mm: add statistics for PUD level pagetable

Recently, we found that cross-die access to pagetable pages on ARM64
machines can cause performance fluctuations in our business.  Currently,
there are no PMU events available to track this situation on our ARM64
machines, so accurate pagetable accounting can help to analyze this issue,
but now the PUD level pagetable accounting is missed.

So introduce pagetable_pud_ctor/dtor() to help to get accurate PUD
pagetable accounting, as well as converting the architectures which use
generic PUD pagetable allocation to add corresponding PUD pagetable
accounting.  Moreover this patch will mark the PUD level pagetable with
PG_table flag, which will help to do sanity validation in
unpoison_memory().

On my testing machine, I can see more pagetables statistics after the patch
with page-types tool:

Before patch:
        flags           page-count      MB  symbolic-flags                     long-symbolic-flags
0x0000000004000000           27326      106  __________________________g_________________       pgtable
After patch:
0x0000000004000000           27541      107  __________________________g_________________       pgtable

Link: https://lkml.kernel.org/r/876c71c03a7e69c17722a690e3225a4f7b172fb2.1695017383.git.baolin.wang@linux.alibaba.comSigned-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Acked-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/arm64/include/asm/tlb.h

@@ -96,7 +96,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
-	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pudp));
+	struct ptdesc *ptdesc = virt_to_ptdesc(pudp);
+
+	pagetable_pud_dtor(ptdesc);
+	tlb_remove_ptdesc(tlb, ptdesc);
 }
 #endif
 

arch/loongarch/include/asm/pgalloc.h

@@ -84,6 +84,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 
 	if (!ptdesc)
 		return NULL;
+	pagetable_pud_ctor(ptdesc);
 	pud = ptdesc_address(ptdesc);
 
 	pud_init(pud);

arch/mips/include/asm/pgalloc.h

@@ -95,6 +95,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 
 	if (!ptdesc)
 		return NULL;
+	pagetable_pud_ctor(ptdesc);
 	pud = ptdesc_address(ptdesc);
 
 	pud_init(pud);

arch/x86/mm/pgtable.c

@@ -76,6 +76,9 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
+	struct ptdesc *ptdesc = virt_to_ptdesc(pud);
+
+	pagetable_pud_dtor(ptdesc);
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
 	paravirt_tlb_remove_table(tlb, virt_to_page(pud));
 }

include/asm-generic/pgalloc.h

@@ -169,6 +169,8 @@ static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 	ptdesc = pagetable_alloc(gfp, 0);
 	if (!ptdesc)
 		return NULL;
+
+	pagetable_pud_ctor(ptdesc);
 	return ptdesc_address(ptdesc);
 }
 
@@ -190,8 +192,11 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 
 static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
 {
+	struct ptdesc *ptdesc = virt_to_ptdesc(pud);
+
 	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
-	pagetable_free(virt_to_ptdesc(pud));
+	pagetable_pud_dtor(ptdesc);
+	pagetable_free(ptdesc);
 }
 
 #ifndef __HAVE_ARCH_PUD_FREE

include/linux/mm.h

@@ -3049,6 +3049,22 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
 	return ptl;
 }
 
+static inline void pagetable_pud_ctor(struct ptdesc *ptdesc)
+{
+	struct folio *folio = ptdesc_folio(ptdesc);
+
+	__folio_set_pgtable(folio);
+	lruvec_stat_add_folio(folio, NR_PAGETABLE);
+}
+
+static inline void pagetable_pud_dtor(struct ptdesc *ptdesc)
+{
+	struct folio *folio = ptdesc_folio(ptdesc);
+
+	__folio_clear_pgtable(folio);
+	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
+}
+
 extern void __init pagecache_init(void);
 extern void free_initmem(void);