From dcfdae04bd92e8a2ea155db0e21e3bddc09e0a89 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Tue, 22 Nov 2011 17:30:29 +0000
Subject: ARM: LPAE: Introduce the 3-level page table format definitions
This patch introduces the pgtable-3level*.h files with definitions
specific to the LPAE page table format (3 levels of page tables).
Each table is 4KB and has 512 64-bit entries. An entry can point to a
40-bit physical address. The young, write and exec software bits share
the corresponding hardware bits (negated). Other software bits use spare
bits in the PTE.
The patch also changes some variable types from unsigned long or int to
pteval_t or pgprot_t.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
arch/arm/include/asm/pgtable-3level.h | 102 ++++++++++++++++++++++++++++++++++
1 file changed, 102 insertions(+)
create mode 100644 arch/arm/include/asm/pgtable-3level.h
(limited to 'arch/arm/include/asm/pgtable-3level.h')
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
new file mode 100644
index 000000000000..79bf0acc40db
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -0,0 +1,102 @@
+/*
+ * arch/arm/include/asm/pgtable-3level.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#ifndef _ASM_PGTABLE_3LEVEL_H
+#define _ASM_PGTABLE_3LEVEL_H
+
+/*
+ * With LPAE, there are 3 levels of page tables. Each level has 512 entries of
+ * 8 bytes each, occupying a 4K page. The first level table covers a range of
+ * 512GB, each entry representing 1GB. Since we are limited to 4GB input
+ * address range, only 4 entries in the PGD are used.
+ *
+ * There are enough spare bits in a page table entry for the kernel specific
+ * state.
+ */
+#define PTRS_PER_PTE 512
+#define PTRS_PER_PMD 512
+#define PTRS_PER_PGD 4
+
+#define PTE_HWTABLE_PTRS (PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF (0)
+#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u64))
+
+/*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map.
+ */
+#define PGDIR_SHIFT 30
+
+/*
+ * PMD_SHIFT determines the size a middle-level page table entry can map.
+ */
+#define PMD_SHIFT 21
+
+#define PMD_SIZE (1UL << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT 21
+#define SECTION_SIZE (1UL << SECTION_SHIFT)
+#define SECTION_MASK (~(SECTION_SIZE-1))
+
+#define USER_PTRS_PER_PGD (PAGE_OFFSET / PGDIR_SIZE)
+
+/*
+ * "Linux" PTE definitions for LPAE.
+ *
+ * These bits overlap with the hardware bits but the naming is preserved for
+ * consistency with the classic page table format.
+ */
+#define L_PTE_PRESENT (_AT(pteval_t, 3) << 0) /* Valid */
+#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */
+#define L_PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) /* AttrIndx[0] */
+#define L_PTE_CACHEABLE (_AT(pteval_t, 1) << 3) /* AttrIndx[1] */
+#define L_PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */
+#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) /* AP[2] */
+#define L_PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */
+#define L_PTE_YOUNG (_AT(pteval_t, 1) << 10) /* AF */
+#define L_PTE_XN (_AT(pteval_t, 1) << 54) /* XN */
+#define L_PTE_DIRTY (_AT(pteval_t, 1) << 55) /* unused */
+#define L_PTE_SPECIAL (_AT(pteval_t, 1) << 56) /* unused */
+
+/*
+ * To be used in assembly code with the upper page attributes.
+ */
+#define L_PTE_XN_HIGH (1 << (54 - 32))
+#define L_PTE_DIRTY_HIGH (1 << (55 - 32))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0) << 2) /* strongly ordered */
+#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 1) << 2) /* normal non-cacheable */
+#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 2) << 2) /* normal inner write-through */
+#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 3) << 2) /* normal inner write-back */
+#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 7) << 2) /* normal inner write-alloc */
+#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 4) << 2) /* device */
+#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 4) << 2) /* device */
+#define L_PTE_MT_DEV_WC (_AT(pteval_t, 1) << 2) /* normal non-cacheable */
+#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 3) << 2) /* normal inner write-back */
+#define L_PTE_MT_MASK (_AT(pteval_t, 7) << 2)
+
+#endif /* _ASM_PGTABLE_3LEVEL_H */
--
cgit v1.2.3
From da02877987e6e173ebba137d4e1e155e1f1151cd Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Tue, 22 Nov 2011 17:30:29 +0000
Subject: ARM: LPAE: Page table maintenance for the 3-level format
This patch modifies the pgd/pmd/pte manipulation functions to support
the 3-level page table format. Since there is no need for an 'ext'
argument to cpu_set_pte_ext(), this patch conditionally defines a
different prototype for this function when CONFIG_ARM_LPAE.
The patch also introduces the L_PGD_SWAPPER flag to mark pgd entries
pointing to pmd tables pre-allocated in the swapper_pg_dir and avoid
trying to free them at run-time. This flag is 0 with the classic page
table format.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
arch/arm/include/asm/pgalloc.h | 24 ++++++++++++++++
arch/arm/include/asm/pgtable-3level.h | 53 +++++++++++++++++++++++++++++++++++
arch/arm/include/asm/proc-fns.h | 21 ++++++++++++++
arch/arm/mm/ioremap.c | 8 ++++--
arch/arm/mm/pgd.c | 51 ++++++++++++++++++++++++++++++---
5 files changed, 150 insertions(+), 7 deletions(-)
(limited to 'arch/arm/include/asm/pgtable-3level.h')
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 7418894a737f..943504f53f57 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -25,6 +25,26 @@
#define _PAGE_USER_TABLE (PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))
#define _PAGE_KERNEL_TABLE (PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
+#ifdef CONFIG_ARM_LPAE
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+ return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+ BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+ free_page((unsigned long)pmd);
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+ set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE));
+}
+
+#else /* !CONFIG_ARM_LPAE */
+
/*
* Since we have only two-level page tables, these are trivial
*/
@@ -32,6 +52,8 @@
#define pmd_free(mm, pmd) do { } while (0)
#define pud_populate(mm,pmd,pte) BUG()
+#endif /* CONFIG_ARM_LPAE */
+
extern pgd_t *pgd_alloc(struct mm_struct *mm);
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
@@ -109,7 +131,9 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
{
pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot;
pmdp[0] = __pmd(pmdval);
+#ifndef CONFIG_ARM_LPAE
pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
+#endif
flush_pmd_entry(pmdp);
}
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 79bf0acc40db..759af70f9a0a 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -99,4 +99,57 @@
#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 3) << 2) /* normal inner write-back */
#define L_PTE_MT_MASK (_AT(pteval_t, 7) << 2)
+/*
+ * Software PGD flags.
+ */
+#define L_PGD_SWAPPER (_AT(pgdval_t, 1) << 55) /* swapper_pg_dir entry */
+
+#ifndef __ASSEMBLY__
+
+#define pud_none(pud) (!pud_val(pud))
+#define pud_bad(pud) (!(pud_val(pud) & 2))
+#define pud_present(pud) (pud_val(pud))
+
+#define pud_clear(pudp) \
+ do { \
+ *pudp = __pud(0); \
+ clean_pmd_entry(pudp); \
+ } while (0)
+
+#define set_pud(pudp, pud) \
+ do { \
+ *pudp = pud; \
+ flush_pmd_entry(pudp); \
+ } while (0)
+
+static inline pmd_t *pud_page_vaddr(pud_t pud)
+{
+ return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
+}
+
+/* Find an entry in the second-level page table.. */
+#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+ return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+#define pmd_bad(pmd) (!(pmd_val(pmd) & 2))
+
+#define copy_pmd(pmdpd,pmdps) \
+ do { \
+ *pmdpd = *pmdps; \
+ flush_pmd_entry(pmdpd); \
+ } while (0)
+
+#define pmd_clear(pmdp) \
+ do { \
+ *pmdp = __pmd(0); \
+ clean_pmd_entry(pmdp); \
+ } while (0)
+
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
+
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_PGTABLE_3LEVEL_H */
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 9e92cb205e65..f3628fb3d2b3 100644
--- a/arch/arm/include/asm/proc-fns.h
+++ b/arch/arm/include/asm/proc-fns.h
@@ -65,7 +65,11 @@ extern struct processor {
* Set a possibly extended PTE. Non-extended PTEs should
* ignore 'ext'.
*/
+#ifdef CONFIG_ARM_LPAE
+ void (*set_pte_ext)(pte_t *ptep, pte_t pte);
+#else
void (*set_pte_ext)(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
/* Suspend/resume */
unsigned int suspend_size;
@@ -79,7 +83,11 @@ extern void cpu_proc_fin(void);
extern int cpu_do_idle(void);
extern void cpu_dcache_clean_area(void *, int);
extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
+#ifdef CONFIG_ARM_LPAE
+extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
+#else
extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
+#endif
extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
/* These three are private to arch/arm/kernel/suspend.c */
@@ -107,6 +115,18 @@ extern void cpu_resume(void);
#define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)
+#ifdef CONFIG_ARM_LPAE
+#define cpu_get_pgd() \
+ ({ \
+ unsigned long pg, pg2; \
+ __asm__("mrrc p15, 0, %0, %1, c2" \
+ : "=r" (pg), "=r" (pg2) \
+ : \
+ : "cc"); \
+ pg &= ~(PTRS_PER_PGD*sizeof(pgd_t)-1); \
+ (pgd_t *)phys_to_virt(pg); \
+ })
+#else
#define cpu_get_pgd() \
({ \
unsigned long pg; \
@@ -115,6 +135,7 @@ extern void cpu_resume(void);
pg &= ~0x3fff; \
(pgd_t *)phys_to_virt(pg); \
})
+#endif
#endif
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index c3fa40da3b75..d1f78bacb015 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -64,7 +64,7 @@ void __check_kvm_seq(struct mm_struct *mm)
} while (seq != init_mm.context.kvm_seq);
}
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
/*
* Section support is unsafe on SMP - If you iounmap and ioremap a region,
* the other CPUs will not see this change until their next context switch.
@@ -202,11 +202,13 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
unsigned long addr;
struct vm_struct * area;
+#ifndef CONFIG_ARM_LPAE
/*
* High mappings must be supersection aligned
*/
if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
return NULL;
+#endif
/*
* Don't allow RAM to be mapped - this causes problems with ARMv6+
@@ -228,7 +230,7 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
return NULL;
addr = (unsigned long)area->addr;
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
if (DOMAIN_IO == 0 &&
(((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) ||
cpu_is_xsc3()) && pfn >= 0x100000 &&
@@ -320,7 +322,7 @@ __arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
void __iounmap(volatile void __iomem *io_addr)
{
void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
struct vm_struct **p, *tmp;
/*
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index b2027c154b2a..a3e78ccabd65 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -10,6 +10,7 @@
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/highmem.h>
+#include <linux/slab.h>
#include <asm/pgalloc.h>
#include <asm/page.h>
@@ -17,6 +18,14 @@
#include "mm.h"
+#ifdef CONFIG_ARM_LPAE
+#define __pgd_alloc() kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL)
+#define __pgd_free(pgd) kfree(pgd)
+#else
+#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL, 2)
+#define __pgd_free(pgd) free_pages((unsigned long)pgd, 2)
+#endif
+
/*
* need to get a 16k page for level 1
*/
@@ -27,7 +36,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
pmd_t *new_pmd, *init_pmd;
pte_t *new_pte, *init_pte;
- new_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, 2);
+ new_pgd = __pgd_alloc();
if (!new_pgd)
goto no_pgd;
@@ -42,10 +51,25 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
+#ifdef CONFIG_ARM_LPAE
+ /*
+ * Allocate PMD table for modules and pkmap mappings.
+ */
+ new_pud = pud_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
+ MODULES_VADDR);
+ if (!new_pud)
+ goto no_pud;
+
+ new_pmd = pmd_alloc(mm, new_pud, 0);
+ if (!new_pmd)
+ goto no_pmd;
+#endif
+
if (!vectors_high()) {
/*
* On ARM, first page must always be allocated since it
- * contains the machine vectors.
+ * contains the machine vectors. The vectors are always high
+ * with LPAE.
*/
new_pud = pud_alloc(mm, new_pgd, 0);
if (!new_pud)
@@ -74,7 +98,7 @@ no_pte:
no_pmd:
pud_free(mm, new_pud);
no_pud:
- free_pages((unsigned long)new_pgd, 2);
+ __pgd_free(new_pgd);
no_pgd:
return NULL;
}
@@ -111,5 +135,24 @@ no_pud:
pgd_clear(pgd);
pud_free(mm, pud);
no_pgd:
- free_pages((unsigned long) pgd_base, 2);
+#ifdef CONFIG_ARM_LPAE
+ /*
+ * Free modules/pkmap or identity pmd tables.
+ */
+ for (pgd = pgd_base; pgd < pgd_base + PTRS_PER_PGD; pgd++) {
+ if (pgd_none_or_clear_bad(pgd))
+ continue;
+ if (pgd_val(*pgd) & L_PGD_SWAPPER)
+ continue;
+ pud = pud_offset(pgd, 0);
+ if (pud_none_or_clear_bad(pud))
+ continue;
+ pmd = pmd_offset(pud, 0);
+ pud_clear(pud);
+ pmd_free(mm, pmd);
+ pgd_clear(pgd);
+ pud_free(mm, pud);
+ }
+#endif
+ __pgd_free(pgd_base);
}
--
cgit v1.2.3