From dc68badcede4ec3b4e5cdfcb8f678670220ac2ca Mon Sep 17 00:00:00 2001 From: Yin Fengwei Date: Mon, 18 Sep 2023 15:33:18 +0800 Subject: mm: mlock: update mlock_pte_range to handle large folio Current kernel only lock base size folio during mlock syscall. Add large folio support with following rules: - Only mlock large folio when it's in VM_LOCKED VMA range and fully mapped to page table. fully mapped folio is required as if folio is not fully mapped to a VM_LOCKED VMA, if system is in memory pressure, page reclaim is allowed to pick up this folio, split it and reclaim the pages which are not in VM_LOCKED VMA. - munlock will apply to the large folio which is in VMA range or cross the VMA boundary. This is required to handle the case that the large folio is mlocked, later the VMA is split in the middle of large folio. Link: https://lkml.kernel.org/r/20230918073318.1181104-4-fengwei.yin@intel.com Signed-off-by: Yin Fengwei Cc: David Hildenbrand Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Ryan Roberts Cc: Yang Shi Cc: Yosry Ahmed Cc: Yu Zhao Signed-off-by: Andrew Morton --- mm/mlock.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 64 insertions(+), 2 deletions(-) (limited to 'mm/mlock.c') diff --git a/mm/mlock.c b/mm/mlock.c index 06bdfab83b58..42b6865f8f82 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -305,6 +305,58 @@ void munlock_folio(struct folio *folio) local_unlock(&mlock_fbatch.lock); } +static inline unsigned int folio_mlock_step(struct folio *folio, + pte_t *pte, unsigned long addr, unsigned long end) +{ + unsigned int count, i, nr = folio_nr_pages(folio); + unsigned long pfn = folio_pfn(folio); + pte_t ptent = ptep_get(pte); + + if (!folio_test_large(folio)) + return 1; + + count = pfn + nr - pte_pfn(ptent); + count = min_t(unsigned int, count, (end - addr) >> PAGE_SHIFT); + + for (i = 0; i < count; i++, pte++) { + pte_t entry = ptep_get(pte); + + if (!pte_present(entry)) + break; + if (pte_pfn(entry) - pfn >= nr) + break; + } + + return i; +} + +static inline bool allow_mlock_munlock(struct folio *folio, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned int step) +{ + /* + * For unlock, allow munlock large folio which is partially + * mapped to VMA. As it's possible that large folio is + * mlocked and VMA is split later. + * + * During memory pressure, such kind of large folio can + * be split. And the pages are not in VM_LOCKed VMA + * can be reclaimed. + */ + if (!(vma->vm_flags & VM_LOCKED)) + return true; + + /* folio not in range [start, end), skip mlock */ + if (!folio_within_range(folio, vma, start, end)) + return false; + + /* folio is not fully mapped, skip mlock */ + if (step != folio_nr_pages(folio)) + return false; + + return true; +} + static int mlock_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -314,6 +366,8 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, pte_t *start_pte, *pte; pte_t ptent; struct folio *folio; + unsigned int step = 1; + unsigned long start = addr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { @@ -334,6 +388,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, walk->action = ACTION_AGAIN; return 0; } + for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (!pte_present(ptent)) @@ -341,12 +396,19 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; - if (folio_test_large(folio)) - continue; + + step = folio_mlock_step(folio, pte, addr, end); + if (!allow_mlock_munlock(folio, vma, start, end, step)) + goto next_entry; + if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); + +next_entry: + pte += step - 1; + addr += (step - 1) << PAGE_SHIFT; } pte_unmap(start_pte); out: -- cgit v1.2.3 From 94d7d923395129b9248777e575c877e40007f9dc Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 11 Oct 2023 18:04:28 +0100 Subject: mm: abstract the vma_merge()/split_vma() pattern for mprotect() et al. mprotect() and other functions which change VMA parameters over a range each employ a pattern of:- 1. Attempt to merge the range with adjacent VMAs. 2. If this fails, and the range spans a subset of the VMA, split it accordingly. This is open-coded and duplicated in each case. Also in each case most of the parameters passed to vma_merge() remain the same. Create a new function, vma_modify(), which abstracts this operation, accepting only those parameters which can be changed. To avoid the mess of invoking each function call with unnecessary parameters, create inline wrapper functions for each of the modify operations, parameterised only by what is required to perform the action. We can also significantly simplify the logic - by returning the VMA if we split (or merged VMA if we do not) we no longer need specific handling for merge/split cases in any of the call sites. Note that the userfaultfd_release() case works even though it does not split VMAs - since start is set to vma->vm_start and end is set to vma->vm_end, the split logic does not trigger. In addition, since we calculate pgoff to be equal to vma->vm_pgoff + (start - vma->vm_start) >> PAGE_SHIFT, and start - vma->vm_start will be 0 in this instance, this invocation will remain unchanged. We eliminate a VM_WARN_ON() in mprotect_fixup() as this simply asserts that vma_merge() correctly ensures that flags remain the same, something that is already checked in is_mergeable_vma() and elsewhere, and in any case is not specific to mprotect(). Link: https://lkml.kernel.org/r/0dfa9368f37199a423674bf0ee312e8ea0619044.1697043508.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Cc: Alexander Viro Cc: Christian Brauner Cc: Liam R. Howlett Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 70 ++++++++++++++---------------------------------------- include/linux/mm.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++ mm/madvise.c | 26 ++++---------------- mm/mempolicy.c | 26 +++----------------- mm/mlock.c | 25 ++++--------------- mm/mmap.c | 48 +++++++++++++++++++++++++++++++++++++ mm/mprotect.c | 29 ++++------------------ 7 files changed, 141 insertions(+), 143 deletions(-) (limited to 'mm/mlock.c') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index a7c6ef764e63..ac616cfbacf5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -927,20 +927,15 @@ static int userfaultfd_release(struct inode *inode, struct file *file) continue; } new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; - prev = vma_merge(&vmi, mm, prev, vma->vm_start, vma->vm_end, - new_flags, vma->anon_vma, - vma->vm_file, vma->vm_pgoff, - vma_policy(vma), - NULL_VM_UFFD_CTX, anon_vma_name(vma)); - if (prev) { - vma = prev; - } else { - prev = vma; - } + vma = vma_modify_flags_uffd(&vmi, prev, vma, vma->vm_start, + vma->vm_end, new_flags, + NULL_VM_UFFD_CTX); vma_start_write(vma); userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + + prev = vma; } mmap_write_unlock(mm); mmput(mm); @@ -1331,7 +1326,6 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long start, end, vma_end; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); - pgoff_t pgoff; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -1484,28 +1478,14 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vma_end = min(end, vma->vm_end); new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, - vma->anon_vma, vma->vm_file, pgoff, - vma_policy(vma), - ((struct vm_userfaultfd_ctx){ ctx }), - anon_vma_name(vma)); - if (prev) { - /* vma_merge() invalidated the mas */ - vma = prev; - goto next; - } - if (vma->vm_start < start) { - ret = split_vma(&vmi, vma, start, 1); - if (ret) - break; - } - if (vma->vm_end > end) { - ret = split_vma(&vmi, vma, end, 0); - if (ret) - break; + vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end, + new_flags, + (struct vm_userfaultfd_ctx){ctx}); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + break; } - next: + /* * In the vma_merge() successful mprotect-like case 8: * the next vma was merged into the current one and @@ -1568,7 +1548,6 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, const void __user *buf = (void __user *)arg; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); - pgoff_t pgoff; ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) @@ -1671,26 +1650,13 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, uffd_wp_range(vma, start, vma_end - start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, - vma->anon_vma, vma->vm_file, pgoff, - vma_policy(vma), - NULL_VM_UFFD_CTX, anon_vma_name(vma)); - if (prev) { - vma = prev; - goto next; - } - if (vma->vm_start < start) { - ret = split_vma(&vmi, vma, start, 1); - if (ret) - break; - } - if (vma->vm_end > end) { - ret = split_vma(&vmi, vma, end, 0); - if (ret) - break; + vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end, + new_flags, NULL_VM_UFFD_CTX); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + break; } - next: + /* * In the vma_merge() successful mprotect-like case 8: * the next vma was merged into the current one and diff --git a/include/linux/mm.h b/include/linux/mm.h index fa608cba041f..895feb814620 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3251,6 +3251,66 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name); + +/* We are about to modify the VMA's flags. */ +static inline struct vm_area_struct +*vma_modify_flags(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, + anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or anon_name. */ +static inline struct vm_area_struct +*vma_modify_flags_name(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long new_flags, + struct anon_vma_name *new_name) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), vma->vm_userfaultfd_ctx, new_name); +} + +/* We are about to modify the VMA's memory policy. */ +static inline struct vm_area_struct +*vma_modify_policy(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct mempolicy *new_pol) +{ + return vma_modify(vmi, prev, vma, start, end, vma->vm_flags, + new_pol, vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +/* We are about to modify the VMA's flags and/or uffd context. */ +static inline struct vm_area_struct +*vma_modify_flags_uffd(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long new_flags, + struct vm_userfaultfd_ctx new_ctx) +{ + return vma_modify(vmi, prev, vma, start, end, new_flags, + vma_policy(vma), new_ctx, anon_vma_name(vma)); +} static inline int check_data_rlimit(unsigned long rlim, unsigned long new, diff --git a/mm/madvise.c b/mm/madvise.c index 59e8860c86af..a6b48d4796ba 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -141,7 +141,6 @@ static int madvise_update_vma(struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; int error; - pgoff_t pgoff; VMA_ITERATOR(vmi, mm, start); if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) { @@ -149,30 +148,13 @@ static int madvise_update_vma(struct vm_area_struct *vma, return 0; } - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *prev = vma_merge(&vmi, mm, *prev, start, end, new_flags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_name); - if (*prev) { - vma = *prev; - goto success; - } + vma = vma_modify_flags_name(&vmi, *prev, vma, start, end, new_flags, + anon_name); + if (IS_ERR(vma)) + return PTR_ERR(vma); *prev = vma; - if (start != vma->vm_start) { - error = split_vma(&vmi, vma, start, 1); - if (error) - return error; - } - - if (end != vma->vm_end) { - error = split_vma(&vmi, vma, end, 0); - if (error) - return error; - } - -success: /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vm_flags_reset(vma, new_flags); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 38a47fa33ef4..8bb5b4b4b395 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -811,10 +811,7 @@ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { - struct vm_area_struct *merged; unsigned long vmstart, vmend; - pgoff_t pgoff; - int err; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { @@ -829,26 +826,9 @@ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, return 0; } - pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); - merged = vma_merge(vmi, vma->vm_mm, *prev, vmstart, vmend, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, new_pol, - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - if (merged) { - *prev = merged; - return vma_replace_policy(merged, new_pol); - } - - if (vma->vm_start != vmstart) { - err = split_vma(vmi, vma, vmstart, 1); - if (err) - return err; - } - - if (vma->vm_end != vmend) { - err = split_vma(vmi, vma, vmend, 0); - if (err) - return err; - } + vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); + if (IS_ERR(vma)) + return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); diff --git a/mm/mlock.c b/mm/mlock.c index 42b6865f8f82..aa44456200e3 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -476,7 +476,6 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long end, vm_flags_t newflags) { struct mm_struct *mm = vma->vm_mm; - pgoff_t pgoff; int nr_pages; int ret = 0; vm_flags_t oldflags = vma->vm_flags; @@ -487,28 +486,12 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *prev = vma_merge(vmi, mm, *prev, start, end, newflags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - if (*prev) { - vma = *prev; - goto success; - } - - if (start != vma->vm_start) { - ret = split_vma(vmi, vma, start, 1); - if (ret) - goto out; - } - - if (end != vma->vm_end) { - ret = split_vma(vmi, vma, end, 0); - if (ret) - goto out; + vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; } -success: /* * Keep track of amount of locked VM. */ diff --git a/mm/mmap.c b/mm/mmap.c index 673429ee8a9e..bca685820763 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2437,6 +2437,54 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, return __split_vma(vmi, vma, addr, new_below); } +/* + * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd + * context and anonymous VMA name within the range [start, end). + * + * As a result, we might be able to merge the newly modified VMA range with an + * adjacent VMA with identical properties. + * + * If no merge is possible and the range does not span the entirety of the VMA, + * we then need to split the VMA to accommodate the change. + * + * The function returns either the merged VMA, the original VMA if a split was + * required instead, or an error if the split failed. + */ +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name) +{ + pgoff_t pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + struct vm_area_struct *merged; + + merged = vma_merge(vmi, vma->vm_mm, prev, start, end, vm_flags, + vma->anon_vma, vma->vm_file, pgoff, policy, + uffd_ctx, anon_name); + if (merged) + return merged; + + if (vma->vm_start < start) { + int err = split_vma(vmi, vma, start, 1); + + if (err) + return ERR_PTR(err); + } + + if (vma->vm_end > end) { + int err = split_vma(vmi, vma, end, 0); + + if (err) + return ERR_PTR(err); + } + + return vma; +} + /* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator diff --git a/mm/mprotect.c b/mm/mprotect.c index 03e2cec3e669..f1dc8f8c84ef 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -581,7 +581,6 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, long nrpages = (end - start) >> PAGE_SHIFT; unsigned int mm_cp_flags = 0; unsigned long charged = 0; - pgoff_t pgoff; int error; if (newflags == oldflags) { @@ -631,34 +630,14 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, newflags &= ~VM_ACCOUNT; } - /* - * First try to merge with previous and/or next vma. - */ - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - *pprev = vma_merge(vmi, mm, *pprev, start, end, newflags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - if (*pprev) { - vma = *pprev; - VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); - goto success; + vma = vma_modify_flags(vmi, *pprev, vma, start, end, newflags); + if (IS_ERR(vma)) { + error = PTR_ERR(vma); + goto fail; } *pprev = vma; - if (start != vma->vm_start) { - error = split_vma(vmi, vma, start, 1); - if (error) - goto fail; - } - - if (end != vma->vm_end) { - error = split_vma(vmi, vma, end, 0); - if (error) - goto fail; - } - -success: /* * vm_flags and vm_page_prot are protected by the mmap_lock * held in write mode. -- cgit v1.2.3 From b1454b463c217e5bc553acc44b2389d9257c9708 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 23 Oct 2023 23:38:41 -0700 Subject: mm: mlock: avoid folio_within_range() on KSM pages Since commit dc68badcede4 ("mm: mlock: update mlock_pte_range to handle large folio") I've just occasionally seen VM_WARN_ON_FOLIO(folio_test_ksm) warnings from folio_within_range(), in a splurge after testing with KSM hyperactive. folio_referenced_one()'s use of folio_within_vma() is safe because it checks folio_test_large() first; but allow_mlock_munlock() needs to do the same to avoid those warnings (or check !folio_test_ksm() itself? Or move either check into folio_within_range()? Hard to tell without more examples of its use). Link: https://lkml.kernel.org/r/23852f6a-5bfa-1ffd-30db-30c5560ad426@google.com Fixes: dc68badcede4 ("mm: mlock: update mlock_pte_range to handle large folio") Signed-off-by: Hugh Dickins Reviewed-by: Yin Fengwei Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Stefan Roesch Signed-off-by: Andrew Morton --- mm/mlock.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'mm/mlock.c') diff --git a/mm/mlock.c b/mm/mlock.c index aa44456200e3..086546ac5766 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -346,6 +346,10 @@ static inline bool allow_mlock_munlock(struct folio *folio, if (!(vma->vm_flags & VM_LOCKED)) return true; + /* folio_within_range() cannot take KSM, but any small folio is OK */ + if (!folio_test_large(folio)) + return true; + /* folio not in range [start, end), skip mlock */ if (!folio_within_range(folio, vma, start, end)) return false; -- cgit v1.2.3