[Devel] [PATCH RHEL8 COMMIT] mm: merge parameters for change_protection()

Konstantin Khorenko khorenko at virtuozzo.com
Mon Apr 20 10:34:35 MSK 2020


The commit is pushed to "branch-rh8-4.18.0-80.1.2.vz8.3.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh8-4.18.0-80.1.2.vz8.3.6
------>
commit 4d093406772d166af87d0e4fe6d6cc33ee87e072
Author: Peter Xu <peterx at redhat.com>
Date:   Mon Apr 20 10:34:35 2020 +0300

    mm: merge parameters for change_protection()
    
    change_protection() was used by either the NUMA or mprotect() code,
    there's one parameter for each of the callers (dirty_accountable and
    prot_numa).  Further, these parameters are passed along the calls:
    
      - change_protection_range()
      - change_p4d_range()
      - change_pud_range()
      - change_pmd_range()
      - ...
    
    Now we introduce a flag for change_protect() and all these helpers to
    replace these parameters.  Then we can avoid passing multiple parameters
    multiple times along the way.
    
    More importantly, it'll greatly simplify the work if we want to introduce
    any new parameters to change_protection().  In the follow up patches, a
    new parameter for userfaultfd write protection will be introduced.
    
    No functional change at all.
    
    Signed-off-by: Peter Xu <peterx at redhat.com>
    Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
    Reviewed-by: Jerome Glisse <jglisse at redhat.com>
    Cc: Andrea Arcangeli <aarcange at redhat.com>
    Cc: Bobby Powers <bobbypowers at gmail.com>
    Cc: Brian Geffon <bgeffon at google.com>
    Cc: David Hildenbrand <david at redhat.com>
    Cc: Denis Plotnikov <dplotnikov at virtuozzo.com>
    Cc: "Dr . David Alan Gilbert" <dgilbert at redhat.com>
    Cc: Hugh Dickins <hughd at google.com>
    Cc: Johannes Weiner <hannes at cmpxchg.org>
    Cc: "Kirill A . Shutemov" <kirill at shutemov.name>
    Cc: Martin Cracauer <cracauer at cons.org>
    Cc: Marty McFadden <mcfadden8 at llnl.gov>
    Cc: Maya Gokhale <gokhale2 at llnl.gov>
    Cc: Mel Gorman <mgorman at suse.de>
    Cc: Mike Kravetz <mike.kravetz at oracle.com>
    Cc: Mike Rapoport <rppt at linux.vnet.ibm.com>
    Cc: Pavel Emelyanov <xemul at openvz.org>
    Cc: Rik van Riel <riel at redhat.com>
    Cc: Shaohua Li <shli at fb.com>
    Link: http://lkml.kernel.org/r/20200220163112.11409-7-peterx@redhat.com
    Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
    
    https://jira.sw.ru/browse/PSBM-102938
    (cherry picked from commit 58705444c45b3ca987b03bd9beb41bbbe41ae439)
    Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 include/linux/huge_mm.h |  2 +-
 include/linux/mm.h      | 14 +++++++++++++-
 mm/huge_memory.c        |  3 ++-
 mm/mempolicy.c          |  2 +-
 mm/mprotect.c           | 29 ++++++++++++++++-------------
 5 files changed, 33 insertions(+), 17 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 0bec79ae4c2d..8de3c1d71173 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -45,7 +45,7 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 			 pmd_t *old_pmd, pmd_t *new_pmd);
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
-			int prot_numa);
+			unsigned long cp_flags);
 int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 			pmd_t *pmd, pfn_t pfn, bool write);
 int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9bddcabb654c..8973ce5aa46b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1662,9 +1662,21 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len,
 		bool need_rmap_locks);
+
+/*
+ * Flags used by change_protection().  For now we make it a bitmap so
+ * that we can pass in multiple flags just like parameters.  However
+ * for now all the callers are only use one of the flags at the same
+ * time.
+ */
+/* Whether we should allow dirty bit accounting */
+#define  MM_CP_DIRTY_ACCT                  (1UL << 0)
+/* Whether this protection change is for NUMA hints */
+#define  MM_CP_PROT_NUMA                   (1UL << 1)
+
 extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 			      unsigned long end, pgprot_t newprot,
-			      int dirty_accountable, int prot_numa);
+			      unsigned long cp_flags);
 extern int mprotect_fixup(struct vm_area_struct *vma,
 			  struct vm_area_struct **pprev, unsigned long start,
 			  unsigned long end, unsigned long newflags);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 68a77dc14a19..77a827a55703 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1835,13 +1835,14 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
  *  - HPAGE_PMD_NR is protections changed and TLB flush necessary
  */
 int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long addr, pgprot_t newprot, int prot_numa)
+		unsigned long addr, pgprot_t newprot, unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
 	pmd_t entry;
 	bool preserve_write;
 	int ret;
+	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
 
 	ptl = __pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 33e8ea655214..08528c72e9c3 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -554,7 +554,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 {
 	int nr_updated;
 
-	nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
+	nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA);
 	if (nr_updated)
 		count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 6d331620b9e5..69bcfb33314e 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,13 +37,15 @@
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa)
+		unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 	unsigned long pages = 0;
 	int target_node = NUMA_NO_NODE;
+	bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT;
+	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
 
 	/*
 	 * Can be called with only the mmap_sem for reading by
@@ -164,7 +166,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pud_t *pud, unsigned long addr, unsigned long end,
-		pgprot_t newprot, int dirty_accountable, int prot_numa)
+		pgprot_t newprot, unsigned long cp_flags)
 {
 	pmd_t *pmd;
 	struct mm_struct *mm = vma->vm_mm;
@@ -193,7 +195,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 				__split_huge_pmd(vma, pmd, addr, false, NULL);
 			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
-						newprot, prot_numa);
+							      newprot, cp_flags);
 
 				if (nr_ptes) {
 					if (nr_ptes == HPAGE_PMD_NR) {
@@ -208,7 +210,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 			/* fall through, the trans huge pmd just split */
 		}
 		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+					      cp_flags);
 		pages += this_pages;
 next:
 		cond_resched();
@@ -224,7 +226,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 
 static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 		p4d_t *p4d, unsigned long addr, unsigned long end,
-		pgprot_t newprot, int dirty_accountable, int prot_numa)
+		pgprot_t newprot, unsigned long cp_flags)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -236,7 +238,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 		if (pud_none_or_clear_bad(pud))
 			continue;
 		pages += change_pmd_range(vma, pud, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+					  cp_flags);
 	} while (pud++, addr = next, addr != end);
 
 	return pages;
@@ -244,7 +246,7 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma,
 
 static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 		pgd_t *pgd, unsigned long addr, unsigned long end,
-		pgprot_t newprot, int dirty_accountable, int prot_numa)
+		pgprot_t newprot, unsigned long cp_flags)
 {
 	p4d_t *p4d;
 	unsigned long next;
@@ -256,7 +258,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 		if (p4d_none_or_clear_bad(p4d))
 			continue;
 		pages += change_pud_range(vma, p4d, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+					  cp_flags);
 	} while (p4d++, addr = next, addr != end);
 
 	return pages;
@@ -264,7 +266,7 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
 
 static unsigned long change_protection_range(struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa)
+		unsigned long cp_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
@@ -281,7 +283,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
 		pages += change_p4d_range(vma, pgd, addr, next, newprot,
-				 dirty_accountable, prot_numa);
+					  cp_flags);
 	} while (pgd++, addr = next, addr != end);
 
 	/* Only flush the TLB if we actually modified any entries: */
@@ -294,14 +296,15 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 
 unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end, pgprot_t newprot,
-		       int dirty_accountable, int prot_numa)
+		       unsigned long cp_flags)
 {
 	unsigned long pages;
 
 	if (is_vm_hugetlb_page(vma))
 		pages = hugetlb_change_protection(vma, start, end, newprot);
 	else
-		pages = change_protection_range(vma, start, end, newprot, dirty_accountable, prot_numa);
+		pages = change_protection_range(vma, start, end, newprot,
+						cp_flags);
 
 	return pages;
 }
@@ -429,7 +432,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	vma_set_page_prot(vma);
 
 	change_protection(vma, start, end, vma->vm_page_prot,
-			  dirty_accountable, 0);
+			  dirty_accountable ? MM_CP_DIRTY_ACCT : 0);
 
 	/*
 	 * Private VM_LOCKED VMA becoming writable: trigger COW to avoid major


More information about the Devel mailing list