mm/ksm: convert break_ksm() to use walk_page_range_vma()

FOLL_MIGRATION exists only for the purpose of break_ksm(), and actually,
there is not even the need to wait for the migration to finish, we only
want to know if we're dealing with a KSM page.

Using follow_page() just to identify a KSM page overcomplicates GUP code.
Let's use walk_page_range_vma() instead, because we don't actually care
about the page itself, we only need to know a single property -- no need
to even grab a reference.

So, get rid of follow_page() usage such that we can get rid of
FOLL_MIGRATION now and eventually be able to get rid of follow_page() in
the future.

In my setup (AMD Ryzen 9 3900X), running the KSM selftest to test unmerge
performance on 2 GiB (taskset 0x8 ./ksm_tests -D -s 2048), this results in
a performance degradation of ~2% (old: ~5010 MiB/s, new: ~4900 MiB/s).  I
don't think we particularly care for now.

Interestingly, the benchmark reduction is due to the single callback.
Adding a second callback (e.g., pud_entry()) reduces the benchmark by
another 100-200 MiB/s.

Link: https://lkml.kernel.org/r/20221021101141.84170-9-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/ksm.c b/mm/ksm.c
index 0805221..dd02780 100644 (file)
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -39,6 +39,7 @@
 #include <linux/freezer.h>
 #include <linux/oom.h>
 #include <linux/numa.h>
+#include <linux/pagewalk.h>
 
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -419,6 +420,39 @@ static inline bool ksm_test_exit(struct mm_struct *mm)
        return atomic_read(&mm->mm_users) == 0;
 }
 
+static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next,
+                       struct mm_walk *walk)
+{
+       struct page *page = NULL;
+       spinlock_t *ptl;
+       pte_t *pte;
+       int ret;
+
+       if (pmd_leaf(*pmd) || !pmd_present(*pmd))
+               return 0;
+
+       pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+       if (pte_present(*pte)) {
+               page = vm_normal_page(walk->vma, addr, *pte);
+       } else if (!pte_none(*pte)) {
+               swp_entry_t entry = pte_to_swp_entry(*pte);
+
+               /*
+                * As KSM pages remain KSM pages until freed, no need to wait
+                * here for migration to end.
+                */
+               if (is_migration_entry(entry))
+                       page = pfn_swap_entry_to_page(entry);
+       }
+       ret = page && PageKsm(page);
+       pte_unmap_unlock(pte, ptl);
+       return ret;
+}
+
+static const struct mm_walk_ops break_ksm_ops = {
+       .pmd_entry = break_ksm_pmd_entry,
+};
+
 /*
  * We use break_ksm to break COW on a ksm page by triggering unsharing,
  * such that the ksm page will get replaced by an exclusive anonymous page.
@@ -434,21 +468,16 @@ static inline bool ksm_test_exit(struct mm_struct *mm)
  */
 static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 {
-       struct page *page;
        vm_fault_t ret = 0;
 
        do {
-               bool ksm_page = false;
+               int ksm_page;
 
                cond_resched();
-               page = follow_page(vma, addr,
-                               FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE);
-               if (IS_ERR_OR_NULL(page))
-                       break;
-               if (PageKsm(page))
-                       ksm_page = true;
-               put_page(page);
-
+               ksm_page = walk_page_range_vma(vma, addr, addr + 1,
+                                              &break_ksm_ops, NULL);
+               if (WARN_ON_ONCE(ksm_page < 0))
+                       return ksm_page;
                if (!ksm_page)
                        return 0;
                ret = handle_mm_fault(vma, addr,