mm/mempolicy: use vma iterator & maple state instead of vma linked list

Reworked the way mbind_range() finds the first VMA to reuse the maple
state and limit the number of tree walks needed.

Note, this drops the VM_BUG_ON(!vma) call, which would catch a start
address higher than the last VMA.  The code was written in a way that
allowed no VMA updates to occur and still return success.  There should be
no functional change to this scenario with the new code.

Link: https://lkml.kernel.org/r/20220906194824.2110408-57-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Tested-by: Yu Zhao <yuzhao@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: SeongJae Park <sj@kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index a88fd94e18d6f36490175f2b72627a5c173f5538..143e2eaaa6ec54d149092906fa6fdb020176c56f 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -381,9 +381,10 @@ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
 void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
 {
        struct vm_area_struct *vma;
+       VMA_ITERATOR(vmi, mm, 0);
 
        mmap_write_lock(mm);
-       for (vma = mm->mmap; vma; vma = vma->vm_next)
+       for_each_vma(vmi, vma)
                mpol_rebind_policy(vma->vm_policy, new);
        mmap_write_unlock(mm);
 }
@@ -654,7 +655,7 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
 static int queue_pages_test_walk(unsigned long start, unsigned long end,
                                struct mm_walk *walk)
 {
-       struct vm_area_struct *vma = walk->vma;
+       struct vm_area_struct *next, *vma = walk->vma;
        struct queue_pages *qp = walk->private;
        unsigned long endvma = vma->vm_end;
        unsigned long flags = qp->flags;
@@ -669,9 +670,10 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
                        /* hole at head side of range */
                        return -EFAULT;
        }
+       next = find_vma(vma->vm_mm, vma->vm_end);
        if (!(flags & MPOL_MF_DISCONTIG_OK) &&
                ((vma->vm_end < qp->end) &&
-               (!vma->vm_next || vma->vm_end < vma->vm_next->vm_start)))
+               (!next || vma->vm_end < next->vm_start)))
                /* hole at middle or tail of range */
                return -EFAULT;
 
@@ -785,26 +787,24 @@ static int vma_replace_policy(struct vm_area_struct *vma,
 static int mbind_range(struct mm_struct *mm, unsigned long start,
                       unsigned long end, struct mempolicy *new_pol)
 {
+       MA_STATE(mas, &mm->mm_mt, start - 1, start - 1);
        struct vm_area_struct *prev;
        struct vm_area_struct *vma;
        int err = 0;
        pgoff_t pgoff;
-       unsigned long vmstart;
-       unsigned long vmend;
-
-       vma = find_vma(mm, start);
-       VM_BUG_ON(!vma);
 
-       prev = vma->vm_prev;
-       if (start > vma->vm_start)
-               prev = vma;
+       prev = mas_find_rev(&mas, 0);
+       if (prev && (start < prev->vm_end))
+               vma = prev;
+       else
+               vma = mas_next(&mas, end - 1);
 
-       for (; vma && vma->vm_start < end; prev = vma, vma = vma->vm_next) {
-               vmstart = max(start, vma->vm_start);
-               vmend   = min(end, vma->vm_end);
+       for (; vma; vma = mas_next(&mas, end - 1)) {
+               unsigned long vmstart = max(start, vma->vm_start);
+               unsigned long vmend = min(end, vma->vm_end);
 
                if (mpol_equal(vma_policy(vma), new_pol))
-                       continue;
+                       goto next;
 
                pgoff = vma->vm_pgoff +
                        ((vmstart - vma->vm_start) >> PAGE_SHIFT);
@@ -813,6 +813,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
                                 new_pol, vma->vm_userfaultfd_ctx,
                                 anon_vma_name(vma));
                if (prev) {
+                       /* vma_merge() invalidated the mas */
+                       mas_pause(&mas);
                        vma = prev;
                        goto replace;
                }
@@ -820,19 +822,25 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
                        err = split_vma(vma->vm_mm, vma, vmstart, 1);
                        if (err)
                                goto out;
+                       /* split_vma() invalidated the mas */
+                       mas_pause(&mas);
                }
                if (vma->vm_end != vmend) {
                        err = split_vma(vma->vm_mm, vma, vmend, 0);
                        if (err)
                                goto out;
+                       /* split_vma() invalidated the mas */
+                       mas_pause(&mas);
                }
- replace:
+replace:
                err = vma_replace_policy(vma, new_pol);
                if (err)
                        goto out;
+next:
+               prev = vma;
        }
 
- out:
+out:
        return err;
 }
 
@@ -1049,6 +1057,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
                           int flags)
 {
        nodemask_t nmask;
+       struct vm_area_struct *vma;
        LIST_HEAD(pagelist);
        int err = 0;
        struct migration_target_control mtc = {
@@ -1064,8 +1073,9 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
         * need migration.  Between passing in the full user address
         * space range and MPOL_MF_DISCONTIG_OK, this call can not fail.
         */
+       vma = find_vma(mm, 0);
        VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)));
-       queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask,
+       queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask,
                        flags | MPOL_MF_DISCONTIG_OK, &pagelist);
 
        if (!list_empty(&pagelist)) {
@@ -1195,14 +1205,13 @@ static struct page *new_page(struct page *page, unsigned long start)
        struct folio *dst, *src = page_folio(page);
        struct vm_area_struct *vma;
        unsigned long address;
+       VMA_ITERATOR(vmi, current->mm, start);
        gfp_t gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL;
 
-       vma = find_vma(current->mm, start);
-       while (vma) {
+       for_each_vma(vmi, vma) {
                address = page_address_in_vma(page, vma);
                if (address != -EFAULT)
                        break;
-               vma = vma->vm_next;
        }
 
        if (folio_test_hugetlb(src))
@@ -1480,6 +1489,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
        unsigned long vmend;
        unsigned long end;
        int err = -ENOENT;
+       VMA_ITERATOR(vmi, mm, start);
 
        start = untagged_addr(start);
        if (start & ~PAGE_MASK)
@@ -1505,9 +1515,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
        if (end == start)
                return 0;
        mmap_write_lock(mm);
-       vma = find_vma(mm, start);
-       for (; vma && vma->vm_start < end;  vma = vma->vm_next) {
-
+       for_each_vma_range(vmi, vma, end) {
                vmstart = max(start, vma->vm_start);
                vmend   = min(end, vma->vm_end);
                new = mpol_dup(vma_policy(vma));