ARM: mm: Transparent huge page support for LPAE systems.

The patch adds support for THP (transparent huge pages) to LPAE
systems. When this feature is enabled, the kernel tries to map
anonymous pages as 2MB sections where possible.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
[steve.capper@linaro.org: symbolic constants used, value of
PMD_SECT_SPLITTING adjusted, tlbflush.h included in pgtable.h,
added PROT_NONE support.]
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Reviewed-by: Will Deacon <will.deacon@arm.com>

arch/arm/Kconfig

@@ -1711,6 +1711,10 @@ config SYS_SUPPORTS_HUGETLBFS
        def_bool y
        depends on ARM_LPAE
 
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE
+       def_bool y
+       depends on ARM_LPAE
+
 source "mm/Kconfig"
 
 config FORCE_MAX_ZONEORDER

arch/arm/include/asm/pgtable-3level-hwdef.h

@@ -42,6 +42,8 @@
  */
 #define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
 #define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
+#define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)

arch/arm/include/asm/pgtable-3level.h

@@ -87,6 +87,11 @@
 #define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 57)	/* PROT_NONE */
 
+#define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
+#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
+#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
+#define PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+
 /*
  * To be used in assembly code with the upper page attributes.
  */
@@ -196,6 +201,61 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pte_huge(pte)		(pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
 #define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
 
+#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
+#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#endif
+
+#define PMD_BIT_FUNC(fn,op) \
+static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+
+PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
+PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
+
+#define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+
+#define pmd_pfn(pmd)		(((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot)	(__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
+
+/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+#define pmd_mknotpresent(pmd)	(__pmd(0))
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY |
+				PMD_SECT_VALID | PMD_SECT_NONE;
+	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
+	return pmd;
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	BUG_ON(addr >= TASK_SIZE);
+
+	/* create a faulting entry if PROT_NONE protected */
+	if (pmd_val(pmd) & PMD_SECT_NONE)
+		pmd_val(pmd) &= ~PMD_SECT_VALID;
+
+	*pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
+	flush_pmd_entry(pmdp);
+}
+
+static inline int has_transparent_hugepage(void)
+{
+	return 1;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_PGTABLE_3LEVEL_H */

arch/arm/include/asm/pgtable.h

@@ -24,6 +24,9 @@
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 
+
+#include <asm/tlbflush.h>
+
 #ifdef CONFIG_ARM_LPAE
 #include <asm/pgtable-3level.h>
 #else

arch/arm/include/asm/tlb.h

@@ -223,6 +223,12 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 #endif
 }
 
+static inline void
+tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)

arch/arm/include/asm/tlbflush.h

@@ -535,6 +535,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 }
 #endif
 
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
 #endif
 
 #endif /* CONFIG_MMU */

arch/arm/mm/fsr-3level.c

@@ -9,7 +9,7 @@ static struct fsr_info fsr_info[] = {
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
-	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
+	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
 	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
 	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},