by: John Hubbard jhubbard@nvidia.com Cc: Anshuman Khandual anshuman.khandual@arm.com Cc: Barry Song v-songbaohua@oppo.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: David Rientjes rientjes@google.com Cc: "Huang, Ying" ying.huang@intel.com Cc: Hugh Dickins hughd@google.com Cc: Itaru Kitayama itaru.kitayama@gmail.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Luis Chamberlain mcgrof@kernel.org Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Vlastimil Babka vbabka@suse.cz Cc: Yang Shi shy828301@gmail.com Cc: Yin Fengwei fengwei.yin@intel.com Cc: Yu Zhao yuzhao@google.com Cc: Zi Yan ziy@nvidia.com Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit b6aab3384cafba151c53d3b5f7e1f8d073aadf03) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- tools/testing/selftests/mm/khugepaged.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 030667cb5533..fc47a1c4944c 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -374,18 +374,22 @@ static void pop_settings(void) write_settings(current_settings()); }

-static void restore_settings(int sig) +static void restore_settings_atexit(void) { if (skip_settings_restore) - goto out; + return;

printf("Restore THP and khugepaged settings..."); write_settings(&saved_settings); success("OK"); - if (sig) - exit(EXIT_FAILURE); -out: - exit(exit_status); + + skip_settings_restore = true; +} + +static void restore_settings(int sig) +{ + /* exit() will invoke the restore_settings_atexit handler. */ + exit(sig ? EXIT_FAILURE : exit_status); }

static void save_settings(void) @@ -415,6 +419,7 @@ static void save_settings(void)

success("OK");

+ atexit(restore_settings_atexit); signal(SIGTERM, restore_settings); signal(SIGINT, restore_settings); signal(SIGHUP, restore_settings);

From: Ryan Roberts ryan.roberts@arm.com

mainline inclusion from mainline-v6.8-rc1 commit 4f5070a5e40db2e9dbf5fff4ec678d6fbb338d5c category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

Save and restore the new per-size hugepage enabled setting, if available on the running kernel.

Since the number of per-size directories is not fixed, solve this as simply as possible by catering for a maximum number in the thp_settings struct (20). Each array index is the order. The value of THP_NEVER is changed to 0 so that all of these new settings default to THP_NEVER and the user only needs to fill in the ones they want to enable.

Link: https://lkml.kernel.org/r/20231207161211.2374093-8-ryan.roberts@arm.com Signed-off-by: Ryan Roberts ryan.roberts@arm.com Tested-by: Kefeng Wang wangkefeng.wang@huawei.com Tested-by: John Hubbard jhubbard@nvidia.com Cc: Alistair Popple apopple@nvidia.com Cc: Anshuman Khandual anshuman.khandual@arm.com Cc: Barry Song v-songbaohua@oppo.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: David Hildenbrand david@redhat.com Cc: David Rientjes rientjes@google.com Cc: "Huang, Ying" ying.huang@intel.com Cc: Hugh Dickins hughd@google.com Cc: Itaru Kitayama itaru.kitayama@gmail.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Luis Chamberlain mcgrof@kernel.org Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Vlastimil Babka vbabka@suse.cz Cc: Yang Shi shy828301@gmail.com Cc: Yin Fengwei fengwei.yin@intel.com Cc: Yu Zhao yuzhao@google.com Cc: Zi Yan ziy@nvidia.com Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit 4f5070a5e40db2e9dbf5fff4ec678d6fbb338d5c) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- tools/testing/selftests/mm/khugepaged.c | 3 ++ tools/testing/selftests/mm/thp_settings.c | 55 ++++++++++++++++++++++- tools/testing/selftests/mm/thp_settings.h | 11 ++++- 3 files changed, 67 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index b15e7fd70176..7bd3baa9d34b 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -1141,6 +1141,7 @@ static void parse_test_type(int argc, const char **argv)

int main(int argc, const char **argv) { + int hpage_pmd_order; struct thp_settings default_settings = { .thp_enabled = THP_MADVISE, .thp_defrag = THP_DEFRAG_ALWAYS, @@ -1175,11 +1176,13 @@ int main(int argc, const char **argv) exit(EXIT_FAILURE); } hpage_pmd_nr = hpage_pmd_size / page_size; + hpage_pmd_order = __builtin_ctz(hpage_pmd_nr);

default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1; default_settings.khugepaged.max_ptes_swap = hpage_pmd_nr / 8; default_settings.khugepaged.max_ptes_shared = hpage_pmd_nr / 2; default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8; + default_settings.hugepages[hpage_pmd_order].enabled = THP_INHERIT;

save_settings(); thp_push_settings(&default_settings); diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c index 5e8ec792cac7..a4163438108e 100644 --- a/tools/testing/selftests/mm/thp_settings.c +++ b/tools/testing/selftests/mm/thp_settings.c @@ -16,9 +16,10 @@ static struct thp_settings saved_settings; static char dev_queue_read_ahead_path[PATH_MAX];

static const char * const thp_enabled_strings[] = { + "never", "always", + "inherit", "madvise", - "never", NULL };

@@ -198,6 +199,10 @@ void thp_write_num(const char *name, unsigned long num)

void thp_read_settings(struct thp_settings *settings) { + unsigned long orders = thp_supported_orders(); + char path[PATH_MAX]; + int i; + *settings = (struct thp_settings) { .thp_enabled = thp_read_string("enabled", thp_enabled_strings), .thp_defrag = thp_read_string("defrag", thp_defrag_strings), @@ -218,11 +223,26 @@ void thp_read_settings(struct thp_settings *settings) }; if (dev_queue_read_ahead_path[0]) settings->read_ahead_kb = read_num(dev_queue_read_ahead_path); + + for (i = 0; i < NR_ORDERS; i++) { + if (!((1 << i) & orders)) { + settings->hugepages[i].enabled = THP_NEVER; + continue; + } + snprintf(path, PATH_MAX, "hugepages-%ukB/enabled", + (getpagesize() >> 10) << i); + settings->hugepages[i].enabled = + thp_read_string(path, thp_enabled_strings); + } }

void thp_write_settings(struct thp_settings *settings) { struct khugepaged_settings *khugepaged = &settings->khugepaged; + unsigned long orders = thp_supported_orders(); + char path[PATH_MAX]; + int enabled; + int i;

thp_write_string("enabled", thp_enabled_strings[settings->thp_enabled]); thp_write_string("defrag", thp_defrag_strings[settings->thp_defrag]); @@ -242,6 +262,15 @@ void thp_write_settings(struct thp_settings *settings)

if (dev_queue_read_ahead_path[0]) write_num(dev_queue_read_ahead_path, settings->read_ahead_kb); + + for (i = 0; i < NR_ORDERS; i++) { + if (!((1 << i) & orders)) + continue; + snprintf(path, PATH_MAX, "hugepages-%ukB/enabled", + (getpagesize() >> 10) << i); + enabled = settings->hugepages[i].enabled; + thp_write_string(path, thp_enabled_strings[enabled]); + } }

struct thp_settings *thp_current_settings(void) @@ -294,3 +323,27 @@ void thp_set_read_ahead_path(char *path) sizeof(dev_queue_read_ahead_path)); dev_queue_read_ahead_path[sizeof(dev_queue_read_ahead_path) - 1] = '\0'; } + +unsigned long thp_supported_orders(void) +{ + unsigned long orders = 0; + char path[PATH_MAX]; + char buf[256]; + int ret; + int i; + + for (i = 0; i < NR_ORDERS; i++) { + ret = snprintf(path, PATH_MAX, THP_SYSFS "hugepages-%ukB/enabled", + (getpagesize() >> 10) << i); + if (ret >= PATH_MAX) { + printf("%s: Pathname is too long\n", __func__); + exit(EXIT_FAILURE); + } + + ret = read_file(path, buf, sizeof(buf)); + if (ret) + orders |= 1UL << i; + } + + return orders; +} diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h index ff3d98c30617..71cbff05f4c7 100644 --- a/tools/testing/selftests/mm/thp_settings.h +++ b/tools/testing/selftests/mm/thp_settings.h @@ -7,9 +7,10 @@ #include <stdint.h>

enum thp_enabled { + THP_NEVER, THP_ALWAYS, + THP_INHERIT, THP_MADVISE, - THP_NEVER, };

enum thp_defrag { @@ -29,6 +30,12 @@ enum shmem_enabled { SHMEM_FORCE, };

+#define NR_ORDERS 20 + +struct hugepages_settings { + enum thp_enabled enabled; +}; + struct khugepaged_settings { bool defrag; unsigned int alloc_sleep_millisecs; @@ -46,6 +53,7 @@ struct thp_settings { bool use_zero_page; struct khugepaged_settings khugepaged; unsigned long read_ahead_kb; + struct hugepages_settings hugepages[NR_ORDERS]; };

int read_file(const char *path, char *buf, size_t buflen); @@ -67,5 +75,6 @@ void thp_restore_settings(void); void thp_save_settings(void);

void thp_set_read_ahead_path(char *path); +unsigned long thp_supported_orders(void);

#endif /* __THP_SETTINGS_H__ */

From: Ryan Roberts ryan.roberts@arm.com

mainline inclusion from mainline-v6.8-rc1 commit 12dc16b38463a671bc91dc2df10f3a014a27ff3b category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I98AW9 CVE: NA

-------------------------------------------------

do_run_with_thp() prepares (PMD-sized) THP memory into different states before running tests. With the introduction of multi-size THP, we would like to reuse this logic to also test those smaller THP sizes. So let's add a thpsize parameter which tells the function what size THP it should operate on.

A separate commit will utilize this change to add new tests for multi-size THP, where available.

Link: https://lkml.kernel.org/r/20231207161211.2374093-10-ryan.roberts@arm.com Signed-off-by: Ryan Roberts ryan.roberts@arm.com Reviewed-by: David Hildenbrand david@redhat.com Tested-by: Kefeng Wang wangkefeng.wang@huawei.com Tested-by: John Hubbard jhubbard@nvidia.com Cc: Alistair Popple apopple@nvidia.com Cc: Anshuman Khandual anshuman.khandual@arm.com Cc: Barry Song v-songbaohua@oppo.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: David Rientjes rientjes@google.com Cc: "Huang, Ying" ying.huang@intel.com Cc: Hugh Dickins hughd@google.com Cc: Itaru Kitayama itaru.kitayama@gmail.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Luis Chamberlain mcgrof@kernel.org Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Vlastimil Babka vbabka@suse.cz Cc: Yang Shi shy828301@gmail.com Cc: Yin Fengwei fengwei.yin@intel.com Cc: Yu Zhao yuzhao@google.com Cc: Zi Yan ziy@nvidia.com Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit 12dc16b38463a671bc91dc2df10f3a014a27ff3b) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- tools/testing/selftests/mm/cow.c | 121 +++++++++++++++++-------------- 1 file changed, 67 insertions(+), 54 deletions(-)

diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 7324ce5363c0..4d0b5a125d3c 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -32,7 +32,7 @@

static size_t pagesize; static int pagemap_fd; -static size_t thpsize; +static size_t pmdsize; static int nr_hugetlbsizes; static size_t hugetlbsizes[10]; static int gup_fd; @@ -734,7 +734,7 @@ enum thp_run { THP_RUN_PARTIAL_SHARED, };

-static void do_run_with_thp(test_fn fn, enum thp_run thp_run) +static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize) { char *mem, *mmap_mem, *tmp, *mremap_mem = MAP_FAILED; size_t size, mmap_size, mremap_size; @@ -759,11 +759,11 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) }

/* - * Try to populate a THP. Touch the first sub-page and test if we get - * another sub-page populated automatically. + * Try to populate a THP. Touch the first sub-page and test if + * we get the last sub-page populated automatically. */ mem[0] = 0; - if (!pagemap_is_populated(pagemap_fd, mem + pagesize)) { + if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { ksft_test_result_skip("Did not get a THP populated\n"); goto munmap; } @@ -773,12 +773,14 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) switch (thp_run) { case THP_RUN_PMD: case THP_RUN_PMD_SWAPOUT: + assert(thpsize == pmdsize); break; case THP_RUN_PTE: case THP_RUN_PTE_SWAPOUT: /* * Trigger PTE-mapping the THP by temporarily mapping a single - * subpage R/O. + * subpage R/O. This is a noop if the THP is not pmdsize (and + * therefore already PTE-mapped). */ ret = mprotect(mem + pagesize, pagesize, PROT_READ); if (ret) { @@ -875,52 +877,60 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run) munmap(mremap_mem, mremap_size); }

-static void run_with_thp(test_fn fn, const char *desc) +static void run_with_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with THP\n", desc); - do_run_with_thp(fn, THP_RUN_PMD); + ksft_print_msg("[RUN] %s ... with THP (%zu kB)\n", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PMD, size); }

-static void run_with_thp_swap(test_fn fn, const char *desc) +static void run_with_thp_swap(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with swapped-out THP\n", desc); - do_run_with_thp(fn, THP_RUN_PMD_SWAPOUT); + ksft_print_msg("[RUN] %s ... with swapped-out THP (%zu kB)\n", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PMD_SWAPOUT, size); }

-static void run_with_pte_mapped_thp(test_fn fn, const char *desc) +static void run_with_pte_mapped_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with PTE-mapped THP\n", desc); - do_run_with_thp(fn, THP_RUN_PTE); + ksft_print_msg("[RUN] %s ... with PTE-mapped THP (%zu kB)\n", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PTE, size); }

-static void run_with_pte_mapped_thp_swap(test_fn fn, const char *desc) +static void run_with_pte_mapped_thp_swap(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with swapped-out, PTE-mapped THP\n", desc); - do_run_with_thp(fn, THP_RUN_PTE_SWAPOUT); + ksft_print_msg("[RUN] %s ... with swapped-out, PTE-mapped THP (%zu kB)\n", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PTE_SWAPOUT, size); }

-static void run_with_single_pte_of_thp(test_fn fn, const char *desc) +static void run_with_single_pte_of_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with single PTE of THP\n", desc); - do_run_with_thp(fn, THP_RUN_SINGLE_PTE); + ksft_print_msg("[RUN] %s ... with single PTE of THP (%zu kB)\n", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_SINGLE_PTE, size); }

-static void run_with_single_pte_of_thp_swap(test_fn fn, const char *desc) +static void run_with_single_pte_of_thp_swap(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with single PTE of swapped-out THP\n", desc); - do_run_with_thp(fn, THP_RUN_SINGLE_PTE_SWAPOUT); + ksft_print_msg("[RUN] %s ... with single PTE of swapped-out THP (%zu kB)\n", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_SINGLE_PTE_SWAPOUT, size); }

-static void run_with_partial_mremap_thp(test_fn fn, const char *desc) +static void run_with_partial_mremap_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with partially mremap()'ed THP\n", desc); - do_run_with_thp(fn, THP_RUN_PARTIAL_MREMAP); + ksft_print_msg("[RUN] %s ... with partially mremap()'ed THP (%zu kB)\n", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PARTIAL_MREMAP, size); }

-static void run_with_partial_shared_thp(test_fn fn, const char *desc) +static void run_with_partial_shared_thp(test_fn fn, const char *desc, size_t size) { - ksft_print_msg("[RUN] %s ... with partially shared THP\n", desc); - do_run_with_thp(fn, THP_RUN_PARTIAL_SHARED); + ksft_print_msg("[RUN] %s ... with partially shared THP (%zu kB)\n", + desc, size / 1024); + do_run_with_thp(fn, THP_RUN_PARTIAL_SHARED, size); }

static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) @@ -1091,15 +1101,15 @@ static void run_anon_test_case(struct test_case const *test_case)

run_with_base_page(test_case->fn, test_case->desc); run_with_base_page_swap(test_case->fn, test_case->desc); - if (thpsize) { - run_with_thp(test_case->fn, test_case->desc); - run_with_thp_swap(test_case->fn, test_case->desc); - run_with_pte_mapped_thp(test_case->fn, test_case->desc); - run_with_pte_mapped_thp_swap(test_case->fn, test_case->desc); - run_with_single_pte_of_thp(test_case->fn, test_case->desc); - run_with_single_pte_of_thp_swap(test_case->fn, test_case->desc); - run_with_partial_mremap_thp(test_case->fn, test_case->desc); - run_with_partial_shared_thp(test_case->fn, test_case->desc); + if (pmdsize) { + run_with_thp(test_case->fn, test_case->desc, pmdsize); + run_with_thp_swap(test_case->fn, test_case->desc, pmdsize); + run_with_pte_mapped_thp(test_case->fn, test_case->desc, pmdsize); + run_with_pte_mapped_thp_swap(test_case->fn, test_case->desc, pmdsize); + run_with_single_pte_of_thp(test_case->fn, test_case->desc, pmdsize); + run_with_single_pte_of_thp_swap(test_case->fn, test_case->desc, pmdsize); + run_with_partial_mremap_thp(test_case->fn, test_case->desc, pmdsize); + run_with_partial_shared_thp(test_case->fn, test_case->desc, pmdsize); } for (i = 0; i < nr_hugetlbsizes; i++) run_with_hugetlb(test_case->fn, test_case->desc, @@ -1120,7 +1130,7 @@ static int tests_per_anon_test_case(void) { int tests = 2 + nr_hugetlbsizes;

- if (thpsize) + if (pmdsize) tests += 8; return tests; } @@ -1329,7 +1339,7 @@ static void run_anon_thp_test_cases(void) { int i;

- if (!thpsize) + if (!pmdsize) return;

ksft_print_msg("[INFO] Anonymous THP tests\n"); @@ -1338,13 +1348,13 @@ static void run_anon_thp_test_cases(void) struct test_case const *test_case = &anon_thp_test_cases[i];

ksft_print_msg("[RUN] %s\n", test_case->desc); - do_run_with_thp(test_case->fn, THP_RUN_PMD); + do_run_with_thp(test_case->fn, THP_RUN_PMD, pmdsize); } }

static int tests_per_anon_thp_test_case(void) { - return thpsize ? 1 : 0; + return pmdsize ? 1 : 0; }

typedef void (*non_anon_test_fn)(char *mem, const char *smem, size_t size); @@ -1419,7 +1429,7 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc) }

/* For alignment purposes, we need twice the thp size. */ - mmap_size = 2 * thpsize; + mmap_size = 2 * pmdsize; mmap_mem = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (mmap_mem == MAP_FAILED) { @@ -1434,11 +1444,11 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc) }

/* We need a THP-aligned memory area. */ - mem = (char *)(((uintptr_t)mmap_mem + thpsize) & ~(thpsize - 1)); - smem = (char *)(((uintptr_t)mmap_smem + thpsize) & ~(thpsize - 1)); + mem = (char *)(((uintptr_t)mmap_mem + pmdsize) & ~(pmdsize - 1)); + smem = (char *)(((uintptr_t)mmap_smem + pmdsize) & ~(pmdsize - 1));

- ret = madvise(mem, thpsize, MADV_HUGEPAGE); - ret |= madvise(smem, thpsize, MADV_HUGEPAGE); + ret = madvise(mem, pmdsize, MADV_HUGEPAGE); + ret |= madvise(smem, pmdsize, MADV_HUGEPAGE); if (ret) { ksft_test_result_fail("MADV_HUGEPAGE failed\n"); goto munmap; @@ -1457,7 +1467,7 @@ static void run_with_huge_zeropage(non_anon_test_fn fn, const char *desc) goto munmap; }

- fn(mem, smem, thpsize); + fn(mem, smem, pmdsize); munmap: munmap(mmap_mem, mmap_size); if (mmap_smem != MAP_FAILED) @@ -1650,7 +1660,7 @@ static void run_non_anon_test_case(struct non_anon_test_case const *test_case) run_with_zeropage(test_case->fn, test_case->desc); run_with_memfd(test_case->fn, test_case->desc); run_with_tmpfile(test_case->fn, test_case->desc); - if (thpsize) + if (pmdsize) run_with_huge_zeropage(test_case->fn, test_case->desc); for (i = 0; i < nr_hugetlbsizes; i++) run_with_memfd_hugetlb(test_case->fn, test_case->desc, @@ -1671,7 +1681,7 @@ static int tests_per_non_anon_test_case(void) { int tests = 3 + nr_hugetlbsizes;

- if (thpsize) + if (pmdsize) tests += 1; return tests; } @@ -1681,10 +1691,13 @@ int main(int argc, char **argv) int err;

pagesize = getpagesize(); - thpsize = read_pmd_pagesize(); - if (thpsize) + pmdsize = read_pmd_pagesize(); + if (pmdsize) { + ksft_print_msg("[INFO] detected PMD size: %zu KiB\n", + pmdsize / 1024); ksft_print_msg("[INFO] detected THP size: %zu KiB\n", - thpsize / 1024); + pmdsize / 1024); + } nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, ARRAY_SIZE(hugetlbsizes)); detect_huge_zeropage();