[RFC PATCH 1/4] powerpc/mm/book3s: Update pmd_present to look at _PAGE_PRESENT bit

[RFC PATCH 1/4] powerpc/mm/book3s: Update pmd_present to look at _PAGE_PRESENT bit

[Aneesh Kumar K.V]

With this patch we use 0x8000000000000000UL (_PAGE_PRESENT) to indicate a valid
pgd/pud/pmd entry. We also switch the p**_present() to look at this bit.

With pmd_present, we have a special case. We need to make sure we consider a
pmd marked invalid during THP split as present. Right now we clear the
_PAGE_PRESENT bit during a pmdp_invalidate. Inorder to consider this special
case we add a new pte bit _PAGE_INVALID (mapped to _RPAGE_SW0). This bit is
only used with _PAGE_PRESENT cleared. Hence we are not really loosing a pte bit
for this special case. pmd_present is also updated to look at _PAGE_INVALID.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/hash.h    |  5 +++++
 arch/powerpc/include/asm/book3s/64/pgtable.h | 23 +++++++++++++++++---
 arch/powerpc/mm/hash_utils_64.c              |  6 ++---
 arch/powerpc/mm/pgtable-book3s64.c           |  2 +-
 4 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 0387b155f13d..a371ac7c3183 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -16,6 +16,11 @@
 #include <asm/book3s/64/hash-4k.h>
 #endif
 
+/* Bits to set in a PMD/PUD/PGD entry valid bit*/
+#define HASH_PMD_VAL_BITS		(0x8000000000000000UL)
+#define HASH_PUD_VAL_BITS		(0x8000000000000000UL)
+#define HASH_PGD_VAL_BITS		(0x8000000000000000UL)
+
 /*
  * Size of EA range mapped by our pagetables.
  */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 676118743a06..fce9ce8781a0 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -44,6 +44,15 @@
 
 #define _PAGE_PTE		0x4000000000000000UL	/* distinguishes PTEs from pointers */
 #define _PAGE_PRESENT		0x8000000000000000UL	/* pte contains a translation */
+/*
+ * We need to mark a pmd pte invalid while splitting. We can do that by clearing the
+ * _PAGE_PRESENT bit. But then that will be taken as a swap pte. Inorder to differentiate
+ * between two use a SW field when invalidating. We don't add a special bit to indicate
+ * swap pte because that is also used for migration ptes, and we do back and forth between
+ * a valid pte entry and migration ptes. So any information in the software bits will be
+ * lost if we overload those bits.
+ */
+#define _PAGE_INVALID		_RPAGE_SW0
 
 /*
  * Top and bottom bits of RPN which can be used by hash
@@ -859,8 +868,16 @@ static inline int pmd_none(pmd_t pmd)
 
 static inline int pmd_present(pmd_t pmd)
 {
+	/*
+	 * A pmd is considerent present if _PAGE_PRESENT is set.
+	 * We also need to consider the pmd present which is marked
+	 * invalid during a split. Hence we look for _PAGE_INVALID
+	 * if we find _PAGE_PRESENT cleared.
+	 */
+	if (pmd_raw(pmd) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID))
+		return true;
 
-	return !pmd_none(pmd);
+	return false;
 }
 
 static inline int pmd_bad(pmd_t pmd)
@@ -887,7 +904,7 @@ static inline int pud_none(pud_t pud)
 
 static inline int pud_present(pud_t pud)
 {
-	return !pud_none(pud);
+	return (pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT));
 }
 
 extern struct page *pud_page(pud_t pud);
@@ -934,7 +951,7 @@ static inline int pgd_none(pgd_t pgd)
 
 static inline int pgd_present(pgd_t pgd)
 {
-	return !pgd_none(pgd);
+	return (pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT));
 }
 
 static inline pte_t pgd_pte(pgd_t pgd)
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 5a72e980e25a..7ce7fa5397d5 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1002,9 +1002,9 @@ void __init hash__early_init_mmu(void)
 	 * 4k use hugepd format, so for hash set then to
 	 * zero
 	 */
-	__pmd_val_bits = 0;
-	__pud_val_bits = 0;
-	__pgd_val_bits = 0;
+	__pmd_val_bits = HASH_PMD_VAL_BITS;
+	__pud_val_bits = HASH_PUD_VAL_BITS;
+	__pgd_val_bits = HASH_PGD_VAL_BITS;
 
 	__kernel_virt_start = H_KERN_VIRT_START;
 	__kernel_virt_size = H_KERN_VIRT_SIZE;
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 5d2328ef7958..c1f825ff251b 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -106,7 +106,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 {
 	unsigned long old_pmd;
 
-	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, _PAGE_INVALID);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
-- 
2.17.1

[RFC PATCH 2/4] powerpc/mm/hugetlb/book3s: add _PAGE_PRESENT to hugepd pointer.

[Aneesh Kumar K.V]

This make hugetlb directory pointer similar to other page able entries. A hugepd
entry is identified by lack of _PAGE_PTE bit set and directory size stored in
HUGEPD_SHIFT_MASK. We update that to also look at _PAGE_PRESENT

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/hash-4k.h | 2 +-
 arch/powerpc/include/asm/book3s/64/hugetlb.h | 3 +++
 arch/powerpc/mm/hugetlbpage.c                | 2 +-
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 9a3798660cef..15bc16b1dc9c 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -66,7 +66,7 @@ static inline int hash__hugepd_ok(hugepd_t hpd)
 	 * if it is not a pte and have hugepd shift mask
 	 * set, then it is a hugepd directory pointer
 	 */
-	if (!(hpdval & _PAGE_PTE) &&
+	if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) &&
 	    ((hpdval & HUGEPD_SHIFT_MASK) != 0))
 		return true;
 	return false;
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index 50888388a359..5b0177733994 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -39,4 +39,7 @@ static inline bool gigantic_page_supported(void)
 }
 #endif
 
+/* hugepd entry valid bit */
+#define HUGEPD_VAL_BITS		(0x8000000000000000UL)
+
 #endif
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index f425b5b37d58..7ae5e4bfd318 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -95,7 +95,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 			break;
 		else {
 #ifdef CONFIG_PPC_BOOK3S_64
-			*hpdp = __hugepd(__pa(new) |
+			*hpdp = __hugepd(__pa(new) | HUGEPD_VAL_BITS |
 					 (shift_to_mmu_psize(pshift) << 2));
 #elif defined(CONFIG_PPC_8xx)
 			*hpdp = __hugepd(__pa(new) | _PMD_USER |
-- 
2.17.1

[RFC PATCH 3/4] powerpc/mm/book3s: Check for pmd_large instead of pmd_trans_huge in set_pmd_at

[Aneesh Kumar K.V]

We want to use this to store swap pte at pmd level. For swap ptes we don't want
to set H_PAGE_THP_HUGE. Hence check for pmd_large in set_pmd_at. This remove
the false WARN_ON when using this with swap pmd entry.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/mm/pgtable-book3s64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index c1f825ff251b..9a4d4908e242 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -71,7 +71,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 #ifdef CONFIG_DEBUG_VM
 	WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
 	assert_spin_locked(pmd_lockptr(mm, pmdp));
-	WARN_ON(!(pmd_trans_huge(pmd) || pmd_devmap(pmd)));
+	WARN_ON(!(pmd_large(pmd) || pmd_devmap(pmd)));
 #endif
 	trace_hugepage_set_pmd(addr, pmd_val(pmd));
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
-- 
2.17.1

[RFC PATCH 4/4] powerpc/mm:book3s: Enable THP migration support

[Aneesh Kumar K.V]

---
 arch/powerpc/include/asm/book3s/64/pgtable.h | 5 +++++
 arch/powerpc/platforms/Kconfig.cputype       | 1 +
 2 files changed, 6 insertions(+)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index fce9ce8781a0..f619f3215c05 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -734,6 +734,8 @@ static inline bool pte_user(pte_t pte)
  */
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE })
 #define __swp_entry_to_pte(x)	__pte((x).val | _PAGE_PTE)
+#define __pmd_to_swp_entry(pmd)	(__pte_to_swp_entry(pmd_pte(pmd)))
+#define __swp_entry_to_pmd(x)	(pte_pmd(__swp_entry_to_pte(x)))
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _PAGE_SWP_SOFT_DIRTY   (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE))
@@ -1079,6 +1081,9 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 #define pmd_mk_savedwrite(pmd)	pte_pmd(pte_mk_savedwrite(pmd_pte(pmd)))
 #define pmd_clear_savedwrite(pmd)	pte_pmd(pte_clear_savedwrite(pmd_pte(pmd)))
+#define pmd_swp_mksoft_dirty(pmd)	pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd)))
+#define pmd_swp_soft_dirty(pmd)		pte_swp_soft_dirty(pmd_pte(pmd))
+#define pmd_swp_clear_soft_dirty(pmd)	pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd)))
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 #define pmd_soft_dirty(pmd)    pte_soft_dirty(pmd_pte(pmd))
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index e6a1de521319..2e8ee6a33587 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -72,6 +72,7 @@ config PPC_BOOK3S_64
 	select PPC_HAVE_PMU_SUPPORT
 	select SYS_SUPPORTS_HUGETLBFS
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select ARCH_ENABLE_THP_MIGRATION
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select IRQ_WORK
 	select HAVE_KERNEL_XZ
-- 
2.17.1