Re: [PATCH] ARM64: Implement arch_report_meminfo()

["Christoph Lameter (Ampere)" <cl@linux.com>]

On Thu, 14 Dec 2023, Robin Murphy wrote:

> It seems somewhat suspect that these counts only ever increase. It's not 
> often that we change or remove parts of the linear map, but it certainly can 
> happen.

Well yes in the case of hotplug I guess ... Ok here is V2



From cl@gentwo.org Fri Dec  8 13:11:58 2023
From: "Christoph Lameter (Ampere)" <cl@gentwo.org>
To: Catalin Marinas <catalin.marinas@arm.com>, Marc Zyngier <maz@kernel.org>, Will Deacon <will@kernel.org>, Ryan Roberts <ryan.roberts@arm.com>, Mark Rutland <mark.rutland@arm.com>, Vishal Moola <vishal.moola@gmail.com>
Cc: linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org
Subject: [PATCH] ARM64: Implement arch_report_meminfo()

V1->V2 hotplug and umapping support

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 (Ampere) <cl@linux.com>

Index: linux/arch/arm64/mm/mmu.c
===================================================================
--- linux.orig/arch/arm64/mm/mmu.c
+++ linux/arch/arm64/mm/mmu.c
@@ -76,6 +76,13 @@ EXPORT_SYMBOL(empty_zero_page);
  static DEFINE_SPINLOCK(swapper_pgdir_lock);
  static DEFINE_MUTEX(fixmap_lock);

+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;
+
+
  void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
  {
  	pgd_t *fixmap_pgdp;
@@ -179,6 +186,7 @@ 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 +231,10 @@ 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 +259,7 @@ 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 +312,10 @@ 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 +359,7 @@ 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.
@@ -859,6 +872,11 @@ static void unmap_hotplug_pte_range(pmd_
  			continue;

  		WARN_ON(!pte_present(pte));
+
+		if (pte_cont(pte))
+			atomic_dec(&nr_pte_cont);
+		atomic_dec(&nr_pte);
+
  		pte_clear(&init_mm, addr, ptep);
  		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
  		if (free_mapped)
@@ -883,6 +901,11 @@ static void unmap_hotplug_pmd_range(pud_

  		WARN_ON(!pmd_present(pmd));
  		if (pmd_sect(pmd)) {
+
+			if (pmd_cont(pmd))
+				atomic_dec(&nr_pmd_cont);
+			atomic_dec(&nr_pmd);
+
  			pmd_clear(pmdp);

  			/*
@@ -916,6 +939,9 @@ static void unmap_hotplug_pud_range(p4d_

  		WARN_ON(!pud_present(pud));
  		if (pud_sect(pud)) {
+
+			atomic_dec(&nr_pud);
+
  			pud_clear(pudp);

  			/*
@@ -1010,6 +1036,7 @@ static void free_empty_pte_table(pmd_t *
  			return;
  	}

+	atomic_dec(&nr_pmd);
  	pmd_clear(pmdp);
  	__flush_tlb_kernel_pgtable(start);
  	free_hotplug_pgtable_page(virt_to_page(ptep));
@@ -1050,6 +1077,7 @@ static void free_empty_pmd_table(pud_t *
  			return;
  	}

+	atomic_dec(&nr_pud);
  	pud_clear(pudp);
  	__flush_tlb_kernel_pgtable(start);
  	free_hotplug_pgtable_page(virt_to_page(pmdp));
@@ -1225,6 +1253,7 @@ int pmd_free_pte_page(pmd_t *pmdp, unsig
  	}

  	table = pte_offset_kernel(pmdp, addr);
+	atomic_dec(&nr_pmd);
  	pmd_clear(pmdp);
  	__flush_tlb_kernel_pgtable(addr);
  	pte_free_kernel(NULL, table);
@@ -1253,6 +1282,7 @@ int pud_free_pmd_page(pud_t *pudp, unsig
  		pmd_free_pte_page(pmdp, next);
  	} while (pmdp++, next += PMD_SIZE, next != end);

+	atomic_dec(&nr_pud);
  	pud_clear(pudp);
  	__flush_tlb_kernel_pgtable(addr);
  	pmd_free(NULL, table);
@@ -1486,3 +1516,36 @@ 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
+