mm: account PMD tables like PTE tables

We account the PTE level of the page tables to the process in order to
make smarter OOM decisions and help diagnose why memory is fragmented.
For these same reasons, we should account pages allocated for PMDs.  With
larger process address spaces and ASLR, the number of PMDs in use is
higher than it used to be so the inaccuracy is starting to matter.

[rppt@linux.ibm.com: arm: __pmd_free_tlb(): call page table destructor]
Link: https://lkml.kernel.org/r/20200825111303.GB69694@linux.ibm.com
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Cc: Anders Roxell <anders.roxell@linaro.org>
Link: http://lkml.kernel.org/r/20200627184642.GF25039@casper.infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 9415222b49ad395d6274d874db06e0f6bd113c5a..b8cbe03ad260344abc1fa74a54bcd036b996eb37 100644 (file)
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -59,6 +59,7 @@ __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 #ifdef CONFIG_ARM_LPAE
        struct page *page = virt_to_page(pmdp);
 
+       pgtable_pmd_page_dtor(page);
        tlb_remove_table(tlb, page);
 #endif
 }

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9cc0894e7d61079df2fe7c9b1c71424e9d3d19c9..5320e7ab843f19540b77d11a9627558700d41a88 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2254,7 +2254,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
        return ptlock_ptr(pmd_to_page(pmd));
 }
 
-static inline bool pgtable_pmd_page_ctor(struct page *page)
+static inline bool pmd_ptlock_init(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
        page->pmd_huge_pte = NULL;
@@ -2262,7 +2262,7 @@ static inline bool pgtable_pmd_page_ctor(struct page *page)
        return ptlock_init(page);
 }
 
-static inline void pgtable_pmd_page_dtor(struct page *page)
+static inline void pmd_ptlock_free(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
        VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
@@ -2279,8 +2279,8 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
        return &mm->page_table_lock;
 }
 
-static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; }
-static inline void pgtable_pmd_page_dtor(struct page *page) {}
+static inline bool pmd_ptlock_init(struct page *page) { return true; }
+static inline void pmd_ptlock_free(struct page *page) {}
 
 #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
 
@@ -2293,6 +2293,22 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
        return ptl;
 }
 
+static inline bool pgtable_pmd_page_ctor(struct page *page)
+{
+       if (!pmd_ptlock_init(page))
+               return false;
+       __SetPageTable(page);
+       inc_zone_page_state(page, NR_PAGETABLE);
+       return true;
+}
+
+static inline void pgtable_pmd_page_dtor(struct page *page)
+{
+       pmd_ptlock_free(page);
+       __ClearPageTable(page);
+       dec_zone_page_state(page, NR_PAGETABLE);
+}
+
 /*
  * No scalability reason to split PUD locks yet, but follow the same pattern
  * as the PMD locks to make it easier if we decide to.  The VM should not be