summaryrefslogtreecommitdiffstats
path: root/mm/mmap.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-11-02 19:38:47 -1000
committerLinus Torvalds <torvalds@linux-foundation.org>2023-11-02 19:38:47 -1000
commitecae0bd5173b1014f95a14a8dfbe40ec10367dcf (patch)
treef571213ef1a35354ea79f0240a180fdb4111b290 /mm/mmap.c
parentbc3012f4e3a9765de81f454cb8f9bb16aafc6ff5 (diff)
parent9732336006764e2ee61225387e3c70eae9139035 (diff)
downloadlinux-stable-ecae0bd5173b1014f95a14a8dfbe40ec10367dcf.tar.gz
linux-stable-ecae0bd5173b1014f95a14a8dfbe40ec10367dcf.tar.bz2
linux-stable-ecae0bd5173b1014f95a14a8dfbe40ec10367dcf.zip
Merge tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: "Many singleton patches against the MM code. The patch series which are included in this merge do the following: - Kemeng Shi has contributed some compation maintenance work in the series 'Fixes and cleanups to compaction' - Joel Fernandes has a patchset ('Optimize mremap during mutual alignment within PMD') which fixes an obscure issue with mremap()'s pagetable handling during a subsequent exec(), based upon an implementation which Linus suggested - More DAMON/DAMOS maintenance and feature work from SeongJae Park i the following patch series: mm/damon: misc fixups for documents, comments and its tracepoint mm/damon: add a tracepoint for damos apply target regions mm/damon: provide pseudo-moving sum based access rate mm/damon: implement DAMOS apply intervals mm/damon/core-test: Fix memory leaks in core-test mm/damon/sysfs-schemes: Do DAMOS tried regions update for only one apply interval - In the series 'Do not try to access unaccepted memory' Adrian Hunter provides some fixups for the recently-added 'unaccepted memory' feature. To increase the feature's checking coverage. 'Plug a few gaps where RAM is exposed without checking if it is unaccepted memory' - In the series 'cleanups for lockless slab shrink' Qi Zheng has done some maintenance work which is preparation for the lockless slab shrinking code - Qi Zheng has redone the earlier (and reverted) attempt to make slab shrinking lockless in the series 'use refcount+RCU method to implement lockless slab shrink' - David Hildenbrand contributes some maintenance work for the rmap code in the series 'Anon rmap cleanups' - Kefeng Wang does more folio conversions and some maintenance work in the migration code. Series 'mm: migrate: more folio conversion and unification' - Matthew Wilcox has fixed an issue in the buffer_head code which was causing long stalls under some heavy memory/IO loads. Some cleanups were added on the way. Series 'Add and use bdev_getblk()' - In the series 'Use nth_page() in place of direct struct page manipulation' Zi Yan has fixed a potential issue with the direct manipulation of hugetlb page frames - In the series 'mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO' has improved our handling of gigantic pages in the hugetlb vmmemmep optimizaton code. This provides significant boot time improvements when significant amounts of gigantic pages are in use - Matthew Wilcox has sent the series 'Small hugetlb cleanups' - code rationalization and folio conversions in the hugetlb code - Yin Fengwei has improved mlock()'s handling of large folios in the series 'support large folio for mlock' - In the series 'Expose swapcache stat for memcg v1' Liu Shixin has added statistics for memcg v1 users which are available (and useful) under memcg v2 - Florent Revest has enhanced the MDWE (Memory-Deny-Write-Executable) prctl so that userspace may direct the kernel to not automatically propagate the denial to child processes. The series is named 'MDWE without inheritance' - Kefeng Wang has provided the series 'mm: convert numa balancing functions to use a folio' which does what it says - In the series 'mm/ksm: add fork-exec support for prctl' Stefan Roesch makes is possible for a process to propagate KSM treatment across exec() - Huang Ying has enhanced memory tiering's calculation of memory distances. This is used to permit the dax/kmem driver to use 'high bandwidth memory' in addition to Optane Data Center Persistent Memory Modules (DCPMM). The series is named 'memory tiering: calculate abstract distance based on ACPI HMAT' - In the series 'Smart scanning mode for KSM' Stefan Roesch has optimized KSM by teaching it to retain and use some historical information from previous scans - Yosry Ahmed has fixed some inconsistencies in memcg statistics in the series 'mm: memcg: fix tracking of pending stats updates values' - In the series 'Implement IOCTL to get and optionally clear info about PTEs' Peter Xu has added an ioctl to /proc/<pid>/pagemap which permits us to atomically read-then-clear page softdirty state. This is mainly used by CRIU - Hugh Dickins contributed the series 'shmem,tmpfs: general maintenance', a bunch of relatively minor maintenance tweaks to this code - Matthew Wilcox has increased the use of the VMA lock over file-backed page faults in the series 'Handle more faults under the VMA lock'. Some rationalizations of the fault path became possible as a result - In the series 'mm/rmap: convert page_move_anon_rmap() to folio_move_anon_rmap()' David Hildenbrand has implemented some cleanups and folio conversions - In the series 'various improvements to the GUP interface' Lorenzo Stoakes has simplified and improved the GUP interface with an eye to providing groundwork for future improvements - Andrey Konovalov has sent along the series 'kasan: assorted fixes and improvements' which does those things - Some page allocator maintenance work from Kemeng Shi in the series 'Two minor cleanups to break_down_buddy_pages' - In thes series 'New selftest for mm' Breno Leitao has developed another MM self test which tickles a race we had between madvise() and page faults - In the series 'Add folio_end_read' Matthew Wilcox provides cleanups and an optimization to the core pagecache code - Nhat Pham has added memcg accounting for hugetlb memory in the series 'hugetlb memcg accounting' - Cleanups and rationalizations to the pagemap code from Lorenzo Stoakes, in the series 'Abstract vma_merge() and split_vma()' - Audra Mitchell has fixed issues in the procfs page_owner code's new timestamping feature which was causing some misbehaviours. In the series 'Fix page_owner's use of free timestamps' - Lorenzo Stoakes has fixed the handling of new mappings of sealed files in the series 'permit write-sealed memfd read-only shared mappings' - Mike Kravetz has optimized the hugetlb vmemmap optimization in the series 'Batch hugetlb vmemmap modification operations' - Some buffer_head folio conversions and cleanups from Matthew Wilcox in the series 'Finish the create_empty_buffers() transition' - As a page allocator performance optimization Huang Ying has added automatic tuning to the allocator's per-cpu-pages feature, in the series 'mm: PCP high auto-tuning' - Roman Gushchin has contributed the patchset 'mm: improve performance of accounted kernel memory allocations' which improves their performance by ~30% as measured by a micro-benchmark - folio conversions from Kefeng Wang in the series 'mm: convert page cpupid functions to folios' - Some kmemleak fixups in Liu Shixin's series 'Some bugfix about kmemleak' - Qi Zheng has improved our handling of memoryless nodes by keeping them off the allocation fallback list. This is done in the series 'handle memoryless nodes more appropriately' - khugepaged conversions from Vishal Moola in the series 'Some khugepaged folio conversions'" [ bcachefs conflicts with the dynamically allocated shrinkers have been resolved as per Stephen Rothwell in https://lore.kernel.org/all/20230913093553.4290421e@canb.auug.org.au/ with help from Qi Zheng. The clone3 test filtering conflict was half-arsed by yours truly ] * tag 'mm-stable-2023-11-01-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (406 commits) mm/damon/sysfs: update monitoring target regions for online input commit mm/damon/sysfs: remove requested targets when online-commit inputs selftests: add a sanity check for zswap Documentation: maple_tree: fix word spelling error mm/vmalloc: fix the unchecked dereference warning in vread_iter() zswap: export compression failure stats Documentation: ubsan: drop "the" from article title mempolicy: migration attempt to match interleave nodes mempolicy: mmap_lock is not needed while migrating folios mempolicy: alloc_pages_mpol() for NUMA policy without vma mm: add page_rmappable_folio() wrapper mempolicy: remove confusing MPOL_MF_LAZY dead code mempolicy: mpol_shared_policy_init() without pseudo-vma mempolicy trivia: use pgoff_t in shared mempolicy tree mempolicy trivia: slightly more consistent naming mempolicy trivia: delete those ancient pr_debug()s mempolicy: fix migrate_pages(2) syscall return nr_failed kernfs: drop shared NUMA mempolicy hooks hugetlbfs: drop shared NUMA mempolicy pretence mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets() ...
Diffstat (limited to 'mm/mmap.c')
-rw-r--r--mm/mmap.c149
1 files changed, 116 insertions, 33 deletions
diff --git a/mm/mmap.c b/mm/mmap.c
index da2e3bd6dba1..1971bfffcc03 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -107,7 +107,7 @@ void vma_set_page_prot(struct vm_area_struct *vma)
static void __remove_shared_vm_struct(struct vm_area_struct *vma,
struct file *file, struct address_space *mapping)
{
- if (vma->vm_flags & VM_SHARED)
+ if (vma_is_shared_maywrite(vma))
mapping_unmap_writable(mapping);
flush_dcache_mmap_lock(mapping);
@@ -384,7 +384,7 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm,
static void __vma_link_file(struct vm_area_struct *vma,
struct address_space *mapping)
{
- if (vma->vm_flags & VM_SHARED)
+ if (vma_is_shared_maywrite(vma))
mapping_allow_writable(mapping);
flush_dcache_mmap_lock(mapping);
@@ -860,13 +860,13 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
* **** is not represented - it will be merged and the vma containing the
* area is returned, or the function will return NULL
*/
-struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
- struct vm_area_struct *prev, unsigned long addr,
- unsigned long end, unsigned long vm_flags,
- struct anon_vma *anon_vma, struct file *file,
- pgoff_t pgoff, struct mempolicy *policy,
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
- struct anon_vma_name *anon_name)
+static struct vm_area_struct
+*vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
+ struct vm_area_struct *prev, unsigned long addr, unsigned long end,
+ unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file,
+ pgoff_t pgoff, struct mempolicy *policy,
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
+ struct anon_vma_name *anon_name)
{
struct vm_area_struct *curr, *next, *res;
struct vm_area_struct *vma, *adjust, *remove, *remove2;
@@ -943,6 +943,11 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm,
vma_start_write(curr);
remove = curr;
remove2 = next;
+ /*
+ * Note that the dup_anon_vma below cannot overwrite err
+ * since the first caller would do nothing unless next
+ * has an anon_vma.
+ */
if (!next->anon_vma)
err = dup_anon_vma(prev, curr, &anon_dup);
}
@@ -1218,7 +1223,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
* Does the application expect PROT_READ to imply PROT_EXEC?
*
* (the exception is when the underlying filesystem is noexec
- * mounted, in which case we dont add PROT_EXEC.)
+ * mounted, in which case we don't add PROT_EXEC.)
*/
if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
if (!(file && path_noexec(&file->f_path)))
@@ -2179,8 +2184,6 @@ struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned lon
#else
int expand_stack_locked(struct vm_area_struct *vma, unsigned long address)
{
- if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
- return -EINVAL;
return expand_downwards(vma, address);
}
@@ -2343,8 +2346,8 @@ static void unmap_region(struct mm_struct *mm, struct ma_state *mas,
* has already been checked or doesn't make sense to fail.
* VMA Iterator will point to the end VMA.
*/
-int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
- unsigned long addr, int new_below)
+static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
+ unsigned long addr, int new_below)
{
struct vma_prepare vp;
struct vm_area_struct *new;
@@ -2425,8 +2428,8 @@ out_free_vma:
* Split a vma into two pieces at address 'addr', a new vma is allocated
* either for the first part or the tail.
*/
-int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
- unsigned long addr, int new_below)
+static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
+ unsigned long addr, int new_below)
{
if (vma->vm_mm->map_count >= sysctl_max_map_count)
return -ENOMEM;
@@ -2435,6 +2438,85 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
}
/*
+ * 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;
+}
+
+/*
+ * Attempt to merge a newly mapped VMA with those adjacent to it. The caller
+ * must ensure that [start, end) does not overlap any existing VMA.
+ */
+static struct vm_area_struct
+*vma_merge_new_vma(struct vma_iterator *vmi, struct vm_area_struct *prev,
+ struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, pgoff_t pgoff)
+{
+ return vma_merge(vmi, vma->vm_mm, prev, start, end, vma->vm_flags,
+ vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+ vma->vm_userfaultfd_ctx, anon_vma_name(vma));
+}
+
+/*
+ * Expand vma by delta bytes, potentially merging with an immediately adjacent
+ * VMA with identical properties.
+ */
+struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi,
+ struct vm_area_struct *vma,
+ unsigned long delta)
+{
+ pgoff_t pgoff = vma->vm_pgoff + vma_pages(vma);
+
+ /* vma is specified as prev, so case 1 or 2 will apply. */
+ return vma_merge(vmi, vma->vm_mm, vma, vma->vm_end, vma->vm_end + delta,
+ vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff,
+ vma_policy(vma), vma->vm_userfaultfd_ctx,
+ anon_vma_name(vma));
+}
+
+/*
* do_vmi_align_munmap() - munmap the aligned region from @start to @end.
* @vmi: The vma iterator
* @vma: The starting vm_area_struct
@@ -2670,6 +2752,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
unsigned long charged = 0;
unsigned long end = addr + len;
unsigned long merge_start = addr, merge_end = end;
+ bool writable_file_mapping = false;
pgoff_t vm_pgoff;
int error;
VMA_ITERATOR(vmi, mm, addr);
@@ -2764,17 +2847,19 @@ cannot_expand:
vma->vm_pgoff = pgoff;
if (file) {
- if (vm_flags & VM_SHARED) {
- error = mapping_map_writable(file->f_mapping);
- if (error)
- goto free_vma;
- }
-
vma->vm_file = get_file(file);
error = call_mmap(file, vma);
if (error)
goto unmap_and_free_vma;
+ if (vma_is_shared_maywrite(vma)) {
+ error = mapping_map_writable(file->f_mapping);
+ if (error)
+ goto close_and_free_vma;
+
+ writable_file_mapping = true;
+ }
+
/*
* Expansion is handled above, merging is handled below.
* Drivers should not alter the address of the VMA.
@@ -2789,10 +2874,9 @@ cannot_expand:
* vma again as we may succeed this time.
*/
if (unlikely(vm_flags != vma->vm_flags && prev)) {
- merge = vma_merge(&vmi, mm, prev, vma->vm_start,
- vma->vm_end, vma->vm_flags, NULL,
- vma->vm_file, vma->vm_pgoff, NULL,
- NULL_VM_UFFD_CTX, NULL);
+ merge = vma_merge_new_vma(&vmi, prev, vma,
+ vma->vm_start, vma->vm_end,
+ vma->vm_pgoff);
if (merge) {
/*
* ->mmap() can change vma->vm_file and fput
@@ -2839,7 +2923,7 @@ cannot_expand:
mm->map_count++;
if (vma->vm_file) {
i_mmap_lock_write(vma->vm_file->f_mapping);
- if (vma->vm_flags & VM_SHARED)
+ if (vma_is_shared_maywrite(vma))
mapping_allow_writable(vma->vm_file->f_mapping);
flush_dcache_mmap_lock(vma->vm_file->f_mapping);
@@ -2856,7 +2940,7 @@ cannot_expand:
/* Once vma denies write, undo our temporary denial count */
unmap_writable:
- if (file && vm_flags & VM_SHARED)
+ if (writable_file_mapping)
mapping_unmap_writable(file->f_mapping);
file = vma->vm_file;
ksm_add_vma(vma);
@@ -2904,7 +2988,7 @@ unmap_and_free_vma:
unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start,
vma->vm_end, vma->vm_end, true);
}
- if (file && (vm_flags & VM_SHARED))
+ if (writable_file_mapping)
mapping_unmap_writable(file->f_mapping);
free_vma:
vm_area_free(vma);
@@ -3292,7 +3376,8 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
}
if (vma_link(mm, vma)) {
- vm_unacct_memory(charged);
+ if (vma->vm_flags & VM_ACCOUNT)
+ vm_unacct_memory(charged);
return -ENOMEM;
}
@@ -3327,9 +3412,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
if (new_vma && new_vma->vm_start < addr + len)
return NULL; /* should never get here */
- new_vma = vma_merge(&vmi, mm, prev, addr, addr + len, vma->vm_flags,
- vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
- vma->vm_userfaultfd_ctx, anon_vma_name(vma));
+ new_vma = vma_merge_new_vma(&vmi, prev, vma, addr, addr + len, pgoff);
if (new_vma) {
/*
* Source vma may have been merged into new_vma