Skip to contentSkip to conversation

thp: transparent hugepages on s390

PATCH New Gerald Schaefer 1 participant 10 messages Sep 6, 2012 – Sep 13, 2012

Subsystems (8)
Memory management x86 MM core s390 +4 more subsystems
lore
Share & tools
lore
#0 lore raw

cover thp: transparent hugepages on s390

This patch series adds support for transparent hugepages on s390. Small changes to common code are necessary with regard to a different pgtable_t, tlb flushing and kvm behaviour on s390, see patches 2 to 4. Also, (x86) Kconfig is touched by patch 1.

Changes since RFC v2:
[PATCH 1/8] introduce HAVE_ARCH_TRANSPARENT_HUGEPAGE in Kconfig [PATCH 2/8] rename pgtable_deposit/withdraw
[PATCH 6/8] rename pgtable_deposit/withdraw
[PATCH 8/8] rename pgtable_deposit/withdraw

Gerald Schaefer (8):
thp, x86: introduce HAVE_ARCH_TRANSPARENT_HUGEPAGE in Kconfig
thp: remove assumptions on pgtable_t type
thp: introduce pmdp_invalidate()
thp: make MADV_HUGEPAGE check for mm->def_flags thp, s390: thp splitting backend for s390
thp, s390: thp pagetable pre-allocation for s390 thp, s390: disable thp for kvm host on s390
thp, s390: architecture backend for thp on s390

 arch/Kconfig                    |   3 +
 arch/s390/Kconfig               |   1 +
 arch/s390/include/asm/hugetlb.h |  18 +---
 arch/s390/include/asm/pgtable.h | 208 ++++++++++++++++++++++++++++++++++++++++
 arch/s390/include/asm/setup.h   |   3 +
 arch/s390/include/asm/tlb.h     |   1 +
 arch/s390/kernel/early.c        |   2 +
 arch/s390/mm/gup.c              |  11 ++-
 arch/s390/mm/pgtable.c          | 108 +++++++++++++++++++++
 arch/x86/Kconfig                |   1 +
 include/asm-generic/pgtable.h   |  13 +++
 include/linux/huge_mm.h         |   1 -
 mm/Kconfig                      |   2 +-
 mm/huge_memory.c                |  53 +++-------
 mm/pgtable-generic.c            |  50 ++++++++++
 15 files changed, 413 insertions(+), 62 deletions(-)
Signature · 1 line
1.7.11.5
#1 lore raw

PATCH 1/8 thp, x86: introduce HAVE_ARCH_TRANSPARENT_HUGEPAGE

Cleanup patch in preparation for transparent hugepage support on s390. Adding new architectures to the TRANSPARENT_HUGEPAGE config option can make the "depends" line rather ugly, like "depends on
(X86 || (S390 && 64BIT)) && MMU".
This patch adds a HAVE_ARCH_TRANSPARENT_HUGEPAGE instead. x86 already has MMU "def_bool y", so the MMU check is superfluous there and HAVE_ARCH_TRANSPARENT_HUGEPAGE can be selected in arch/x86/Kconfig.

Cc Ingo Molnar <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
---
 arch/Kconfig     | 3 +++
 arch/x86/Kconfig | 1 +
 mm/Kconfig       | 2 +-
 3 files changed, 5 insertions(+), 1 deletion(-)
arch/Kconfig +3 -0
index 72f2fa1..04de2d2 100644
@@ -281,4 +281,7 @@ config SECCOMP_FILTER
 
 	  See Documentation/prctl/seccomp_filter.txt for details.
 
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	bool
+
 source "kernel/gcov/Kconfig"
arch/x86/Kconfig +1 -0
index 8ec3a1a..0b9bb7b 100644
@@ -97,6 +97,7 @@ config X86
 	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS || UPROBES)
mm/Kconfig +1 -1
index d5c8019..3322342 100644
@@ -318,7 +318,7 @@ config NOMMU_INITIAL_TRIM_EXCESS
 
 config TRANSPARENT_HUGEPAGE
 	bool "Transparent Hugepage Support"
-	depends on X86 && MMU
+	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select COMPACTION
 	help
 	  Transparent Hugepages allows the kernel to use huge pages and
Signature · 1 line
1.7.11.5
#2 lore raw

PATCH 2/8 thp: remove assumptions on pgtable_t type

In reply to Gerald Schaefer

The thp page table pre-allocation code currently assumes that pgtable_t is of type "struct page *". This may not be true for all architectures, so this patch removes that assumption by replacing the functions prepare_pmd_huge_pte() and get_pmd_huge_pte() with two new functions that can be defined architecture-specific.

It also removes two VM_BUG_ON checks for page_count() and page_mapcount() operating on a pgtable_t. Apart from the VM_BUG_ON removal, there will be no functional change introduced by this patch.

---
 include/asm-generic/pgtable.h |  8 ++++++++
 include/linux/huge_mm.h       |  1 -
 mm/huge_memory.c              | 46 ++++++-------------------------------------
 mm/pgtable-generic.c          | 39 ++++++++++++++++++++++++++++++++++++
 4 files changed, 53 insertions(+), 41 deletions(-)
include/asm-generic/pgtable.h +8 -0
index ff4947b..548a12e 100644
@@ -162,6 +162,14 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp);
 #endif
 
+#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+#endif
+
+#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
include/linux/huge_mm.h +0 -1
index 4c59b11..6ab47af 100644
@@ -11,7 +11,6 @@ extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			       unsigned long address, pmd_t *pmd,
 			       pmd_t orig_pmd);
-extern pgtable_t get_pmd_huge_pte(struct mm_struct *mm);
 extern struct page *follow_trans_huge_pmd(struct mm_struct *mm,
 					  unsigned long addr,
 					  pmd_t *pmd,
mm/huge_memory.c +6 -40

100 lines not on this page · raw message

mm/pgtable-generic.c +39 -0
index 74c0dda..29867e0 100644
@@ -120,3 +120,42 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
+
+#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+{
+	assert_spin_locked(&mm->page_table_lock);
+
+	/* FIFO */
+	if (!mm->pmd_huge_pte)
+		INIT_LIST_HEAD(&pgtable->lru);
+	else
+		list_add(&pgtable->lru, &mm->pmd_huge_pte->lru);
+	mm->pmd_huge_pte = pgtable;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/* no "address" argument so destroys page coloring of some arch */
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+{
+	pgtable_t pgtable;
+
+	assert_spin_locked(&mm->page_table_lock);
+
+	/* FIFO */
+	pgtable = mm->pmd_huge_pte;
+	if (list_empty(&pgtable->lru))
+		mm->pmd_huge_pte = NULL;
+	else {
+		mm->pmd_huge_pte = list_entry(pgtable->lru.next,
+					      struct page, lru);
+		list_del(&pgtable->lru);
+	}
+	return pgtable;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
Signature · 1 line
1.7.11.5
#3 lore raw

PATCH 3/8 thp: introduce pmdp_invalidate()

In reply to Gerald Schaefer

On s390, a valid page table entry must not be changed while it is attached to any CPU. So instead of pmd_mknotpresent() and set_pmd_at(), an IDTE operation would be necessary there. This patch introduces the pmdp_invalidate() function, to allow architecture-specific implementations.

---
 include/asm-generic/pgtable.h |  5 +++++
 mm/huge_memory.c              |  3 +--
 mm/pgtable-generic.c          | 11 +++++++++++
 3 files changed, 17 insertions(+), 2 deletions(-)
include/asm-generic/pgtable.h +5 -0
index 548a12e..e4821cf 100644
@@ -170,6 +170,11 @@ extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
 extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
mm/huge_memory.c +1 -2
index 5fce078..5617ee0 100644
@@ -1374,8 +1374,7 @@ static int __split_huge_page_map(struct page *page,
 		 * SMP TLB and finally we write the non-huge version
 		 * of the pmd entry with pmd_populate.
 		 */
-		set_pmd_at(mm, address, pmd, pmd_mknotpresent(*pmd));
-		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+		pmdp_invalidate(vma, address, pmd);
 		pmd_populate(mm, pmd, pgtable);
 		ret = 1;
 	}
mm/pgtable-generic.c +11 -0
index 29867e0..e642627 100644
@@ -159,3 +159,14 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
+
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pmd_t *pmdp)
+{
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
Signature · 1 line
1.7.11.5
#4 lore raw

PATCH 4/8 thp: make MADV_HUGEPAGE check for mm->def_flags

In reply to Gerald Schaefer

This adds a check to hugepage_madvise(), to refuse MADV_HUGEPAGE if VM_NOHUGEPAGE is set in mm->def_flags. On s390, the VM_NOHUGEPAGE flag will be set in mm->def_flags for kvm processes, to prevent any future thp mappings. In order to also prevent MADV_HUGEPAGE on such an mm, hugepage_madvise() should check mm->def_flags.

---
 mm/huge_memory.c | 4 ++++
 1 file changed, 4 insertions(+)
mm/huge_memory.c +4 -0
index 5617ee0..5fa0cd3 100644
@@ -1464,6 +1464,8 @@ out:
 int hugepage_madvise(struct vm_area_struct *vma,
 		     unsigned long *vm_flags, int advice)
 {
+	struct mm_struct *mm = vma->vm_mm;
+
 	switch (advice) {
 	case MADV_HUGEPAGE:
 		/*
@@ -1471,6 +1473,8 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 */
 		if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP))
 			return -EINVAL;
+		if (mm->def_flags & VM_NOHUGEPAGE)
+			return -EINVAL;
 		*vm_flags &= ~VM_NOHUGEPAGE;
 		*vm_flags |= VM_HUGEPAGE;
 		/*
Signature · 1 line
1.7.11.5
#5 lore raw

PATCH 5/8 thp, s390: thp splitting backend for s390

In reply to Gerald Schaefer

This patch is part of the architecture backend for thp on s390. It provides the functions related to thp splitting, including serialization against gup. Unlike other archs, pmdp_splitting_flush() cannot use a tlb flushing operation to serialize against gup on s390, because that wouldn't be stopped by the disabled IRQs. So instead, smp_call_function() is called with an empty function, which will have the expected effect.

---
 arch/s390/include/asm/pgtable.h | 13 +++++++++++++
 arch/s390/mm/gup.c              | 11 ++++++++++-
 arch/s390/mm/pgtable.c          | 18 ++++++++++++++++++
 3 files changed, 41 insertions(+), 1 deletion(-)
arch/s390/include/asm/pgtable.h +13 -0
index 6bd7d74..c3f0775 100644
@@ -347,6 +347,8 @@ extern struct page *vmemmap;
 
 #define _SEGMENT_ENTRY_LARGE	0x400	/* STE-format control, large page   */
 #define _SEGMENT_ENTRY_CO	0x100	/* change-recording override   */
+#define _SEGMENT_ENTRY_SPLIT_BIT 0	/* THP splitting bit number */
+#define _SEGMENT_ENTRY_SPLIT	(1UL << _SEGMENT_ENTRY_SPLIT_BIT)
 
 /* Page status table bits for virtualization */
 #define RCP_ACC_BITS	0xf000000000000000UL
@@ -506,6 +508,10 @@ static inline int pmd_bad(pmd_t pmd)
 	return (pmd_val(pmd) & mask) != _SEGMENT_ENTRY;
 }
 
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+				 unsigned long addr, pmd_t *pmdp);
+
 static inline int pte_none(pte_t pte)
 {
 	return (pte_val(pte) & _PAGE_INVALID) && !(pte_val(pte) & _PAGE_SWT);
@@ -1159,6 +1165,13 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
 #define pte_unmap(pte) do { } while (0)
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_splitting(pmd_t pmd)
+{
+	return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 /*
  * 31 bit swap entry format:
  * A page-table entry has some bits we have to treat in a special way.
arch/s390/mm/gup.c +10 -1
index 65cb06e..d34fd6e 100644
@@ -115,7 +115,16 @@ static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
 		pmd = *pmdp;
 		barrier();
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		/*
+		 * The pmd_trans_splitting() check below explains why
+		 * pmdp_splitting_flush() has to serialize with
+		 * smp_call_function() against our disabled IRQs, to stop
+		 * this gup-fast code from running while we set the
+		 * splitting bit in the pmd. Returning zero will take
+		 * the slow path that will call wait_split_huge_page()
+		 * if the pmd is still in splitting state.
+		 */
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_huge(pmd))) {
 			if (!gup_huge_pmd(pmdp, pmd, addr, next,
arch/s390/mm/pgtable.c +18 -0
index 18df31d..5a73522 100644
@@ -866,3 +866,21 @@ bool kernel_page_present(struct page *page)
 	return cc == 0;
 }
 #endif /* CONFIG_HIBERNATION && CONFIG_DEBUG_PAGEALLOC */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void pmdp_splitting_flush_sync(void *arg)
+{
+	/* Simply deliver the interrupt */
+}
+
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp)
+{
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	if (!test_and_set_bit(_SEGMENT_ENTRY_SPLIT_BIT,
+			      (unsigned long *) pmdp)) {
+		/* need to serialize against gup-fast (IRQ disabled) */
+		smp_call_function(pmdp_splitting_flush_sync, NULL, 1);
+	}
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
Signature · 1 line
1.7.11.5
#6 lore raw

PATCH 6/8 thp, s390: thp pagetable pre-allocation for s390

In reply to Gerald Schaefer

This patch is part of the architecture backend for thp on s390. It provides the pagetable pre-allocation functions pgtable_trans_huge_deposit() and pgtable_trans_huge_withdraw(). Unlike other archs, s390 has no struct page * as pgtable_t, but rather a pointer to the page table. So instead of saving the pagetable pre- allocation list info inside the struct page, it is being saved within the pagetable itself.

---
 arch/s390/include/asm/pgtable.h |  6 ++++++
 arch/s390/mm/pgtable.c          | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)
arch/s390/include/asm/pgtable.h +6 -0
index c3f0775..2c8f00d 100644
@@ -1166,6 +1166,12 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 #define pte_unmap(pte) do { } while (0)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+
 static inline int pmd_trans_splitting(pmd_t pmd)
 {
 	return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT;
arch/s390/mm/pgtable.c +38 -0
index 5a73522..091e06d 100644
@@ -883,4 +883,42 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 		smp_call_function(pmdp_splitting_flush_sync, NULL, 1);
 	}
 }
+
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable)
+{
+	struct list_head *lh = (struct list_head *) pgtable;
+
+	assert_spin_locked(&mm->page_table_lock);
+
+	/* FIFO */
+	if (!mm->pmd_huge_pte)
+		INIT_LIST_HEAD(lh);
+	else
+		list_add(lh, (struct list_head *) mm->pmd_huge_pte);
+	mm->pmd_huge_pte = pgtable;
+}
+
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm)
+{
+	struct list_head *lh;
+	pgtable_t pgtable;
+	pte_t *ptep;
+
+	assert_spin_locked(&mm->page_table_lock);
+
+	/* FIFO */
+	pgtable = mm->pmd_huge_pte;
+	lh = (struct list_head *) pgtable;
+	if (list_empty(lh))
+		mm->pmd_huge_pte = NULL;
+	else {
+		mm->pmd_huge_pte = (pgtable_t) lh->next;
+		list_del(lh);
+	}
+	ptep = (pte_t *) pgtable;
+	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+	ptep++;
+	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
+	return pgtable;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
Signature · 1 line
1.7.11.5
#7 lore raw

PATCH 7/8 thp, s390: disable thp for kvm host on s390

In reply to Gerald Schaefer

This patch is part of the architecture backend for thp on s390. It disables thp for kvm hosts, because there is no kvm host hugepage support so far. Existing thp mappings are split by follow_page() with FOLL_SPLIT, and future thp mappings are prevented by setting VM_NOHUGEPAGE in mm->def_flags.

---
 arch/s390/mm/pgtable.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
arch/s390/mm/pgtable.c +30 -0
index 091e06d..2b848ef 100644
@@ -787,6 +787,30 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 		tlb_table_flush(tlb);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void thp_split_vma(struct vm_area_struct *vma)
+{
+	unsigned long addr;
+	struct page *page;
+
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
+		page = follow_page(vma, addr, FOLL_SPLIT);
+	}
+}
+
+void thp_split_mm(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma = mm->mmap;
+
+	while (vma != NULL) {
+		thp_split_vma(vma);
+		vma->vm_flags &= ~VM_HUGEPAGE;
+		vma->vm_flags |= VM_NOHUGEPAGE;
+		vma = vma->vm_next;
+	}
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 /*
  * switch on pgstes for its userspace process (for kvm)
  */
@@ -824,6 +848,12 @@ int s390_enable_sie(void)
 	if (!mm)
 		return -ENOMEM;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	/* split thp mappings and disable thp for future mappings */
+	thp_split_mm(mm);
+	mm->def_flags |= VM_NOHUGEPAGE;
+#endif
+
 	/* Now lets check again if something happened */
 	task_lock(tsk);
 	if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
Signature · 1 line
1.7.11.5
#8 lore raw

PATCH 8/8 thp, s390: architecture backend for thp on s390

In reply to Gerald Schaefer

This implements the architecture backend for transparent hugepages on s390.

---
 arch/s390/Kconfig               |   1 +
 arch/s390/include/asm/hugetlb.h |  18 +---
 arch/s390/include/asm/pgtable.h | 189 ++++++++++++++++++++++++++++++++++++++++
 arch/s390/include/asm/setup.h   |   3 +
 arch/s390/include/asm/tlb.h     |   1 +
 arch/s390/kernel/early.c        |   2 +
 arch/s390/mm/pgtable.c          |  22 +++++
 7 files changed, 219 insertions(+), 17 deletions(-)
arch/s390/Kconfig +1 -0
index 107610e..d0f68ee 100644
@@ -125,6 +125,7 @@ config S390
 	select GENERIC_CLOCKEVENTS
 	select KTIME_SCALAR if 32BIT
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT
 
 config SCHED_OMIT_FRAME_POINTER
 	def_bool y
arch/s390/include/asm/hugetlb.h +1 -17
index 799ed0f..a840662 100644
@@ -87,23 +87,6 @@ static inline void __pmd_csp(pmd_t *pmdp)
 		"	csp %1,%3"
 		: "=m" (*pmdp)
 		: "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
-	pmd_val(*pmdp) = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY;
-}
-
-static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
-{
-	unsigned long sto = (unsigned long) pmdp -
-				pmd_index(address) * sizeof(pmd_t);
-
-	if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INV)) {
-		asm volatile(
-			"	.insn	rrf,0xb98e0000,%2,%3,0,0"
-			: "=m" (*pmdp)
-			: "m" (*pmdp), "a" (sto),
-			  "a" ((address & HPAGE_MASK))
-		);
-	}
-	pmd_val(*pmdp) = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY;
 }
 
 static inline void huge_ptep_invalidate(struct mm_struct *mm,
@@ -115,6 +98,7 @@ static inline void huge_ptep_invalidate(struct mm_struct *mm,
 		__pmd_idte(address, pmdp);
 	else
 		__pmd_csp(pmdp);
+	pmd_val(*pmdp) = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY;
 }
 
 #define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \
arch/s390/include/asm/pgtable.h +189 -0

213 lines not on this page · raw message

arch/s390/include/asm/setup.h +3 -0
index e6859d1..13b545f 100644
@@ -80,6 +80,7 @@ extern unsigned int addressing_mode;
 #define MACHINE_FLAG_LPAR	(1UL << 12)
 #define MACHINE_FLAG_SPP	(1UL << 13)
 #define MACHINE_FLAG_TOPOLOGY	(1UL << 14)
+#define MACHINE_FLAG_RRBM	(1UL << 16)
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -98,6 +99,7 @@ extern unsigned int addressing_mode;
 #define MACHINE_HAS_PFMF	(0)
 #define MACHINE_HAS_SPP		(0)
 #define MACHINE_HAS_TOPOLOGY	(0)
+#define MACHINE_HAS_RRBM	(0)
 #else /* CONFIG_64BIT */
 #define MACHINE_HAS_IEEE	(1)
 #define MACHINE_HAS_CSP		(1)
@@ -109,6 +111,7 @@ extern unsigned int addressing_mode;
 #define MACHINE_HAS_PFMF	(S390_lowcore.machine_flags & MACHINE_FLAG_PFMF)
 #define MACHINE_HAS_SPP		(S390_lowcore.machine_flags & MACHINE_FLAG_SPP)
 #define MACHINE_HAS_TOPOLOGY	(S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
+#define MACHINE_HAS_RRBM	(S390_lowcore.machine_flags & MACHINE_FLAG_RRBM)
 #endif /* CONFIG_64BIT */
 
 #define ZFCPDUMP_HSA_SIZE	(32UL<<20)
arch/s390/include/asm/tlb.h +1 -0
index 06e5acb..b75d7d6 100644
@@ -137,6 +137,7 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 #define tlb_start_vma(tlb, vma)			do { } while (0)
 #define tlb_end_vma(tlb, vma)			do { } while (0)
 #define tlb_remove_tlb_entry(tlb, ptep, addr)	do { } while (0)
+#define tlb_remove_pmd_tlb_entry(tlb, pmdp, addr)	do { } while (0)
 #define tlb_migrate_finish(mm)			do { } while (0)
 
 #endif /* _S390_TLB_H */
arch/s390/kernel/early.c +2 -0
index 83c3271..fb03cce 100644
@@ -372,6 +372,8 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS;
 	if (test_facility(40))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_SPP;
+	if (test_facility(66))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_RRBM;
 #endif
 }
 
arch/s390/mm/pgtable.c +22 -0
index 2b848ef..b26daf5 100644
@@ -898,6 +898,28 @@ bool kernel_page_present(struct page *page)
 #endif /* CONFIG_HIBERNATION && CONFIG_DEBUG_PAGEALLOC */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address,
+			   pmd_t *pmdp)
+{
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	/* No need to flush TLB
+	 * On s390 reference bits are in storage key and never in TLB */
+	return pmdp_test_and_clear_young(vma, address, pmdp);
+}
+
+int pmdp_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp,
+			  pmd_t entry, int dirty)
+{
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+	if (pmd_same(*pmdp, entry))
+		return 0;
+	pmdp_invalidate(vma, address, pmdp);
+	set_pmd_at(vma->vm_mm, address, pmdp, entry);
+	return 1;
+}
+
 static void pmdp_splitting_flush_sync(void *arg)
 {
 	/* Simply deliver the interrupt */
Signature · 1 line
1.7.11.5
#9 lore raw

PATCH 1/1 thp, s390: add missing earlyclobber to inline assembly

The constraints of the rrbm inline assembly are missing two earlyclobber operands, which can lead to an addressing exception depending on compiler register allocation decisions.

---

Hello Andrew, please merge this with patch thp-s390-architecture-backend-for-thp-on-s390.patch

 arch/s390/include/asm/pgtable.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
arch/s390/include/asm/pgtable.h +2 -1
index 1393a3c..ce67458 100644
@@ -1296,7 +1296,8 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 			"	ogr	%1,%0\n"
 			"	la	%3,0(%4,%3)\n"
 			"	brct	%2,0b\n"
-			: "=d" (tmp), "+d" (rc), "+d" (counter), "+a" (pmd_addr)
+			: "=&d" (tmp), "+&d" (rc), "+d" (counter),
+			  "+a" (pmd_addr)
 			: "a" (64 * 4096UL) : "cc");
 		rc = !!rc;
 	} else {
Signature · 1 line
1.7.11.6