mm: remove redundant smp_wmb()

The smp_wmb() which is in the __pte_alloc() is used to ensure all ptes
setup is visible before the pte is made visible to other CPUs by being
put into page tables.  We only need this when the pte is actually
populated, so move it to pmd_install().  __pte_alloc_kernel(),
__p4d_alloc(), __pud_alloc() and __pmd_alloc() are similar to this case.

We can also defer smp_wmb() to the place where the pmd entry is really
populated by preallocated pte.  There are two kinds of user of
preallocated pte, one is filemap & finish_fault(), another is THP.  The
former does not need another smp_wmb() because the smp_wmb() has been
done by pmd_install().  Fortunately, the latter also does not need
another smp_wmb() because there is already a smp_wmb() before populating
the new pte when the THP uses a preallocated pte to split a huge pmd.

Link: https://lkml.kernel.org/r/20210901102722.47686-3-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mika Penttila <mika.penttila@nextfour.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 23 insertions, 29 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 38d63f6d998b..5db36280950a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -439,6 +439,20 @@ void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte)
 
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		mm_inc_nr_ptes(mm);
+		/*
+		 * Ensure all pte setup (eg. pte page lock and page clearing) are
+		 * visible before the pte is made visible to other CPUs by being
+		 * put into page tables.
+		 *
+		 * The other side of the story is the pointer chasing in the page
+		 * table walking code (when walking the page table without locking;
+		 * ie. most of the time). Fortunately, these data accesses consist
+		 * of a chain of data-dependent loads, meaning most CPUs (alpha
+		 * being the notable exception) will already guarantee loads are
+		 * seen in-order. See the alpha page table accessors for the
+		 * smp_rmb() barriers in page table walking code.
+		 */
+		smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 		pmd_populate(mm, pmd, *pte);
 		*pte = NULL;
 	}
@@ -451,21 +465,6 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd)
 	if (!new)
 		return -ENOMEM;
 
-	/*
-	 * Ensure all pte setup (eg. pte page lock and page clearing) are
-	 * visible before the pte is made visible to other CPUs by being
-	 * put into page tables.
-	 *
-	 * The other side of the story is the pointer chasing in the page
-	 * table walking code (when walking the page table without locking;
-	 * ie. most of the time). Fortunately, these data accesses consist
-	 * of a chain of data-dependent loads, meaning most CPUs (alpha
-	 * being the notable exception) will already guarantee loads are
-	 * seen in-order. See the alpha page table accessors for the
-	 * smp_rmb() barriers in page table walking code.
-	 */
-	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
-
 	pmd_install(mm, pmd, &new);
 	if (new)
 		pte_free(mm, new);
@@ -478,10 +477,9 @@ int __pte_alloc_kernel(pmd_t *pmd)
 	if (!new)
 		return -ENOMEM;
 
-	smp_wmb(); /* See comment in __pte_alloc */
-
 	spin_lock(&init_mm.page_table_lock);
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
+		smp_wmb(); /* See comment in pmd_install() */
 		pmd_populate_kernel(&init_mm, pmd, new);
 		new = NULL;
 	}
@@ -3845,7 +3843,6 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
-		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
 	ret = vma->vm_ops->fault(vmf);
@@ -3916,7 +3913,6 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 		vmf->prealloc_pte = pte_alloc_one(vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
-		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
 	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
@@ -4141,7 +4137,6 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf)
 		vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm);
 		if (!vmf->prealloc_pte)
 			return VM_FAULT_OOM;
-		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
 	return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff);
@@ -4815,13 +4810,13 @@ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
 	if (!new)
 		return -ENOMEM;
 
-	smp_wmb(); /* See comment in __pte_alloc */
-
 	spin_lock(&mm->page_table_lock);
-	if (pgd_present(*pgd))		/* Another has populated it */
+	if (pgd_present(*pgd)) {	/* Another has populated it */
 		p4d_free(mm, new);
-	else
+	} else {
+		smp_wmb(); /* See comment in pmd_install() */
 		pgd_populate(mm, pgd, new);
+	}
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
@@ -4838,11 +4833,10 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address)
 	if (!new)
 		return -ENOMEM;
 
-	smp_wmb(); /* See comment in __pte_alloc */
-
 	spin_lock(&mm->page_table_lock);
 	if (!p4d_present(*p4d)) {
 		mm_inc_nr_puds(mm);
+		smp_wmb(); /* See comment in pmd_install() */
 		p4d_populate(mm, p4d, new);
 	} else	/* Another has populated it */
 		pud_free(mm, new);
@@ -4863,14 +4857,14 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 	if (!new)
 		return -ENOMEM;
 
-	smp_wmb(); /* See comment in __pte_alloc */
-
 	ptl = pud_lock(mm, pud);
 	if (!pud_present(*pud)) {
 		mm_inc_nr_pmds(mm);
+		smp_wmb(); /* See comment in pmd_install() */
 		pud_populate(mm, pud, new);
-	} else	/* Another has populated it */
+	} else {	/* Another has populated it */
 		pmd_free(mm, new);
+	}
 	spin_unlock(ptl);
 	return 0;
 }