[S390] System z large page support.

This adds hugetlbfs support on System z, using both hardware large page
support if available and software large page emulation on older hardware.
Shared (large) page tables are implemented in software emulation mode,
by using page->index of the first tail page from a compound large page
to store page table information.

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

5 files changed, 225 insertions, 6 deletions

diff --git a/include/asm-s390/hugetlb.h b/include/asm-s390/hugetlb.h
new file mode 100644
index 000000000000..600a776f8f75
--- /dev/null
+++ b/include/asm-s390/hugetlb.h
@@ -0,0 +1,183 @@
+/*
+ *  IBM System z Huge TLB Page Support for Kernel.
+ *
+ *    Copyright IBM Corp. 2008
+ *    Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
+ */
+
+#ifndef _ASM_S390_HUGETLB_H
+#define _ASM_S390_HUGETLB_H
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+
+#define is_hugepage_only_range(mm, addr, len)   0
+#define hugetlb_free_pgd_range                  free_pgd_range
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+                     pte_t *ptep, pte_t pte);
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(unsigned long addr, unsigned long len)
+{
+        if (len & ~HPAGE_MASK)
+                return -EINVAL;
+        if (addr & ~HPAGE_MASK)
+                return -EINVAL;
+        return 0;
+}
+
+#define hugetlb_prefault_arch_hook(mm)          do { } while (0)
+
+int arch_prepare_hugepage(struct page *page);
+void arch_release_hugepage(struct page *page);
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+        /*
+         * PROT_NONE needs to be remapped from the pte type to the ste type.
+         * The HW invalid bit is also different for pte and ste. The pte
+         * invalid bit happens to be the same as the ste _SEGMENT_ENTRY_LARGE
+         * bit, so we don't have to clear it.
+         */
+        if (pte_val(pte) & _PAGE_INVALID) {
+                if (pte_val(pte) & _PAGE_SWT)
+                        pte_val(pte) |= _HPAGE_TYPE_NONE;
+                pte_val(pte) |= _SEGMENT_ENTRY_INV;
+        }
+        /*
+         * Clear SW pte bits SWT and SWX, there are no SW bits in a segment
+         * table entry.
+         */
+        pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX);
+        /*
+         * Also set the change-override bit because we don't need dirty bit
+         * tracking for hugetlbfs pages.
+         */
+        pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO);
+        return pte;
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+        pte_val(pte) |= _PAGE_RO;
+        return pte;
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+        return (pte_val(pte) & _SEGMENT_ENTRY_INV) &&
+                !(pte_val(pte) & _SEGMENT_ENTRY_RO);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+        pte_t pte = *ptep;
+        unsigned long mask;
+
+        if (!MACHINE_HAS_HPAGE) {
+                ptep = (pte_t *) (pte_val(pte) & _SEGMENT_ENTRY_ORIGIN);
+                if (ptep) {
+                        mask = pte_val(pte) &
+                                (_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO);
+                        pte = pte_mkhuge(*ptep);
+                        pte_val(pte) |= mask;
+                }
+        }
+        return pte;
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+                                            unsigned long addr, pte_t *ptep)
+{
+        pte_t pte = huge_ptep_get(ptep);
+
+        pmd_clear((pmd_t *) ptep);
+        return pte;
+}
+
+static inline void __pmd_csp(pmd_t *pmdp)
+{
+        register unsigned long reg2 asm("2") = pmd_val(*pmdp);
+        register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
+                                               _SEGMENT_ENTRY_INV;
+        register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
+
+        asm volatile(
+                "       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,
+                                        unsigned long address, pte_t *ptep)
+{
+        pmd_t *pmdp = (pmd_t *) ptep;
+
+        if (!MACHINE_HAS_IDTE) {
+                __pmd_csp(pmdp);
+                if (mm->context.noexec) {
+                        pmdp = get_shadow_table(pmdp);
+                        __pmd_csp(pmdp);
+                }
+                return;
+        }
+
+        __pmd_idte(address, pmdp);
+        if (mm->context.noexec) {
+                pmdp = get_shadow_table(pmdp);
+                __pmd_idte(address, pmdp);
+        }
+        return;
+}
+
+#define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \
+({                                                                          \
+        int __changed = !pte_same(huge_ptep_get(__ptep), __entry);          \
+        if (__changed) {                                                    \
+                huge_ptep_invalidate((__vma)->vm_mm, __addr, __ptep);       \
+                set_huge_pte_at((__vma)->vm_mm, __addr, __ptep, __entry);   \
+        }                                                                   \
+        __changed;                                                          \
+})
+
+#define huge_ptep_set_wrprotect(__mm, __addr, __ptep)                   \
+({                                                                      \
+        pte_t __pte = huge_ptep_get(__ptep);                            \
+        if (pte_write(__pte)) {                                         \
+                if (atomic_read(&(__mm)->mm_users) > 1 ||               \
+                    (__mm) != current->active_mm)                       \
+                        huge_ptep_invalidate(__mm, __addr, __ptep);     \
+                set_huge_pte_at(__mm, __addr, __ptep,                   \
+                                huge_pte_wrprotect(__pte));             \
+        }                                                               \
+})
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+                                         unsigned long address, pte_t *ptep)
+{
+        huge_ptep_invalidate(vma->vm_mm, address, ptep);
+}
+
+#endif /* _ASM_S390_HUGETLB_H */
diff --git a/include/asm-s390/page.h b/include/asm-s390/page.h
index fe7f92b6ae6d..b01e6fc9a295 100644
--- a/include/asm-s390/page.h
+++ b/include/asm-s390/page.h
@@ -19,17 +19,34 @@
 #define PAGE_DEFAULT_ACC        0
 #define PAGE_DEFAULT_KEY        (PAGE_DEFAULT_ACC << 4)
 
+#define HPAGE_SHIFT     20
+#define HPAGE_SIZE      (1UL << HPAGE_SHIFT)
+#define HPAGE_MASK      (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
+
+#define ARCH_HAS_SETCLEAR_HUGE_PTE
+#define ARCH_HAS_HUGE_PTE_TYPE
+#define ARCH_HAS_PREPARE_HUGEPAGE
+#define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH
+
 #include <asm/setup.h>
 #ifndef __ASSEMBLY__
 
 static inline void clear_page(void *page)
 {
-        register unsigned long reg1 asm ("1") = 0;
-        register void *reg2 asm ("2") = page;
-        register unsigned long reg3 asm ("3") = 4096;
-        asm volatile(
-                "       mvcl    2,0"
-                : "+d" (reg2), "+d" (reg3) : "d" (reg1) : "memory", "cc");
+        if (MACHINE_HAS_PFMF) {
+                asm volatile(
+                        "       .insn   rre,0xb9af0000,%0,%1"
+                        : : "d" (0x10000), "a" (page) : "memory", "cc");
+        } else {
+                register unsigned long reg1 asm ("1") = 0;
+                register void *reg2 asm ("2") = page;
+                register unsigned long reg3 asm ("3") = 4096;
+                asm volatile(
+                        "       mvcl    2,0"
+                        : "+d" (reg2), "+d" (reg3) : "d" (reg1)
+                        : "memory", "cc");
+        }
 }
 
 static inline void copy_page(void *to, void *from)
diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h
index f8347ce9c5a1..fd336f2e2a7a 100644
--- a/include/asm-s390/pgtable.h
+++ b/include/asm-s390/pgtable.h
@@ -234,6 +234,15 @@ extern char empty_zero_page[PAGE_SIZE];
 #define _PAGE_TYPE_EX_RW        0x002
 
 /*
+ * Only four types for huge pages, using the invalid bit and protection bit
+ * of a segment table entry.
+ */
+#define _HPAGE_TYPE_EMPTY       0x020   /* _SEGMENT_ENTRY_INV */
+#define _HPAGE_TYPE_NONE        0x220
+#define _HPAGE_TYPE_RO          0x200   /* _SEGMENT_ENTRY_RO  */
+#define _HPAGE_TYPE_RW          0x000
+
+/*
  * PTE type bits are rather complicated. handle_pte_fault uses pte_present,
  * pte_none and pte_file to find out the pte type WITHOUT holding the page
  * table lock. ptep_clear_flush on the other hand uses ptep_clear_flush to
@@ -325,6 +334,9 @@ extern char empty_zero_page[PAGE_SIZE];
 #define _SEGMENT_ENTRY          (0)
 #define _SEGMENT_ENTRY_EMPTY    (_SEGMENT_ENTRY_INV)
 
+#define _SEGMENT_ENTRY_LARGE    0x400   /* STE-format control, large page   */
+#define _SEGMENT_ENTRY_CO       0x100   /* change-recording override   */
+
 #endif /* __s390x__ */
 
 /*
diff --git a/include/asm-s390/setup.h b/include/asm-s390/setup.h
index 3a9e458fd8c3..ba69674012a7 100644
--- a/include/asm-s390/setup.h
+++ b/include/asm-s390/setup.h
@@ -69,6 +69,8 @@ extern unsigned long machine_flags;
 #define MACHINE_FLAG_DIAG9C     (1UL << 7)
 #define MACHINE_FLAG_MVCOS      (1UL << 8)
 #define MACHINE_FLAG_KVM        (1UL << 9)
+#define MACHINE_FLAG_HPAGE      (1UL << 10)
+#define MACHINE_FLAG_PFMF       (1UL << 11)
 
 #define MACHINE_IS_VM           (machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM          (machine_flags & MACHINE_FLAG_KVM)
@@ -82,6 +84,8 @@ extern unsigned long machine_flags;
 #define MACHINE_HAS_DIAG44      (1)
 #define MACHINE_HAS_MVPG        (machine_flags & MACHINE_FLAG_MVPG)
 #define MACHINE_HAS_MVCOS       (0)
+#define MACHINE_HAS_HPAGE       (0)
+#define MACHINE_HAS_PFMF        (0)
 #else /* __s390x__ */
 #define MACHINE_HAS_IEEE        (1)
 #define MACHINE_HAS_CSP         (1)
@@ -89,6 +93,8 @@ extern unsigned long machine_flags;
 #define MACHINE_HAS_DIAG44      (machine_flags & MACHINE_FLAG_DIAG44)
 #define MACHINE_HAS_MVPG        (1)
 #define MACHINE_HAS_MVCOS       (machine_flags & MACHINE_FLAG_MVCOS)
+#define MACHINE_HAS_HPAGE       (machine_flags & MACHINE_FLAG_HPAGE)
+#define MACHINE_HAS_PFMF        (machine_flags & MACHINE_FLAG_PFMF)
 #endif /* __s390x__ */
 
 #define MACHINE_HAS_SCLP        (!MACHINE_IS_P390)
diff --git a/include/asm-s390/tlbflush.h b/include/asm-s390/tlbflush.h
index 9e57a93d7de1..d60394b9745e 100644
--- a/include/asm-s390/tlbflush.h
+++ b/include/asm-s390/tlbflush.h
@@ -2,6 +2,7 @@
 #define _S390_TLBFLUSH_H
 
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <asm/processor.h>
 #include <asm/pgalloc.h>