[PATCH] ARM64: Implement arch_report_meminfo()

[Christoph Lameter (Ampere)]

X86 has information in /proc/meminfo showing the use of large mappings
for the kernel direct map. This has now also become important for
ARM since the kernel default CONFIG_RODATA_FULL_DEFAULT_ENABLED
forces 4K PTE use for the direct map and users may not be aware
of the performance impact of the increased TLB use etc.

The output of /proc/meminfo on ARM64 is then after this patch:

4K page size:

Hugepagesize:       2048 kB
Hugetlb:               0 kB
DirectMap4k:      155912 kB
CONT DMap4k:        1176 kB
DirectMap2M:      722944 kB
CONT DMap2M:       28672 kB
DirectMap1G:   534773760 kB

64K page size:

Hugepagesize:     524288 kB
Hugetlb:               0 kB
DirectMap64k:      882624 kB
CONT DMap64k:       19904 kB
DirectMap512M:    534773760 kB
CONT DMap512M:           0 kB
DirectMap4096G:           0 kB

Signed-off-by: Christoph Lameter <cl at linux.com>

Index: linux/arch/arm64/mm/mmu.c
===================================================================
--- linux.orig/arch/arm64/mm/mmu.c
+++ linux/arch/arm64/mm/mmu.c
@@ -66,6 +66,12 @@ u32 __boot_cpu_mode[] = { BOOT_CPU_MODE_
   */
  long __section(".mmuoff.data.write") __early_cpu_boot_status;

+static atomic_t nr_pte;
+static atomic_t nr_pmd;
+static atomic_t nr_pud;
+static atomic_t nr_pte_cont;
+static atomic_t nr_pmd_cont;
+
  /*
   * Empty_zero_page is a special page that is used for zero-initialized data
   * and COW.
@@ -179,6 +185,7 @@ static void init_pte(pmd_t *pmdp, unsign
  		pte_t old_pte = READ_ONCE(*ptep);

  		set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+		atomic_inc(&nr_pte);

  		/*
  		 * After the PTE entry has been populated once, we
@@ -223,8 +230,10 @@ static void alloc_init_cont_pte(pmd_t *p

  		/* use a contiguous mapping if the range is suitably aligned */
  		if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
-		    (flags & NO_CONT_MAPPINGS) == 0)
+		    (flags & NO_CONT_MAPPINGS) == 0) {
  			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+			atomic_inc(&nr_pte_cont);
+		}

  		init_pte(pmdp, addr, next, phys, __prot);

@@ -249,6 +258,7 @@ static void init_pmd(pud_t *pudp, unsign
  		if (((addr | next | phys) & ~PMD_MASK) == 0 &&
  		    (flags & NO_BLOCK_MAPPINGS) == 0) {
  			pmd_set_huge(pmdp, phys, prot);
+			atomic_inc(&nr_pmd);

  			/*
  			 * After the PMD entry has been populated once, we
@@ -301,8 +311,10 @@ static void alloc_init_cont_pmd(pud_t *p

  		/* use a contiguous mapping if the range is suitably aligned */
  		if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) &&
-		    (flags & NO_CONT_MAPPINGS) == 0)
+		    (flags & NO_CONT_MAPPINGS) == 0) {
  			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+			atomic_inc(&nr_pmd_cont);
+		}

  		init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);

@@ -346,7 +358,7 @@ static void alloc_init_pud(pgd_t *pgdp,
  		   ((addr | next | phys) & ~PUD_MASK) == 0 &&
  		    (flags & NO_BLOCK_MAPPINGS) == 0) {
  			pud_set_huge(pudp, phys, prot);
-
+			atomic_inc(&nr_pud);
  			/*
  			 * After the PUD entry has been populated once, we
  			 * only allow updates to the permission attributes.
@@ -1486,3 +1498,35 @@ void ptep_modify_prot_commit(struct vm_a
  {
  	set_pte_at(vma->vm_mm, addr, ptep, pte);
  }
+
+#ifdef CONFIG_PROC_FS
+void arch_report_meminfo(struct seq_file *m)
+{
+	unsigned long pagesize_in_kb = PAGE_SIZE / 1024;
+
+	seq_printf(m, "DirectMap%luk:    %8lu kB\n",
+			pagesize_in_kb,
+		  	(unsigned long)atomic_read(&nr_pte) * pagesize_in_kb);
+
+        seq_printf(m, "CONT DMap%luk:    %8lu kB\n",
+			pagesize_in_kb,
+			(unsigned long)atomic_read(&nr_pte_cont) * pagesize_in_kb);
+
+	pagesize_in_kb = PMD_SIZE / 1024;
+
+        seq_printf(m, "DirectMap%luM:    %8lu kB\n",
+			pagesize_in_kb / 1024,
+			(unsigned long)atomic_read(&nr_pmd) * pagesize_in_kb);
+
+	seq_printf(m, "CONT DMap%luM:    %8lu kB\n",
+			pagesize_in_kb / 1024,
+			(unsigned long)atomic_read(&nr_pmd_cont) * pagesize_in_kb);
+
+	pagesize_in_kb = PUD_SIZE / 1024;
+
+	seq_printf(m, "DirectMap%luG:  %10lu kB\n",
+		       	pagesize_in_kb >> 20,
+                        (unsigned long)atomic_read(&nr_pud) * pagesize_in_kb);
+}
+#endif
+