[PATCH v1 6/9] s390/vmem: cleanup empty page tables

[David Hildenbrand <david@redhat.com>]

Let's cleanup empty page tables. Consider only page tables that fully
fall into the idendity mapping and the vmemmap range.

As there are no valid accesses to vmem/vmemmap within non-populated ranges,
the single tlb flush at the end should be sufficient.

Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 arch/s390/mm/vmem.c | 98 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 97 insertions(+), 1 deletion(-)

diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index aa968f67d7f9f..5239130770b7b 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -63,6 +63,15 @@ pte_t __ref *vmem_pte_alloc(void)
 	return pte;
 }
 
+static void vmem_pte_free(unsigned long *table)
+{
+	/* We don't expect boot memory to be removed ever. */
+	if (!slab_is_available() ||
+	    WARN_ON_ONCE(PageReserved(virt_to_page(table))))
+		return;
+	page_table_free(&init_mm, table);
+}
+
 /*
  * Add a physical memory range to the 1:1 mapping.
  */
@@ -168,6 +177,21 @@ static void remove_pte_table(pmd_t *pmd, unsigned long addr,
 		update_page_count(PG_DIRECT_MAP_4K, -pages);
 }
 
+static void try_free_pte_table(pmd_t *pmd, unsigned long start)
+{
+	pte_t *pte;
+	int i;
+
+	/* We can safely assume this is fully in 1:1 mapping & vmemmap area */
+	pte = pte_offset_kernel(pmd, start);
+	for (i = 0; i < PTRS_PER_PTE; i++, pte++)
+		if (!pte_none(*pte))
+			return;
+
+	vmem_pte_free(__va(pmd_deref(*pmd)));
+	pmd_clear(pmd);
+}
+
 static void remove_pmd_table(pud_t *pud, unsigned long addr,
 			     unsigned long end, bool direct)
 {
@@ -194,12 +218,36 @@ static void remove_pmd_table(pud_t *pud, unsigned long addr,
 		}
 
 		remove_pte_table(pmd, addr, next, direct);
+		try_free_pte_table(pmd, addr & PMD_MASK);
 	}
 
 	if (direct)
 		update_page_count(PG_DIRECT_MAP_1M, -pages);
 }
 
+static void try_free_pmd_table(pud_t *pud, unsigned long start)
+{
+	const unsigned long end = start + PUD_SIZE;
+	pmd_t *pmd;
+	int i;
+
+	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+	if (end > VMALLOC_START)
+		return;
+#ifdef CONFIG_KASAN
+	if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+		return;
+#endif
+
+	pmd = pmd_offset(pud, start);
+	for (i = 0; i < PTRS_PER_PMD; i++, pmd++)
+		if (!pmd_none(*pmd))
+			return;
+
+	vmem_free_pages(pud_deref(*pud), CRST_ALLOC_ORDER);
+	pud_clear(pud);
+}
+
 static void remove_pud_table(p4d_t *p4d, unsigned long addr,
 			     unsigned long end, bool direct)
 {
@@ -224,12 +272,36 @@ static void remove_pud_table(p4d_t *p4d, unsigned long addr,
 		}
 
 		remove_pmd_table(pud, addr, next, direct);
+		try_free_pmd_table(pud, addr & PUD_MASK);
 	}
 
 	if (direct)
 		update_page_count(PG_DIRECT_MAP_2G, -pages);
 }
 
+static void try_free_pud_table(p4d_t *p4d, unsigned long start)
+{
+	const unsigned long end = start + P4D_SIZE;
+	pud_t *pud;
+	int i;
+
+	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+	if (end > VMALLOC_START)
+		return;
+#ifdef CONFIG_KASAN
+	if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+		return;
+#endif
+
+	pud = pud_offset(p4d, start);
+	for (i = 0; i < PTRS_PER_PUD; i++, pud++)
+		if (!pud_none(*pud))
+			return;
+
+	vmem_free_pages(p4d_deref(*p4d), CRST_ALLOC_ORDER);
+	p4d_clear(p4d);
+}
+
 static void remove_p4d_table(pgd_t *pgd, unsigned long addr,
 			     unsigned long end, bool direct)
 {
@@ -244,9 +316,33 @@ static void remove_p4d_table(pgd_t *pgd, unsigned long addr,
 			continue;
 
 		remove_pud_table(p4d, addr, next, direct);
+		try_free_pud_table(p4d, addr & P4D_MASK);
 	}
 }
 
+static void try_free_p4d_table(pgd_t *pgd, unsigned long start)
+{
+	const unsigned long end = start + PGDIR_SIZE;
+	p4d_t *p4d;
+	int i;
+
+	/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+	if (end > VMALLOC_START)
+		return;
+#ifdef CONFIG_KASAN
+	if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+		return;
+#endif
+
+	p4d = p4d_offset(pgd, start);
+	for (i = 0; i < PTRS_PER_P4D; i++, p4d++)
+		if (!p4d_none(*p4d))
+			return;
+
+	vmem_free_pages(pgd_deref(*pgd), CRST_ALLOC_ORDER);
+	pgd_clear(pgd);
+}
+
 static void remove_pagetable(unsigned long start, unsigned long end,
 			     bool direct)
 {
@@ -264,6 +360,7 @@ static void remove_pagetable(unsigned long start, unsigned long end,
 			continue;
 
 		remove_p4d_table(pgd, addr, next, direct);
+		try_free_p4d_table(pgd, addr & PGDIR_MASK);
 	}
 
 	flush_tlb_kernel_range(start, end);
@@ -271,7 +368,6 @@ static void remove_pagetable(unsigned long start, unsigned long end,
 
 /*
  * Remove a physical memory range from the 1:1 mapping.
- * Currently only invalidates page table entries.
  */
 static void vmem_remove_range(unsigned long start, unsigned long size)
 {
-- 
2.26.2