s390/mm: implement software dirty bits

The s390 architecture is unique in respect to dirty page detection,
it uses the change bit in the per-page storage key to track page
modifications. All other architectures track dirty bits by means
of page table entries. This property of s390 has caused numerous
problems in the past, e.g. see git commit ef5d437f71afdf4a
"mm: fix XFS oops due to dirty pages without buffers on s390".

To avoid future issues in regard to per-page dirty bits convert
s390 to a fault based software dirty bit detection mechanism. All
user page table entries which are marked as clean will be hardware
read-only, even if the pte is supposed to be writable. A write by
the user process will trigger a protection fault which will cause
the user pte to be marked as dirty and the hardware read-only bit
is removed.

With this change the dirty bit in the storage key is irrelevant
for Linux as a host, but the storage key is still required for
KVM guests. The effect is that page_test_and_clear_dirty and the
related code can be removed. The referenced bit in the storage
key is still used by the page_test_and_clear_young primitive to
provide page age information.

For page cache pages of mappings with mapping_cap_account_dirty
there will not be any change in behavior as the dirty bit tracking
already uses read-only ptes to control the amount of dirty pages.
Only for swap cache pages and pages of mappings without
mapping_cap_account_dirty there can be additional protection faults.
To avoid an excessive number of additional faults the mk_pte
primitive checks for PageDirty if the pgprot value allows for writes
and pre-dirties the pte. That avoids all additional faults for
tmpfs and shmem pages until these pages are added to the swap cache.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

1 files changed, 10 insertions, 14 deletions

diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 6ed1426d27c5..79699f46a443 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -85,11 +85,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 	pud_t *pu_dir;
 	pmd_t *pm_dir;
 	pte_t *pt_dir;
-	pte_t  pte;
 	int ret = -ENOMEM;
 
 	while (address < end) {
-		pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0));
 		pg_dir = pgd_offset_k(address);
 		if (pgd_none(*pg_dir)) {
 			pu_dir = vmem_pud_alloc();
@@ -101,9 +99,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 #if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC)
 		if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
 		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) {
-			pte_val(pte) |= _REGION3_ENTRY_LARGE;
-			pte_val(pte) |= _REGION_ENTRY_TYPE_R3;
-			pud_val(*pu_dir) = pte_val(pte);
+			pud_val(*pu_dir) = __pa(address) |
+				_REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE |
+				(ro ? _REGION_ENTRY_RO : 0);
 			address += PUD_SIZE;
 			continue;
 		}
@@ -118,8 +116,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 #if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC)
 		if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
 		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) {
-			pte_val(pte) |= _SEGMENT_ENTRY_LARGE;
-			pmd_val(*pm_dir) = pte_val(pte);
+			pmd_val(*pm_dir) = __pa(address) |
+				_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE |
+				(ro ? _SEGMENT_ENTRY_RO : 0);
 			address += PMD_SIZE;
 			continue;
 		}
@@ -132,7 +131,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		}
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
-		*pt_dir = pte;
+		pte_val(*pt_dir) = __pa(address) | (ro ? _PAGE_RO : 0);
 		address += PAGE_SIZE;
 	}
 	ret = 0;
@@ -199,7 +198,6 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 	pud_t *pu_dir;
 	pmd_t *pm_dir;
 	pte_t *pt_dir;
-	pte_t  pte;
 	int ret = -ENOMEM;
 
 	start_addr = (unsigned long) start;
@@ -237,9 +235,8 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 				new_page = vmemmap_alloc_block(PMD_SIZE, node);
 				if (!new_page)
 					goto out;
-				pte = mk_pte_phys(__pa(new_page), PAGE_RW);
-				pte_val(pte) |= _SEGMENT_ENTRY_LARGE;
-				pmd_val(*pm_dir) = pte_val(pte);
+				pmd_val(*pm_dir) = __pa(new_page) |
+					_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE;
 				address = (address + PMD_SIZE) & PMD_MASK;
 				continue;
 			}
@@ -260,8 +257,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 			new_page =__pa(vmem_alloc_pages(0));
 			if (!new_page)
 				goto out;
-			pte = pfn_pte(new_page >> PAGE_SHIFT, PAGE_KERNEL);
-			*pt_dir = pte;
+			pte_val(*pt_dir) = __pa(new_page);
 		}
 		address += PAGE_SIZE;
 	}