Hi,
This set of patches adds support for the Large Physical Extensions on
the ARM architecture (available with the Cortex-A15 processor). LPAE
comes with a 3-level page table format (compared to 2-level for the
classic one), allowing up to 40-bit physical address space.
The ARM LPAE documentation is available from (free registration needed):
http://infocenter.arm.com/help/topic/com.arm.doc.ddi0406b_virtualization_extns/index.html
The full set of patches on top Linux 2.6.39 (LPAE, support for an
emulated Versatile Express with Cortex-A15 tile and generic timers) is
available on this branch:
git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-2.6-cm.git arm-lpae
Changelog:
- Rebased on top of Linux 2.6.39.
- Russell's nopud patch included in the branch above (but not posted as
part of the LPAE series).
- The reserved ASID 0 is no longer used during context switching. The
ASID fixes posted separately by Will Deacon have been included in the
branch above.
- Fixes for ISBs during MMU enabling.
- Separate proc-v7lpae.S file to avoid unreadable asm code (there are a
few other #ifdefs in head.S but not that many to require a dedicated
LPAE() macro).
Catalin Marinas (14):
ARM: LPAE: Use long long printk format for displaying the pud
ARM: LPAE: Use unsigned long for __phys_to_virt and __virt_to_phys
ARM: LPAE: Use PMD_(SHIFT|SIZE|MASK) instead of PGDIR_*
ARM: LPAE: Factor out 2-level page table definitions into separate
files
ARM: LPAE: Add (pte|pmd|pgd|pgprot)val_t type definitions as u32
ARM: LPAE: Use a mask for physical addresses in page table entries
ARM: LPAE: Introduce the 3-level page table format definitions
ARM: LPAE: Page table maintenance for the 3-level format
ARM: LPAE: MMU setup for the 3-level page table format
ARM: LPAE: Invalidate the TLB before freeing the PMD
ARM: LPAE: Add fault handling support
ARM: LPAE: Add context switching support
ARM: LPAE: Add identity mapping support for the 3-level page table
format
ARM: LPAE: Add the Kconfig entries
Will Deacon (4):
ARM: LPAE: add ISBs around MMU enabling code
ARM: LPAE: Use generic dma_addr_t type definition
ARM: LPAE: mark memory banks with start > ULONG_MAX as highmem
ARM: LPAE: add support for ATAG_MEM64
arch/arm/Kconfig | 2 +-
arch/arm/boot/compressed/head.S | 1 +
arch/arm/include/asm/assembler.h | 11 +
arch/arm/include/asm/memory.h | 4 +-
arch/arm/include/asm/page.h | 44 +---
arch/arm/include/asm/pgalloc.h | 28 ++-
arch/arm/include/asm/pgtable-2level-hwdef.h | 93 ++++++
arch/arm/include/asm/pgtable-2level-types.h | 67 +++++
arch/arm/include/asm/pgtable-2level.h | 143 +++++++++
arch/arm/include/asm/pgtable-3level-hwdef.h | 82 ++++++
arch/arm/include/asm/pgtable-3level-types.h | 69 +++++
arch/arm/include/asm/pgtable-3level.h | 107 +++++++
arch/arm/include/asm/pgtable-hwdef.h | 81 +-----
arch/arm/include/asm/pgtable.h | 211 +++++---------
arch/arm/include/asm/proc-fns.h | 25 ++
arch/arm/include/asm/setup.h | 10 +-
arch/arm/include/asm/tlb.h | 11 +-
arch/arm/include/asm/tlbflush.h | 4 +-
arch/arm/include/asm/types.h | 11 +-
arch/arm/kernel/compat.c | 4 +-
arch/arm/kernel/head.S | 119 ++++++---
arch/arm/kernel/module.c | 2 +-
arch/arm/kernel/setup.c | 12 +-
arch/arm/kernel/sleep.S | 2 +
arch/arm/mm/Kconfig | 13 +
arch/arm/mm/Makefile | 4 +
arch/arm/mm/alignment.c | 8 +-
arch/arm/mm/context.c | 34 ++-
arch/arm/mm/dma-mapping.c | 6 +-
arch/arm/mm/fault.c | 82 +++++-
arch/arm/mm/idmap.c | 36 +++-
arch/arm/mm/ioremap.c | 8 +-
arch/arm/mm/mm.h | 4 +-
arch/arm/mm/mmu.c | 51 +++-
arch/arm/mm/pgd.c | 51 +++-
arch/arm/mm/proc-macros.S | 5 +-
arch/arm/mm/proc-v7lpae.S | 422 +++++++++++++++++++++++++++
37 files changed, 1517 insertions(+), 350 deletions(-)
create mode 100644 arch/arm/include/asm/pgtable-2level-hwdef.h
create mode 100644 arch/arm/include/asm/pgtable-2level-types.h
create mode 100644 arch/arm/include/asm/pgtable-2level.h
create mode 100644 arch/arm/include/asm/pgtable-3level-hwdef.h
create mode 100644 arch/arm/include/asm/pgtable-3level-types.h
create mode 100644 arch/arm/include/asm/pgtable-3level.h
create mode 100644 arch/arm/mm/proc-v7lpae.S
Currently using just long but this is not enough for the LPAE format
(64-bit entries).
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/mm/fault.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index bc0e1d8..ee76923 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -94,7 +94,7 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
pud = pud_offset(pgd, addr);
if (PTRS_PER_PUD != 1)
- printk(", *pud=%08lx", pud_val(*pud));
+ printk(", *pud=%08llx", (long long)pud_val(*pud));
if (pud_none(*pud))
break;
From: Will Deacon <[email protected]>
Before we enable the MMU, we must ensure that the TTBR registers contain
sane values. After the MMU has been enabled, we jump to the *virtual*
address of the following function, so we also need to ensure that the
SCTLR write has taken effect.
This patch adds ISB instructions around the SCTLR write to ensure the
visibility of the above.
Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/boot/compressed/head.S | 1 +
arch/arm/include/asm/assembler.h | 11 +++++++++++
arch/arm/kernel/head.S | 2 ++
arch/arm/kernel/sleep.S | 2 ++
4 files changed, 16 insertions(+), 0 deletions(-)
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 49f5b2e..ef22486 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -526,6 +526,7 @@ __armv7_mmu_cache_on:
mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer
mcrne p15, 0, r1, c3, c0, 0 @ load domain access control
#endif
+ mcr p15, 0, r0, c7, c5, 4 @ ISB
mcr p15, 0, r0, c1, c0, 0 @ load control register
mrc p15, 0, r0, c1, c0, 0 @ and read it back
mov r0, #0
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index bc2d2d7..2bcc456 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -184,6 +184,17 @@
#endif
/*
+ * Instruction barrier
+ */
+ .macro instr_sync
+#if __LINUX_ARM_ARCH__ >= 7
+ isb
+#elif __LINUX_ARM_ARCH__ == 6
+ mcr p15, 0, r0, c7, c5, 4
+#endif
+ .endm
+
+/*
* SMP data memory barrier
*/
.macro smp_dmb mode
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 8224b1d..b7101ff 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -388,8 +388,10 @@ ENDPROC(__enable_mmu)
.align 5
__turn_mmu_on:
mov r0, r0
+ instr_sync
mcr p15, 0, r0, c1, c0, 0 @ write control reg
mrc p15, 0, r3, c0, c0, 0 @ read id reg
+ instr_sync
mov r3, r3
mov r3, r13
mov pc, r3
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 6398ead..1ac5dce 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -88,8 +88,10 @@ ENDPROC(cpu_resume_mmu)
.ltorg
.align 5
cpu_resume_turn_mmu_on:
+ instr_sync
mcr p15, 0, r1, c1, c0, 0 @ turn on MMU, I-cache, etc
mrc p15, 0, r1, c0, c0, 0 @ read id reg
+ instr_sync
mov r1, r1
mov r1, r1
mov pc, r3 @ jump to virtual address
The !CONFIG_ARM_PATCH_PHYS_VIRT case uses macros for __phys_to_virt and
__virt_to_phys but does not use any type casting. This causes compiler
warnings with LPAE where the phys_addr_t and dma_addr_t are 64-bit:
CC arch/arm/mm/dma-mapping.o
In file included from /work/Linux/linux-marc/include/linux/dma-mapping.h:93:0,
from /work/Linux/linux-marc/arch/arm/mm/dma-mapping.c:19:
/work/Linux/linux-marc/arch/arm/include/asm/dma-mapping.h: In function 'dma_to_virt':
/work/Linux/linux-marc/arch/arm/include/asm/dma-mapping.h:35:9: warning:
cast to pointer from integer of different size
Note that these macros are only valid for lowmem physical addresses
where the range is within 32-bit address range.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/include/asm/memory.h | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 431077c..10e4b4c 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -194,8 +194,8 @@ static inline unsigned long __phys_to_virt(unsigned long x)
return t;
}
#else
-#define __virt_to_phys(x) ((x) - PAGE_OFFSET + PHYS_OFFSET)
-#define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET)
+#define __virt_to_phys(x) ((unsigned long)(x) - PAGE_OFFSET + PHYS_OFFSET)
+#define __phys_to_virt(x) ((unsigned long)(x) - PHYS_OFFSET + PAGE_OFFSET)
#endif
#endif
PGDIR_SHIFT and PMD_SHIFT for the classic 2-level page table format have
the same value (21). This patch converts the PGDIR_* uses in the kernel
to the PMD_* equivalent so that LPAE builds can reuse the same code.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/kernel/module.c | 2 +-
arch/arm/mm/dma-mapping.c | 6 +++---
arch/arm/mm/mmu.c | 10 +++++-----
3 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index fee7c36..116016d 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -33,7 +33,7 @@
* recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
*/
#undef MODULES_VADDR
-#define MODULES_VADDR (((unsigned long)_etext + ~PGDIR_MASK) & PGDIR_MASK)
+#define MODULES_VADDR (((unsigned long)_etext + ~PMD_MASK) & PMD_MASK)
#endif
#ifdef CONFIG_MMU
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 82a093c..334e9af 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -121,8 +121,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
#endif
#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
-#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
+#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PMD_SHIFT)
+#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PMD_SHIFT)
/*
* These are the page tables (2MB each) covering uncached, DMA consistent allocations
@@ -181,7 +181,7 @@ static int __init consistent_init(void)
}
consistent_pte[i++] = pte;
- base += (1 << PGDIR_SHIFT);
+ base += (1 << PMD_SHIFT);
} while (base < CONSISTENT_END);
return ret;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 9d8f0c8..a69f8e4 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -865,14 +865,14 @@ static inline void prepare_page_table(void)
/*
* Clear out all the mappings below the kernel image.
*/
- for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
+ for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
#ifdef CONFIG_XIP_KERNEL
/* The XIP kernel is mapped in the module area -- skip over it */
- addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK;
+ addr = ((unsigned long)_etext + PMD_SIZE - 1) & PMD_MASK;
#endif
- for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
+ for ( ; addr < PAGE_OFFSET; addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
/*
@@ -887,7 +887,7 @@ static inline void prepare_page_table(void)
* memory bank, up to the end of the vmalloc region.
*/
for (addr = __phys_to_virt(end);
- addr < VMALLOC_END; addr += PGDIR_SIZE)
+ addr < VMALLOC_END; addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
}
@@ -928,7 +928,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
*/
vectors_page = early_alloc(PAGE_SIZE);
- for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
+ for (addr = VMALLOC_END; addr; addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
/*
This patch moves page table definitions from asm/page.h, asm/pgtable.h
and asm/ptgable-hwdef.h into corresponding *-2level* files.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/include/asm/page.h | 42 +--------
arch/arm/include/asm/pgtable-2level-hwdef.h | 91 +++++++++++++++++
arch/arm/include/asm/pgtable-2level-types.h | 64 ++++++++++++
arch/arm/include/asm/pgtable-2level.h | 143 +++++++++++++++++++++++++++
arch/arm/include/asm/pgtable-hwdef.h | 77 +--------------
arch/arm/include/asm/pgtable.h | 135 +-------------------------
6 files changed, 302 insertions(+), 250 deletions(-)
create mode 100644 arch/arm/include/asm/pgtable-2level-hwdef.h
create mode 100644 arch/arm/include/asm/pgtable-2level-types.h
create mode 100644 arch/arm/include/asm/pgtable-2level.h
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index ac75d08..ca94653 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -151,47 +151,7 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
extern void copy_page(void *to, const void *from);
-typedef unsigned long pteval_t;
-
-#undef STRICT_MM_TYPECHECKS
-
-#ifdef STRICT_MM_TYPECHECKS
-/*
- * These are used to make use of C type-checking..
- */
-typedef struct { pteval_t pte; } pte_t;
-typedef struct { unsigned long pmd; } pmd_t;
-typedef struct { unsigned long pgd[2]; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
-
-#define pte_val(x) ((x).pte)
-#define pmd_val(x) ((x).pmd)
-#define pgd_val(x) ((x).pgd[0])
-#define pgprot_val(x) ((x).pgprot)
-
-#define __pte(x) ((pte_t) { (x) } )
-#define __pmd(x) ((pmd_t) { (x) } )
-#define __pgprot(x) ((pgprot_t) { (x) } )
-
-#else
-/*
- * .. while these make it easier on the compiler
- */
-typedef pteval_t pte_t;
-typedef unsigned long pmd_t;
-typedef unsigned long pgd_t[2];
-typedef unsigned long pgprot_t;
-
-#define pte_val(x) (x)
-#define pmd_val(x) (x)
-#define pgd_val(x) ((x)[0])
-#define pgprot_val(x) (x)
-
-#define __pte(x) (x)
-#define __pmd(x) (x)
-#define __pgprot(x) (x)
-
-#endif /* STRICT_MM_TYPECHECKS */
+#include <asm/pgtable-2level-types.h>
#endif /* CONFIG_MMU */
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
new file mode 100644
index 0000000..436529c
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -0,0 +1,91 @@
+/*
+ * arch/arm/include/asm/pgtable-2level-hwdef.h
+ *
+ * Copyright (C) 1995-2002 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_HWDEF_H
+#define _ASM_PGTABLE_2LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1 descriptor (PMD)
+ * - common
+ */
+#define PMD_TYPE_MASK (3 << 0)
+#define PMD_TYPE_FAULT (0 << 0)
+#define PMD_TYPE_TABLE (1 << 0)
+#define PMD_TYPE_SECT (2 << 0)
+#define PMD_BIT4 (1 << 4)
+#define PMD_DOMAIN(x) ((x) << 5)
+#define PMD_PROTECTION (1 << 9) /* v5 */
+/*
+ * - section
+ */
+#define PMD_SECT_BUFFERABLE (1 << 2)
+#define PMD_SECT_CACHEABLE (1 << 3)
+#define PMD_SECT_XN (1 << 4) /* v6 */
+#define PMD_SECT_AP_WRITE (1 << 10)
+#define PMD_SECT_AP_READ (1 << 11)
+#define PMD_SECT_TEX(x) ((x) << 12) /* v5 */
+#define PMD_SECT_APX (1 << 15) /* v6 */
+#define PMD_SECT_S (1 << 16) /* v6 */
+#define PMD_SECT_nG (1 << 17) /* v6 */
+#define PMD_SECT_SUPER (1 << 18) /* v6 */
+#define PMD_SECT_AF (0)
+
+#define PMD_SECT_UNCACHED (0)
+#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE)
+#define PMD_SECT_WT (PMD_SECT_CACHEABLE)
+#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
+#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2))
+
+/*
+ * - coarse table (not used)
+ */
+
+/*
+ * + Level 2 descriptor (PTE)
+ * - common
+ */
+#define PTE_TYPE_MASK (3 << 0)
+#define PTE_TYPE_FAULT (0 << 0)
+#define PTE_TYPE_LARGE (1 << 0)
+#define PTE_TYPE_SMALL (2 << 0)
+#define PTE_TYPE_EXT (3 << 0) /* v5 */
+#define PTE_BUFFERABLE (1 << 2)
+#define PTE_CACHEABLE (1 << 3)
+
+/*
+ * - extended small page/tiny page
+ */
+#define PTE_EXT_XN (1 << 0) /* v6 */
+#define PTE_EXT_AP_MASK (3 << 4)
+#define PTE_EXT_AP0 (1 << 4)
+#define PTE_EXT_AP1 (2 << 4)
+#define PTE_EXT_AP_UNO_SRO (0 << 4)
+#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0)
+#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1)
+#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0)
+#define PTE_EXT_TEX(x) ((x) << 6) /* v5 */
+#define PTE_EXT_APX (1 << 9) /* v6 */
+#define PTE_EXT_COHERENT (1 << 9) /* XScale3 */
+#define PTE_EXT_SHARED (1 << 10) /* v6 */
+#define PTE_EXT_NG (1 << 11) /* v6 */
+
+/*
+ * - small page
+ */
+#define PTE_SMALL_AP_MASK (0xff << 4)
+#define PTE_SMALL_AP_UNO_SRO (0x00 << 4)
+#define PTE_SMALL_AP_UNO_SRW (0x55 << 4)
+#define PTE_SMALL_AP_URO_SRW (0xaa << 4)
+#define PTE_SMALL_AP_URW_SRW (0xff << 4)
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-2level-types.h b/arch/arm/include/asm/pgtable-2level-types.h
new file mode 100644
index 0000000..8a01f62
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level-types.h
@@ -0,0 +1,64 @@
+/*
+ * arch/arm/include/asm/pgtable-2level-types.h
+ *
+ * Copyright (C) 1995-2003 Russell King
+ *
+ * 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_2LEVEL_TYPES_H
+#define _ASM_PGTABLE_2LEVEL_TYPES_H
+
+typedef unsigned long pteval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pgd[2]; } pgd_t;
+typedef struct { unsigned long pgprot; } pgprot_t;
+
+#define pte_val(x) ((x).pte)
+#define pmd_val(x) ((x).pmd)
+#define pgd_val(x) ((x).pgd[0])
+#define pgprot_val(x) ((x).pgprot)
+
+#define __pte(x) ((pte_t) { (x) } )
+#define __pmd(x) ((pmd_t) { (x) } )
+#define __pgprot(x) ((pgprot_t) { (x) } )
+
+#else
+/*
+ * .. while these make it easier on the compiler
+ */
+typedef pteval_t pte_t;
+typedef unsigned long pmd_t;
+typedef unsigned long pgd_t[2];
+typedef unsigned long pgprot_t;
+
+#define pte_val(x) (x)
+#define pmd_val(x) (x)
+#define pgd_val(x) ((x)[0])
+#define pgprot_val(x) (x)
+
+#define __pte(x) (x)
+#define __pmd(x) (x)
+#define __pgprot(x) (x)
+
+#endif /* STRICT_MM_TYPECHECKS */
+
+#endif /* _ASM_PGTABLE_2LEVEL_TYPES_H */
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
new file mode 100644
index 0000000..470457e
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -0,0 +1,143 @@
+/*
+ * arch/arm/include/asm/pgtable-2level.h
+ *
+ * Copyright (C) 1995-2002 Russell King
+ *
+ * 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.
+ */
+#ifndef _ASM_PGTABLE_2LEVEL_H
+#define _ASM_PGTABLE_2LEVEL_H
+
+/*
+ * Hardware-wise, we have a two level page table structure, where the first
+ * level has 4096 entries, and the second level has 256 entries. Each entry
+ * is one 32-bit word. Most of the bits in the second level entry are used
+ * by hardware, and there aren't any "accessed" and "dirty" bits.
+ *
+ * Linux on the other hand has a three level page table structure, which can
+ * be wrapped to fit a two level page table structure easily - using the PGD
+ * and PTE only. However, Linux also expects one "PTE" table per page, and
+ * at least a "dirty" bit.
+ *
+ * Therefore, we tweak the implementation slightly - we tell Linux that we
+ * have 2048 entries in the first level, each of which is 8 bytes (iow, two
+ * hardware pointers to the second level.) The second level contains two
+ * hardware PTE tables arranged contiguously, preceded by Linux versions
+ * which contain the state information Linux needs. We, therefore, end up
+ * with 512 entries in the "PTE" level.
+ *
+ * This leads to the page tables having the following layout:
+ *
+ * pgd pte
+ * | |
+ * +--------+
+ * | | +------------+ +0
+ * +- - - - + | Linux pt 0 |
+ * | | +------------+ +1024
+ * +--------+ +0 | Linux pt 1 |
+ * | |-----> +------------+ +2048
+ * +- - - - + +4 | h/w pt 0 |
+ * | |-----> +------------+ +3072
+ * +--------+ +8 | h/w pt 1 |
+ * | | +------------+ +4096
+ *
+ * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
+ * PTE_xxx for definitions of bits appearing in the "h/w pt".
+ *
+ * PMD_xxx definitions refer to bits in the first level page table.
+ *
+ * The "dirty" bit is emulated by only granting hardware write permission
+ * iff the page is marked "writable" and "dirty" in the Linux PTE. This
+ * means that a write to a clean page will cause a permission fault, and
+ * the Linux MM layer will mark the page dirty via handle_pte_fault().
+ * For the hardware to notice the permission change, the TLB entry must
+ * be flushed, and ptep_set_access_flags() does that for us.
+ *
+ * The "accessed" or "young" bit is emulated by a similar method; we only
+ * allow accesses to the page if the "young" bit is set. Accesses to the
+ * page will cause a fault, and handle_pte_fault() will set the young bit
+ * for us as long as the page is marked present in the corresponding Linux
+ * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is
+ * up to date.
+ *
+ * However, when the "young" bit is cleared, we deny access to the page
+ * by clearing the hardware PTE. Currently Linux does not flush the TLB
+ * for us in this case, which means the TLB will retain the transation
+ * until either the TLB entry is evicted under pressure, or a context
+ * switch which changes the user space mapping occurs.
+ */
+#define PTRS_PER_PTE 512
+#define PTRS_PER_PMD 1
+#define PTRS_PER_PGD 2048
+
+#define PTE_HWTABLE_PTRS (PTRS_PER_PTE)
+#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t))
+#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32))
+
+/*
+ * PMD_SHIFT determines the size of the area a second-level page table can map
+ * PGDIR_SHIFT determines what a third-level page table entry can map
+ */
+#define PMD_SHIFT 21
+#define PGDIR_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 20
+#define SECTION_SIZE (1UL << SECTION_SHIFT)
+#define SECTION_MASK (~(SECTION_SIZE-1))
+
+/*
+ * ARMv6 supersection address mask and size definitions.
+ */
+#define SUPERSECTION_SHIFT 24
+#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT)
+#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1))
+
+#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
+
+/*
+ * "Linux" PTE definitions.
+ *
+ * We keep two sets of PTEs - the hardware and the linux version.
+ * This allows greater flexibility in the way we map the Linux bits
+ * onto the hardware tables, and allows us to have YOUNG and DIRTY
+ * bits.
+ *
+ * The PTE table pointer refers to the hardware entries; the "Linux"
+ * entries are stored 1024 bytes below.
+ */
+#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0)
+#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1)
+#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */
+#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6)
+#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7)
+#define L_PTE_USER (_AT(pteval_t, 1) << 8)
+#define L_PTE_XN (_AT(pteval_t, 1) << 9)
+#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */
+
+/*
+ * These are the memory types, defined to be compatible with
+ * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB
+ */
+#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */
+#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */
+#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */
+#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */
+#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */
+#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */
+#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */
+#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */
+#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */
+#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */
+#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2)
+
+#endif /* _ASM_PGTABLE_2LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable-hwdef.h b/arch/arm/include/asm/pgtable-hwdef.h
index fd1521d..1831111 100644
--- a/arch/arm/include/asm/pgtable-hwdef.h
+++ b/arch/arm/include/asm/pgtable-hwdef.h
@@ -10,81 +10,6 @@
#ifndef _ASMARM_PGTABLE_HWDEF_H
#define _ASMARM_PGTABLE_HWDEF_H
-/*
- * Hardware page table definitions.
- *
- * + Level 1 descriptor (PMD)
- * - common
- */
-#define PMD_TYPE_MASK (3 << 0)
-#define PMD_TYPE_FAULT (0 << 0)
-#define PMD_TYPE_TABLE (1 << 0)
-#define PMD_TYPE_SECT (2 << 0)
-#define PMD_BIT4 (1 << 4)
-#define PMD_DOMAIN(x) ((x) << 5)
-#define PMD_PROTECTION (1 << 9) /* v5 */
-/*
- * - section
- */
-#define PMD_SECT_BUFFERABLE (1 << 2)
-#define PMD_SECT_CACHEABLE (1 << 3)
-#define PMD_SECT_XN (1 << 4) /* v6 */
-#define PMD_SECT_AP_WRITE (1 << 10)
-#define PMD_SECT_AP_READ (1 << 11)
-#define PMD_SECT_TEX(x) ((x) << 12) /* v5 */
-#define PMD_SECT_APX (1 << 15) /* v6 */
-#define PMD_SECT_S (1 << 16) /* v6 */
-#define PMD_SECT_nG (1 << 17) /* v6 */
-#define PMD_SECT_SUPER (1 << 18) /* v6 */
-
-#define PMD_SECT_UNCACHED (0)
-#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE)
-#define PMD_SECT_WT (PMD_SECT_CACHEABLE)
-#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
-#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
-#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
-#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2))
-
-/*
- * - coarse table (not used)
- */
-
-/*
- * + Level 2 descriptor (PTE)
- * - common
- */
-#define PTE_TYPE_MASK (3 << 0)
-#define PTE_TYPE_FAULT (0 << 0)
-#define PTE_TYPE_LARGE (1 << 0)
-#define PTE_TYPE_SMALL (2 << 0)
-#define PTE_TYPE_EXT (3 << 0) /* v5 */
-#define PTE_BUFFERABLE (1 << 2)
-#define PTE_CACHEABLE (1 << 3)
-
-/*
- * - extended small page/tiny page
- */
-#define PTE_EXT_XN (1 << 0) /* v6 */
-#define PTE_EXT_AP_MASK (3 << 4)
-#define PTE_EXT_AP0 (1 << 4)
-#define PTE_EXT_AP1 (2 << 4)
-#define PTE_EXT_AP_UNO_SRO (0 << 4)
-#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0)
-#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1)
-#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0)
-#define PTE_EXT_TEX(x) ((x) << 6) /* v5 */
-#define PTE_EXT_APX (1 << 9) /* v6 */
-#define PTE_EXT_COHERENT (1 << 9) /* XScale3 */
-#define PTE_EXT_SHARED (1 << 10) /* v6 */
-#define PTE_EXT_NG (1 << 11) /* v6 */
-
-/*
- * - small page
- */
-#define PTE_SMALL_AP_MASK (0xff << 4)
-#define PTE_SMALL_AP_UNO_SRO (0x00 << 4)
-#define PTE_SMALL_AP_UNO_SRW (0x55 << 4)
-#define PTE_SMALL_AP_URO_SRW (0xaa << 4)
-#define PTE_SMALL_AP_URW_SRW (0xff << 4)
+#include <asm/pgtable-2level-hwdef.h>
#endif
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index c2663f4..9618052 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -25,6 +25,8 @@
#include <mach/vmalloc.h>
#include <asm/pgtable-hwdef.h>
+#include <asm/pgtable-2level.h>
+
/*
* Just any arbitrary offset to the start of the vmalloc VM area: the
* current 8MB value just means that there will be a 8MB "hole" after the
@@ -42,79 +44,6 @@
#define VMALLOC_START (((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
#endif
-/*
- * Hardware-wise, we have a two level page table structure, where the first
- * level has 4096 entries, and the second level has 256 entries. Each entry
- * is one 32-bit word. Most of the bits in the second level entry are used
- * by hardware, and there aren't any "accessed" and "dirty" bits.
- *
- * Linux on the other hand has a three level page table structure, which can
- * be wrapped to fit a two level page table structure easily - using the PGD
- * and PTE only. However, Linux also expects one "PTE" table per page, and
- * at least a "dirty" bit.
- *
- * Therefore, we tweak the implementation slightly - we tell Linux that we
- * have 2048 entries in the first level, each of which is 8 bytes (iow, two
- * hardware pointers to the second level.) The second level contains two
- * hardware PTE tables arranged contiguously, preceded by Linux versions
- * which contain the state information Linux needs. We, therefore, end up
- * with 512 entries in the "PTE" level.
- *
- * This leads to the page tables having the following layout:
- *
- * pgd pte
- * | |
- * +--------+
- * | | +------------+ +0
- * +- - - - + | Linux pt 0 |
- * | | +------------+ +1024
- * +--------+ +0 | Linux pt 1 |
- * | |-----> +------------+ +2048
- * +- - - - + +4 | h/w pt 0 |
- * | |-----> +------------+ +3072
- * +--------+ +8 | h/w pt 1 |
- * | | +------------+ +4096
- *
- * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
- * PTE_xxx for definitions of bits appearing in the "h/w pt".
- *
- * PMD_xxx definitions refer to bits in the first level page table.
- *
- * The "dirty" bit is emulated by only granting hardware write permission
- * iff the page is marked "writable" and "dirty" in the Linux PTE. This
- * means that a write to a clean page will cause a permission fault, and
- * the Linux MM layer will mark the page dirty via handle_pte_fault().
- * For the hardware to notice the permission change, the TLB entry must
- * be flushed, and ptep_set_access_flags() does that for us.
- *
- * The "accessed" or "young" bit is emulated by a similar method; we only
- * allow accesses to the page if the "young" bit is set. Accesses to the
- * page will cause a fault, and handle_pte_fault() will set the young bit
- * for us as long as the page is marked present in the corresponding Linux
- * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is
- * up to date.
- *
- * However, when the "young" bit is cleared, we deny access to the page
- * by clearing the hardware PTE. Currently Linux does not flush the TLB
- * for us in this case, which means the TLB will retain the transation
- * until either the TLB entry is evicted under pressure, or a context
- * switch which changes the user space mapping occurs.
- */
-#define PTRS_PER_PTE 512
-#define PTRS_PER_PMD 1
-#define PTRS_PER_PGD 2048
-
-#define PTE_HWTABLE_PTRS (PTRS_PER_PTE)
-#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t))
-#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32))
-
-/*
- * PMD_SHIFT determines the size of the area a second-level page table can map
- * PGDIR_SHIFT determines what a third-level page table entry can map
- */
-#define PMD_SHIFT 21
-#define PGDIR_SHIFT 21
-
#define LIBRARY_TEXT_START 0x0c000000
#ifndef __ASSEMBLY__
@@ -125,12 +54,6 @@ extern void __pgd_error(const char *file, int line, pgd_t);
#define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte)
#define pmd_ERROR(pmd) __pmd_error(__FILE__, __LINE__, pmd)
#define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd)
-#endif /* !__ASSEMBLY__ */
-
-#define PMD_SIZE (1UL << PMD_SHIFT)
-#define PMD_MASK (~(PMD_SIZE-1))
-#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
-#define PGDIR_MASK (~(PGDIR_SIZE-1))
/*
* This is the lowest virtual address we can permit any user space
@@ -139,60 +62,6 @@ extern void __pgd_error(const char *file, int line, pgd_t);
*/
#define FIRST_USER_ADDRESS PAGE_SIZE
-#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
-
-/*
- * section address mask and size definitions.
- */
-#define SECTION_SHIFT 20
-#define SECTION_SIZE (1UL << SECTION_SHIFT)
-#define SECTION_MASK (~(SECTION_SIZE-1))
-
-/*
- * ARMv6 supersection address mask and size definitions.
- */
-#define SUPERSECTION_SHIFT 24
-#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT)
-#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1))
-
-/*
- * "Linux" PTE definitions.
- *
- * We keep two sets of PTEs - the hardware and the linux version.
- * This allows greater flexibility in the way we map the Linux bits
- * onto the hardware tables, and allows us to have YOUNG and DIRTY
- * bits.
- *
- * The PTE table pointer refers to the hardware entries; the "Linux"
- * entries are stored 1024 bytes below.
- */
-#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0)
-#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1)
-#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */
-#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6)
-#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7)
-#define L_PTE_USER (_AT(pteval_t, 1) << 8)
-#define L_PTE_XN (_AT(pteval_t, 1) << 9)
-#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */
-
-/*
- * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB
- */
-#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */
-#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */
-#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */
-#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */
-#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */
-#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */
-#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */
-#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */
-#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */
-#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */
-#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2)
-
-#ifndef __ASSEMBLY__
-
/*
* The pgprot_* and protection_map entries will be fixed up in runtime
* to include the cachable and bufferable bits based on memory policy,
This patch defines the (pte|pmd|pgd|pgprot)val_t as u32 and changes the
page table types to be based on these. The PMD bits are converted to the
corresponding type using the _AT macro.
The flush_pmd_entry/clean_pmd_entry argument was changed to (void *) to
allow them to be used with both PGD and PMD pointers and avoid code
duplication.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/include/asm/pgalloc.h | 4 +-
arch/arm/include/asm/pgtable-2level-hwdef.h | 82 +++++++++++++-------------
arch/arm/include/asm/pgtable-2level-types.h | 17 +++--
arch/arm/include/asm/tlbflush.h | 4 +-
arch/arm/mm/mm.h | 4 +-
arch/arm/mm/mmu.c | 4 +-
6 files changed, 59 insertions(+), 56 deletions(-)
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index a87d4cf..7418894 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -105,9 +105,9 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
}
static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
- unsigned long prot)
+ pmdval_t prot)
{
- unsigned long pmdval = (pte + PTE_HWTABLE_OFF) | prot;
+ pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot;
pmdp[0] = __pmd(pmdval);
pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
flush_pmd_entry(pmdp);
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index 436529c..2b52c40 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -16,29 +16,29 @@
* + Level 1 descriptor (PMD)
* - common
*/
-#define PMD_TYPE_MASK (3 << 0)
-#define PMD_TYPE_FAULT (0 << 0)
-#define PMD_TYPE_TABLE (1 << 0)
-#define PMD_TYPE_SECT (2 << 0)
-#define PMD_BIT4 (1 << 4)
-#define PMD_DOMAIN(x) ((x) << 5)
-#define PMD_PROTECTION (1 << 9) /* v5 */
+#define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0)
+#define PMD_TYPE_TABLE (_AT(pmdval_t, 1) << 0)
+#define PMD_TYPE_SECT (_AT(pmdval_t, 2) << 0)
+#define PMD_BIT4 (_AT(pmdval_t, 1) << 4)
+#define PMD_DOMAIN(x) (_AT(pmdval_t, (x)) << 5)
+#define PMD_PROTECTION (_AT(pmdval_t, 1) << 9) /* v5 */
/*
* - section
*/
-#define PMD_SECT_BUFFERABLE (1 << 2)
-#define PMD_SECT_CACHEABLE (1 << 3)
-#define PMD_SECT_XN (1 << 4) /* v6 */
-#define PMD_SECT_AP_WRITE (1 << 10)
-#define PMD_SECT_AP_READ (1 << 11)
-#define PMD_SECT_TEX(x) ((x) << 12) /* v5 */
-#define PMD_SECT_APX (1 << 15) /* v6 */
-#define PMD_SECT_S (1 << 16) /* v6 */
-#define PMD_SECT_nG (1 << 17) /* v6 */
-#define PMD_SECT_SUPER (1 << 18) /* v6 */
-#define PMD_SECT_AF (0)
+#define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_XN (_AT(pmdval_t, 1) << 4) /* v6 */
+#define PMD_SECT_AP_WRITE (_AT(pmdval_t, 1) << 10)
+#define PMD_SECT_AP_READ (_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_TEX(x) (_AT(pmdval_t, (x)) << 12) /* v5 */
+#define PMD_SECT_APX (_AT(pmdval_t, 1) << 15) /* v6 */
+#define PMD_SECT_S (_AT(pmdval_t, 1) << 16) /* v6 */
+#define PMD_SECT_nG (_AT(pmdval_t, 1) << 17) /* v6 */
+#define PMD_SECT_SUPER (_AT(pmdval_t, 1) << 18) /* v6 */
+#define PMD_SECT_AF (_AT(pmdval_t, 0))
-#define PMD_SECT_UNCACHED (0)
+#define PMD_SECT_UNCACHED (_AT(pmdval_t, 0))
#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE)
#define PMD_SECT_WT (PMD_SECT_CACHEABLE)
#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
@@ -54,38 +54,38 @@
* + Level 2 descriptor (PTE)
* - common
*/
-#define PTE_TYPE_MASK (3 << 0)
-#define PTE_TYPE_FAULT (0 << 0)
-#define PTE_TYPE_LARGE (1 << 0)
-#define PTE_TYPE_SMALL (2 << 0)
-#define PTE_TYPE_EXT (3 << 0) /* v5 */
-#define PTE_BUFFERABLE (1 << 2)
-#define PTE_CACHEABLE (1 << 3)
+#define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0)
+#define PTE_TYPE_LARGE (_AT(pteval_t, 1) << 0)
+#define PTE_TYPE_SMALL (_AT(pteval_t, 2) << 0)
+#define PTE_TYPE_EXT (_AT(pteval_t, 3) << 0) /* v5 */
+#define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2)
+#define PTE_CACHEABLE (_AT(pteval_t, 1) << 3)
/*
* - extended small page/tiny page
*/
-#define PTE_EXT_XN (1 << 0) /* v6 */
-#define PTE_EXT_AP_MASK (3 << 4)
-#define PTE_EXT_AP0 (1 << 4)
-#define PTE_EXT_AP1 (2 << 4)
-#define PTE_EXT_AP_UNO_SRO (0 << 4)
+#define PTE_EXT_XN (_AT(pteval_t, 1) << 0) /* v6 */
+#define PTE_EXT_AP_MASK (_AT(pteval_t, 3) << 4)
+#define PTE_EXT_AP0 (_AT(pteval_t, 1) << 4)
+#define PTE_EXT_AP1 (_AT(pteval_t, 2) << 4)
+#define PTE_EXT_AP_UNO_SRO (_AT(pteval_t, 0) << 4)
#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0)
#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1)
#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0)
-#define PTE_EXT_TEX(x) ((x) << 6) /* v5 */
-#define PTE_EXT_APX (1 << 9) /* v6 */
-#define PTE_EXT_COHERENT (1 << 9) /* XScale3 */
-#define PTE_EXT_SHARED (1 << 10) /* v6 */
-#define PTE_EXT_NG (1 << 11) /* v6 */
+#define PTE_EXT_TEX(x) (_AT(pteval_t, (x)) << 6) /* v5 */
+#define PTE_EXT_APX (_AT(pteval_t, 1) << 9) /* v6 */
+#define PTE_EXT_COHERENT (_AT(pteval_t, 1) << 9) /* XScale3 */
+#define PTE_EXT_SHARED (_AT(pteval_t, 1) << 10) /* v6 */
+#define PTE_EXT_NG (_AT(pteval_t, 1) << 11) /* v6 */
/*
* - small page
*/
-#define PTE_SMALL_AP_MASK (0xff << 4)
-#define PTE_SMALL_AP_UNO_SRO (0x00 << 4)
-#define PTE_SMALL_AP_UNO_SRW (0x55 << 4)
-#define PTE_SMALL_AP_URO_SRW (0xaa << 4)
-#define PTE_SMALL_AP_URW_SRW (0xff << 4)
+#define PTE_SMALL_AP_MASK (_AT(pteval_t, 0xff) << 4)
+#define PTE_SMALL_AP_UNO_SRO (_AT(pteval_t, 0x00) << 4)
+#define PTE_SMALL_AP_UNO_SRW (_AT(pteval_t, 0x55) << 4)
+#define PTE_SMALL_AP_URO_SRW (_AT(pteval_t, 0xaa) << 4)
+#define PTE_SMALL_AP_URW_SRW (_AT(pteval_t, 0xff) << 4)
#endif
diff --git a/arch/arm/include/asm/pgtable-2level-types.h b/arch/arm/include/asm/pgtable-2level-types.h
index 8a01f62..9cb877a 100644
--- a/arch/arm/include/asm/pgtable-2level-types.h
+++ b/arch/arm/include/asm/pgtable-2level-types.h
@@ -19,7 +19,10 @@
#ifndef _ASM_PGTABLE_2LEVEL_TYPES_H
#define _ASM_PGTABLE_2LEVEL_TYPES_H
-typedef unsigned long pteval_t;
+typedef u32 pteval_t;
+typedef u32 pmdval_t;
+typedef u32 pgdval_t;
+typedef u32 pgprotval_t;
#undef STRICT_MM_TYPECHECKS
@@ -28,9 +31,9 @@ typedef unsigned long pteval_t;
* These are used to make use of C type-checking..
*/
typedef struct { pteval_t pte; } pte_t;
-typedef struct { unsigned long pmd; } pmd_t;
-typedef struct { unsigned long pgd[2]; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pgdval_t pgd[2]; } pgd_t;
+typedef struct { pgprotval_t pgprot; } pgprot_t;
#define pte_val(x) ((x).pte)
#define pmd_val(x) ((x).pmd)
@@ -46,9 +49,9 @@ typedef struct { unsigned long pgprot; } pgprot_t;
* .. while these make it easier on the compiler
*/
typedef pteval_t pte_t;
-typedef unsigned long pmd_t;
-typedef unsigned long pgd_t[2];
-typedef unsigned long pgprot_t;
+typedef pmdval_t pmd_t;
+typedef pgdval_t pgd_t[2];
+typedef pgprotval_t pgprot_t;
#define pte_val(x) (x)
#define pmd_val(x) (x)
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index d2005de..2a49568 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -509,7 +509,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
* these operations. This is typically used when we are removing
* PMD entries.
*/
-static inline void flush_pmd_entry(pmd_t *pmd)
+static inline void flush_pmd_entry(void *pmd)
{
const unsigned int __tlb_flag = __cpu_tlb_flags;
@@ -525,7 +525,7 @@ static inline void flush_pmd_entry(pmd_t *pmd)
dsb();
}
-static inline void clean_pmd_entry(pmd_t *pmd)
+static inline void clean_pmd_entry(void *pmd)
{
const unsigned int __tlb_flag = __cpu_tlb_flags;
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index d238410..2b179af 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -17,8 +17,8 @@ static inline pmd_t *pmd_off_k(unsigned long virt)
struct mem_type {
pteval_t prot_pte;
- unsigned int prot_l1;
- unsigned int prot_sect;
+ pgprotval_t prot_l1;
+ pgprotval_t prot_sect;
unsigned int domain;
};
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index a69f8e4..1a80749 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -62,7 +62,7 @@ EXPORT_SYMBOL(pgprot_kernel);
struct cachepolicy {
const char policy[16];
unsigned int cr_mask;
- unsigned int pmd;
+ pmdval_t pmd;
pteval_t pte;
};
@@ -290,7 +290,7 @@ static void __init build_mem_type_table(void)
{
struct cachepolicy *cp;
unsigned int cr = get_cr();
- unsigned int user_pgprot, kern_pgprot, vecs_pgprot;
+ pgprotval_t user_pgprot, kern_pgprot, vecs_pgprot;
int cpu_arch = cpu_architecture();
int i;
With LPAE, the physical address mask is 40-bit while the page table
entry is 64-bit. This patch introduces PHYS_MASK for the 2-level page
table format, defined as ~0UL.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/include/asm/pgtable-2level-hwdef.h | 2 ++
arch/arm/include/asm/pgtable.h | 6 +++---
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index 2b52c40..5cfba15 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -88,4 +88,6 @@
#define PTE_SMALL_AP_URO_SRW (_AT(pteval_t, 0xaa) << 4)
#define PTE_SMALL_AP_URW_SRW (_AT(pteval_t, 0xff) << 4)
+#define PHYS_MASK (~0UL)
+
#endif
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 9618052..8f9e1dd 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -199,10 +199,10 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
{
- return __va(pmd_val(pmd) & PAGE_MASK);
+ return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK);
}
-#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
+#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
/* we don't need complex calculations here as the pmd is folded into the pgd */
#define pmd_addr_end(addr,end) (end)
@@ -223,7 +223,7 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
#define pte_offset_map(pmd,addr) (__pte_map(pmd) + pte_index(addr))
#define pte_unmap(pte) __pte_unmap(pte)
-#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT)
+#define pte_pfn(pte) ((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
#define pfn_pte(pfn,prot) __pte(__pfn_to_phys(pfn) | pgprot_val(prot))
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
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 <[email protected]>
---
arch/arm/include/asm/page.h | 4 +
arch/arm/include/asm/pgtable-3level-hwdef.h | 82 +++++++++++++++++++++
arch/arm/include/asm/pgtable-3level-types.h | 69 ++++++++++++++++++
arch/arm/include/asm/pgtable-3level.h | 102 +++++++++++++++++++++++++++
arch/arm/include/asm/pgtable-hwdef.h | 4 +
arch/arm/include/asm/pgtable.h | 4 +
6 files changed, 265 insertions(+), 0 deletions(-)
create mode 100644 arch/arm/include/asm/pgtable-3level-hwdef.h
create mode 100644 arch/arm/include/asm/pgtable-3level-types.h
create mode 100644 arch/arm/include/asm/pgtable-3level.h
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index ca94653..97b440c 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -151,7 +151,11 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
extern void copy_page(void *to, const void *from);
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-types.h>
+#else
#include <asm/pgtable-2level-types.h>
+#endif
#endif /* CONFIG_MMU */
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
new file mode 100644
index 0000000..7c238a3
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -0,0 +1,82 @@
+/*
+ * arch/arm/include/asm/pgtable-3level-hwdef.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <[email protected]>
+ *
+ * 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_HWDEF_H
+#define _ASM_PGTABLE_3LEVEL_HWDEF_H
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1/2 descriptor
+ * - common
+ */
+#define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0)
+#define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0)
+#define PMD_TYPE_SECT (_AT(pmdval_t, 1) << 0)
+#define PMD_BIT4 (_AT(pmdval_t, 0))
+#define PMD_DOMAIN(x) (_AT(pmdval_t, 0))
+
+/*
+ * - section
+ */
+#define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2)
+#define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3)
+#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)
+#ifdef __ASSEMBLY__
+/* avoid 'shift count out of range' warning */
+#define PMD_SECT_XN (0)
+#else
+#define PMD_SECT_XN ((pmdval_t)1 << 54)
+#endif
+#define PMD_SECT_AP_WRITE (_AT(pmdval_t, 0))
+#define PMD_SECT_AP_READ (_AT(pmdval_t, 0))
+#define PMD_SECT_TEX(x) (_AT(pmdval_t, 0))
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PMD_SECT_UNCACHED (_AT(pmdval_t, 0) << 2) /* strongly ordered */
+#define PMD_SECT_BUFFERED (_AT(pmdval_t, 1) << 2) /* normal non-cacheable */
+#define PMD_SECT_WT (_AT(pmdval_t, 2) << 2) /* normal inner write-through */
+#define PMD_SECT_WB (_AT(pmdval_t, 3) << 2) /* normal inner write-back */
+#define PMD_SECT_WBWA (_AT(pmdval_t, 7) << 2) /* normal inner write-alloc */
+
+/*
+ * + Level 3 descriptor (PTE)
+ */
+#define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0)
+#define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0)
+#define PTE_TYPE_PAGE (_AT(pteval_t, 3) << 0)
+#define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) /* AttrIndx[0] */
+#define PTE_CACHEABLE (_AT(pteval_t, 1) << 3) /* AttrIndx[1] */
+#define PTE_EXT_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */
+#define PTE_EXT_AF (_AT(pteval_t, 1) << 10) /* Access Flag */
+#define PTE_EXT_NG (_AT(pteval_t, 1) << 11) /* nG */
+#define PTE_EXT_XN (_AT(pteval_t, 1) << 54) /* XN */
+
+/*
+ * 40-bit physical address supported.
+ */
+#define PHYS_MASK_SHIFT (40)
+#define PHYS_MASK ((1ULL << PHYS_MASK_SHIFT) - 1)
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-3level-types.h b/arch/arm/include/asm/pgtable-3level-types.h
new file mode 100644
index 0000000..03cd91d
--- /dev/null
+++ b/arch/arm/include/asm/pgtable-3level-types.h
@@ -0,0 +1,69 @@
+/*
+ * arch/arm/include/asm/pgtable-3level-types.h
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <[email protected]>
+ *
+ * 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_TYPES_H
+#define _ASM_PGTABLE_3LEVEL_TYPES_H
+
+typedef u64 pteval_t;
+typedef u64 pmdval_t;
+typedef u64 pgdval_t;
+typedef u64 pgprotval_t;
+
+#undef STRICT_MM_TYPECHECKS
+
+#ifdef STRICT_MM_TYPECHECKS
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef struct { pteval_t pte; } pte_t;
+typedef struct { pmdval_t pmd; } pmd_t;
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pgprotval_t pgprot; } pgprot_t;
+
+#define pte_val(x) ((x).pte)
+#define pmd_val(x) ((x).pmd)
+#define pgd_val(x) ((x).pgd)
+#define pgprot_val(x) ((x).pgprot)
+
+#define __pte(x) ((pte_t) { (x) } )
+#define __pmd(x) ((pmd_t) { (x) } )
+#define __pgd(x) ((pgd_t) { (x) } )
+#define __pgprot(x) ((pgprot_t) { (x) } )
+
+#else /* !STRICT_MM_TYPECHECKS */
+
+typedef pteval_t pte_t;
+typedef pmdval_t pmd_t;
+typedef pgdval_t pgd_t;
+typedef pgprotval_t pgprot_t;
+
+#define pte_val(x) (x)
+#define pmd_val(x) (x)
+#define pgd_val(x) (x)
+#define pgprot_val(x) (x)
+
+#define __pte(x) (x)
+#define __pmd(x) (x)
+#define __pgd(x) (x)
+#define __pgprot(x) (x)
+
+#endif /* STRICT_MM_TYPECHECKS */
+
+#endif /* _ASM_PGTABLE_3LEVEL_TYPES_H */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
new file mode 100644
index 0000000..79bf0ac
--- /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 <[email protected]>
+ *
+ * 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 */
diff --git a/arch/arm/include/asm/pgtable-hwdef.h b/arch/arm/include/asm/pgtable-hwdef.h
index 1831111..8426229 100644
--- a/arch/arm/include/asm/pgtable-hwdef.h
+++ b/arch/arm/include/asm/pgtable-hwdef.h
@@ -10,6 +10,10 @@
#ifndef _ASMARM_PGTABLE_HWDEF_H
#define _ASMARM_PGTABLE_HWDEF_H
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level-hwdef.h>
+#else
#include <asm/pgtable-2level-hwdef.h>
+#endif
#endif
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 8f9e1dd..95fefd9 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -25,7 +25,11 @@
#include <mach/vmalloc.h>
#include <asm/pgtable-hwdef.h>
+#ifdef CONFIG_ARM_LPAE
+#include <asm/pgtable-3level.h>
+#else
#include <asm/pgtable-2level.h>
+#endif
/*
* Just any arbitrary offset to the start of the vmalloc VM area: the
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 <[email protected]>
---
arch/arm/include/asm/pgalloc.h | 24 +++++++++++++
arch/arm/include/asm/pgtable-3level.h | 5 +++
arch/arm/include/asm/pgtable.h | 62 ++++++++++++++++++++++++++++++++-
arch/arm/include/asm/proc-fns.h | 25 +++++++++++++
arch/arm/mm/ioremap.c | 8 +++--
arch/arm/mm/pgd.c | 51 +++++++++++++++++++++++++--
6 files changed, 167 insertions(+), 8 deletions(-)
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 7418894..943504f 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 79bf0ac..a6261f5 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -99,4 +99,9 @@
#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 */
+
#endif /* _ASM_PGTABLE_3LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 95fefd9..1db9ad6 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -165,6 +165,31 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
/* to find an entry in a kernel page-table-directory */
#define pgd_offset_k(addr) pgd_offset(&init_mm, addr)
+#ifdef CONFIG_ARM_LPAE
+
+#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);
+}
+
+#else /* !CONFIG_ARM_LPAE */
+
/*
* The "pud_xxx()" functions here are trivial when the pmd is folded into
* the pud: the pud entry is never bad, always exists, and can't be set or
@@ -176,15 +201,43 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
#define pud_clear(pudp) do { } while (0)
#define set_pud(pud,pudp) do { } while (0)
+#endif /* CONFIG_ARM_LPAE */
/* Find an entry in the second-level page table.. */
+#ifdef CONFIG_ARM_LPAE
+#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);
+}
+#else
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
{
return (pmd_t *)pud;
}
+#endif
#define pmd_none(pmd) (!pmd_val(pmd))
#define pmd_present(pmd) (pmd_val(pmd))
+
+#ifdef CONFIG_ARM_LPAE
+
+#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)
+
+#else /* !CONFIG_ARM_LPAE */
+
#define pmd_bad(pmd) (pmd_val(pmd) & 2)
#define copy_pmd(pmdpd,pmdps) \
@@ -201,6 +254,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
clean_pmd_entry(pmdp); \
} while (0)
+#endif /* CONFIG_ARM_LPAE */
+
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
{
return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK);
@@ -233,9 +288,14 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
#define mk_pte(page,prot) pfn_pte(page_to_pfn(page), prot)
-#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
#define pte_clear(mm,addr,ptep) set_pte_ext(ptep, __pte(0), 0)
+#ifdef CONFIG_ARM_LPAE
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
+#else
+#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+#endif
+
#if __LINUX_ARM_ARCH__ < 6
static inline void __sync_icache_dcache(pte_t pteval)
{
diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h
index 233dccd..3a68cd4 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));
#else
#define cpu_proc_init() processor._proc_init()
@@ -87,7 +95,11 @@ extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
#define cpu_reset(addr) processor.reset(addr)
#define cpu_do_idle() processor._do_idle()
#define cpu_dcache_clean_area(addr,sz) processor.dcache_clean_area(addr,sz)
+#ifdef CONFIG_ARM_LPAE
+#define cpu_set_pte_ext(ptep,pte) processor.set_pte_ext(ptep,pte)
+#else
#define cpu_set_pte_ext(ptep,pte,ext) processor.set_pte_ext(ptep,pte,ext)
+#endif
#define cpu_do_switch_mm(pgd,mm) processor.switch_mm(pgd,mm)
#endif
@@ -113,6 +125,18 @@ extern void cpu_resume(void);
#endif
+#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; \
@@ -121,6 +145,7 @@ 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 ab50627..6bdf42c 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.
@@ -195,11 +195,13 @@ 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+
@@ -221,7 +223,7 @@ 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 &&
@@ -292,7 +294,7 @@ EXPORT_SYMBOL(__arm_ioremap);
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 b2027c1..a3e78cc 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);
}
This patch adds the MMU initialisation for the LPAE page table format.
The swapper_pg_dir size with LPAE is 5 rather than 4 pages. A new
proc-v7lpae.S file contains the initialisation, context switch and
save/restore code for ARMv7 with the LPAE. The TTBRx split is based on
the PAGE_OFFSET with TTBR1 used for the kernel mappings. The 36-bit
mappings (supersections) and a few other memory types in mmu.c are
conditionally compiled.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/kernel/head.S | 117 +++++++++----
arch/arm/mm/Makefile | 4 +
arch/arm/mm/mmu.c | 32 ++++-
arch/arm/mm/proc-macros.S | 5 +-
arch/arm/mm/proc-v7lpae.S | 422 +++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 540 insertions(+), 40 deletions(-)
create mode 100644 arch/arm/mm/proc-v7lpae.S
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index b7101ff..30a817f 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -21,6 +21,7 @@
#include <asm/memory.h>
#include <asm/thread_info.h>
#include <asm/system.h>
+#include <asm/pgtable.h>
#ifdef CONFIG_DEBUG_LL
#include <mach/debug-macro.S>
@@ -38,11 +39,20 @@
#error KERNEL_RAM_VADDR must start at 0xXXXX8000
#endif
+#ifdef CONFIG_ARM_LPAE
+ /* LPAE requires an additional page for the PGD */
+#define PG_DIR_SIZE 0x5000
+#define PMD_ORDER 3
+#else
+#define PG_DIR_SIZE 0x4000
+#define PMD_ORDER 2
+#endif
+
.globl swapper_pg_dir
- .equ swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000
+ .equ swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
.macro pgtbl, rd, phys
- add \rd, \phys, #TEXT_OFFSET - 0x4000
+ add \rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE
.endm
#ifdef CONFIG_XIP_KERNEL
@@ -140,11 +150,11 @@ __create_page_tables:
pgtbl r4, r8 @ page table address
/*
- * Clear the 16K level 1 swapper page table
+ * Clear the swapper page table
*/
mov r0, r4
mov r3, #0
- add r6, r0, #0x4000
+ add r6, r0, #PG_DIR_SIZE
1: str r3, [r0], #4
str r3, [r0], #4
str r3, [r0], #4
@@ -152,6 +162,25 @@ __create_page_tables:
teq r0, r6
bne 1b
+#ifdef CONFIG_ARM_LPAE
+ /*
+ * Build the PGD table (first level) to point to the PMD table. A PGD
+ * entry is 64-bit wide.
+ */
+ mov r0, r4
+ add r3, r4, #0x1000 @ first PMD table address
+ orr r3, r3, #3 @ PGD block type
+ mov r6, #4 @ PTRS_PER_PGD
+ mov r7, #1 << (55 - 32) @ L_PGD_SWAPPER
+1: str r3, [r0], #4 @ set bottom PGD entry bits
+ str r7, [r0], #4 @ set top PGD entry bits
+ add r3, r3, #0x1000 @ next PMD table
+ subs r6, r6, #1
+ bne 1b
+
+ add r4, r4, #0x1000 @ point to the PMD tables
+#endif
+
ldr r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags
/*
@@ -163,30 +192,30 @@ __create_page_tables:
sub r0, r0, r3 @ virt->phys offset
add r5, r5, r0 @ phys __enable_mmu
add r6, r6, r0 @ phys __enable_mmu_end
- mov r5, r5, lsr #20
- mov r6, r6, lsr #20
+ mov r5, r5, lsr #SECTION_SHIFT
+ mov r6, r6, lsr #SECTION_SHIFT
-1: orr r3, r7, r5, lsl #20 @ flags + kernel base
- str r3, [r4, r5, lsl #2] @ identity mapping
- teq r5, r6
- addne r5, r5, #1 @ next section
- bne 1b
+1: orr r3, r7, r5, lsl #SECTION_SHIFT @ flags + kernel base
+ str r3, [r4, r5, lsl #PMD_ORDER] @ identity mapping
+ cmp r5, r6
+ addlo r5, r5, #SECTION_SHIFT >> 20 @ next section
+ blo 1b
/*
* Now setup the pagetables for our kernel direct
* mapped region.
*/
mov r3, pc
- mov r3, r3, lsr #20
- orr r3, r7, r3, lsl #20
- add r0, r4, #(KERNEL_START & 0xff000000) >> 18
- str r3, [r0, #(KERNEL_START & 0x00f00000) >> 18]!
+ mov r3, r3, lsr #SECTION_SHIFT
+ orr r3, r7, r3, lsl #SECTION_SHIFT
+ add r0, r4, #(KERNEL_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+ str r3, [r0, #(KERNEL_START & 0x00e00000) >> (SECTION_SHIFT - PMD_ORDER)]!
ldr r6, =(KERNEL_END - 1)
- add r0, r0, #4
- add r6, r4, r6, lsr #18
+ add r0, r0, #1 << PMD_ORDER
+ add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
1: cmp r0, r6
- add r3, r3, #1 << 20
- strls r3, [r0], #4
+ add r3, r3, #1 << SECTION_SHIFT
+ strls r3, [r0], #1 << PMD_ORDER
bls 1b
#ifdef CONFIG_XIP_KERNEL
@@ -195,11 +224,11 @@ __create_page_tables:
*/
add r3, r8, #TEXT_OFFSET
orr r3, r3, r7
- add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> 18
- str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> 18]!
+ add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+ str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> (SECTION_SHIFT - PMD_ORDER)]!
ldr r6, =(_end - 1)
add r0, r0, #4
- add r6, r4, r6, lsr #18
+ add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
1: cmp r0, r6
add r3, r3, #1 << 20
strls r3, [r0], #4
@@ -207,15 +236,15 @@ __create_page_tables:
#endif
/*
- * Then map boot params address in r2 or
- * the first 1MB of ram if boot params address is not specified.
+ * Then map boot params address in r2 or the first 1MB (2MB with LPAE)
+ * of ram if boot params address is not specified.
*/
- mov r0, r2, lsr #20
- movs r0, r0, lsl #20
+ mov r0, r2, lsr #SECTION_SHIFT
+ movs r0, r0, lsl #SECTION_SHIFT
moveq r0, r8
sub r3, r0, r8
add r3, r3, #PAGE_OFFSET
- add r3, r4, r3, lsr #18
+ add r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
orr r6, r7, r0
str r6, [r3]
@@ -228,21 +257,27 @@ __create_page_tables:
*/
addruart r7, r3
- mov r3, r3, lsr #20
- mov r3, r3, lsl #2
+ mov r3, r3, lsr #SECTION_SHIFT
+ mov r3, r3, lsl #PMD_ORDER
add r0, r4, r3
rsb r3, r3, #0x4000 @ PTRS_PER_PGD*sizeof(long)
cmp r3, #0x0800 @ limit to 512MB
movhi r3, #0x0800
add r6, r0, r3
- mov r3, r7, lsr #20
+ mov r3, r7, lsr #SECTION_SHIFT
ldr r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
- orr r3, r7, r3, lsl #20
+ orr r3, r7, r3, lsl #SECTION_SHIFT
+#ifdef CONFIG_ARM_LPAE
+ mov r7, #1 << (54 - 32) @ XN
+#endif
1: str r3, [r0], #4
- add r3, r3, #1 << 20
- teq r0, r6
- bne 1b
+#ifdef CONFIG_ARM_LPAE
+ str r7, [r0], #4
+#endif
+ add r3, r3, #1 << SECTION_SHIFT
+ cmp r0, r6
+ blo 1b
#else /* CONFIG_DEBUG_ICEDCC */
/* we don't need any serial debugging mappings for ICEDCC */
@@ -254,7 +289,7 @@ __create_page_tables:
* If we're using the NetWinder or CATS, we also need to map
* in the 16550-type serial port for the debug messages
*/
- add r0, r4, #0xff000000 >> 18
+ add r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ORDER)
orr r3, r7, #0x7c000000
str r3, [r0]
#endif
@@ -264,13 +299,16 @@ __create_page_tables:
* Similar reasons here - for debug. This is
* only for Acorn RiscPC architectures.
*/
- add r0, r4, #0x02000000 >> 18
+ add r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ORDER)
orr r3, r7, #0x02000000
str r3, [r0]
- add r0, r4, #0xd8000000 >> 18
+ add r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER)
str r3, [r0]
#endif
#endif
+#ifdef CONFIG_ARM_LPAE
+ sub r4, r4, #0x1000 @ point to the PGD table
+#endif
mov pc, lr
ENDPROC(__create_page_tables)
.ltorg
@@ -362,12 +400,17 @@ __enable_mmu:
#ifdef CONFIG_CPU_ICACHE_DISABLE
bic r0, r0, #CR_I
#endif
+#ifdef CONFIG_ARM_LPAE
+ mov r5, #0
+ mcrr p15, 0, r4, r5, c2 @ load TTBR0
+#else
mov r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
domain_val(DOMAIN_IO, DOMAIN_CLIENT))
mcr p15, 0, r5, c3, c0, 0 @ load domain access register
mcr p15, 0, r4, c2, c0, 0 @ load page table pointer
+#endif
b __turn_mmu_on
ENDPROC(__enable_mmu)
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index bca7e61..48639e7 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -91,7 +91,11 @@ obj-$(CONFIG_CPU_MOHAWK) += proc-mohawk.o
obj-$(CONFIG_CPU_FEROCEON) += proc-feroceon.o
obj-$(CONFIG_CPU_V6) += proc-v6.o
obj-$(CONFIG_CPU_V6K) += proc-v6.o
+ifeq ($(CONFIG_ARM_LPAE),y)
+obj-$(CONFIG_CPU_V7) += proc-v7lpae.o
+else
obj-$(CONFIG_CPU_V7) += proc-v7.o
+endif
AFLAGS_proc-v6.o :=-Wa,-march=armv6
AFLAGS_proc-v7.o :=-Wa,-march=armv7-a
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 1a80749..139beb7 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -152,6 +152,7 @@ static int __init early_nowrite(char *__unused)
}
early_param("nowb", early_nowrite);
+#ifndef CONFIG_ARM_LPAE
static int __init early_ecc(char *p)
{
if (memcmp(p, "on", 2) == 0)
@@ -161,6 +162,7 @@ static int __init early_ecc(char *p)
return 0;
}
early_param("ecc", early_ecc);
+#endif
static int __init noalign_setup(char *__unused)
{
@@ -230,10 +232,12 @@ static struct mem_type mem_types[] = {
.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
.domain = DOMAIN_KERNEL,
},
+#ifndef CONFIG_ARM_LPAE
[MT_MINICLEAN] = {
.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_MINICACHE,
.domain = DOMAIN_KERNEL,
},
+#endif
[MT_LOW_VECTORS] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_RDONLY,
@@ -423,6 +427,7 @@ static void __init build_mem_type_table(void)
* ARMv6 and above have extended page tables.
*/
if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {
+#ifndef CONFIG_ARM_LPAE
/*
* Mark cache clean areas and XIP ROM read only
* from SVC mode and no access from userspace.
@@ -430,6 +435,7 @@ static void __init build_mem_type_table(void)
mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
+#endif
if (is_smp()) {
/*
@@ -468,6 +474,18 @@ static void __init build_mem_type_table(void)
mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE;
}
+#ifdef CONFIG_ARM_LPAE
+ /*
+ * Do not generate access flag faults for the kernel mappings.
+ */
+ for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
+ mem_types[i].prot_pte |= PTE_EXT_AF;
+ mem_types[i].prot_sect |= PMD_SECT_AF;
+ }
+ kern_pgprot |= PTE_EXT_AF;
+ vecs_pgprot |= PTE_EXT_AF;
+#endif
+
for (i = 0; i < 16; i++) {
unsigned long v = pgprot_val(protection_map[i]);
protection_map[i] = __pgprot(v | user_pgprot);
@@ -597,6 +615,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
} while (pud++, addr = next, addr != end);
}
+#ifndef CONFIG_ARM_LPAE
static void __init create_36bit_mapping(struct map_desc *md,
const struct mem_type *type)
{
@@ -656,6 +675,7 @@ static void __init create_36bit_mapping(struct map_desc *md,
pgd += SUPERSECTION_SIZE >> PGDIR_SHIFT;
} while (addr != end);
}
+#endif /* !CONFIG_ARM_LPAE */
/*
* Create the page directory entries and any necessary
@@ -687,6 +707,7 @@ static void __init create_mapping(struct map_desc *md)
type = &mem_types[md->type];
+#ifndef CONFIG_ARM_LPAE
/*
* Catch 36-bit addresses
*/
@@ -694,6 +715,7 @@ static void __init create_mapping(struct map_desc *md)
create_36bit_mapping(md, type);
return;
}
+#endif
addr = md->virtual & PAGE_MASK;
phys = __pfn_to_phys(md->pfn);
@@ -891,6 +913,14 @@ static inline void prepare_page_table(void)
pmd_clear(pmd_off_k(addr));
}
+#ifdef CONFIG_ARM_LPAE
+/* the first page is reserved for pgd */
+#define SWAPPER_PG_DIR_SIZE (PAGE_SIZE + \
+ PTRS_PER_PGD * PTRS_PER_PMD * sizeof(pmd_t))
+#else
+#define SWAPPER_PG_DIR_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
+#endif
+
/*
* Reserve the special regions of memory
*/
@@ -900,7 +930,7 @@ void __init arm_mm_memblock_reserve(void)
* Reserve the page tables. These are already in use,
* and can only be in node 0.
*/
- memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
+ memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE);
#ifdef CONFIG_SA1111
/*
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 34261f9..48b85f6 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -91,8 +91,9 @@
#if L_PTE_SHARED != PTE_EXT_SHARED
#error PTE shared bit mismatch
#endif
-#if (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
- L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED
+#if !defined (CONFIG_ARM_LPAE) && \
+ (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
+ L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED
#error Invalid Linux PTE bit settings
#endif
#endif /* CONFIG_MMU */
diff --git a/arch/arm/mm/proc-v7lpae.S b/arch/arm/mm/proc-v7lpae.S
new file mode 100644
index 0000000..0bee213
--- /dev/null
+++ b/arch/arm/mm/proc-v7lpae.S
@@ -0,0 +1,422 @@
+/*
+ * arch/arm/mm/proc-v7lpae.S
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ * Copyright (C) 2011 ARM Ltd.
+ * Author: Catalin Marinas <[email protected]>
+ * based on arch/arm/mm/proc-v7.S
+ *
+ * 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
+ */
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/asm-offsets.h>
+#include <asm/hwcap.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/pgtable.h>
+
+#include "proc-macros.S"
+
+#define TTB_IRGN_NC (0 << 8)
+#define TTB_IRGN_WBWA (1 << 8)
+#define TTB_IRGN_WT (2 << 8)
+#define TTB_IRGN_WB (3 << 8)
+#define TTB_RGN_NC (0 << 10)
+#define TTB_RGN_OC_WBWA (1 << 10)
+#define TTB_RGN_OC_WT (2 << 10)
+#define TTB_RGN_OC_WB (3 << 10)
+#define TTB_S (3 << 12)
+#define TTB_EAE (1 << 31)
+
+/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
+#define TTB_FLAGS_UP (TTB_IRGN_WB|TTB_RGN_OC_WB)
+#define PMD_FLAGS_UP (PMD_SECT_WB)
+
+/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
+#define TTB_FLAGS_SMP (TTB_IRGN_WBWA|TTB_S|TTB_RGN_OC_WBWA)
+#define PMD_FLAGS_SMP (PMD_SECT_WBWA|PMD_SECT_S)
+
+ENTRY(cpu_v7_proc_init)
+ mov pc, lr
+ENDPROC(cpu_v7_proc_init)
+
+ENTRY(cpu_v7_proc_fin)
+ mrc p15, 0, r0, c1, c0, 0 @ ctrl register
+ bic r0, r0, #0x1000 @ ...i............
+ bic r0, r0, #0x0006 @ .............ca.
+ mcr p15, 0, r0, c1, c0, 0 @ disable caches
+ mov pc, lr
+ENDPROC(cpu_v7_proc_fin)
+
+/*
+ * cpu_v7_reset(loc)
+ *
+ * Perform a soft reset of the system. Put the CPU into the
+ * same state as it would be if it had been reset, and branch
+ * to what would be the reset vector.
+ *
+ * - loc - location to jump to for soft reset
+ */
+ .align 5
+ENTRY(cpu_v7_reset)
+ mov pc, r0
+ENDPROC(cpu_v7_reset)
+
+/*
+ * cpu_v7_do_idle()
+ *
+ * Idle the processor (eg, wait for interrupt).
+ *
+ * IRQs are already disabled.
+ */
+ENTRY(cpu_v7_do_idle)
+ dsb @ WFI may enter a low-power mode
+ wfi
+ mov pc, lr
+ENDPROC(cpu_v7_do_idle)
+
+ENTRY(cpu_v7_dcache_clean_area)
+#ifndef TLB_CAN_READ_FROM_L1_CACHE
+ dcache_line_size r2, r3
+1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry
+ add r0, r0, r2
+ subs r1, r1, r2
+ bhi 1b
+ dsb
+#endif
+ mov pc, lr
+ENDPROC(cpu_v7_dcache_clean_area)
+
+/*
+ * cpu_v7_switch_mm(pgd_phys, tsk)
+ *
+ * Set the translation table base pointer to be pgd_phys
+ *
+ * - pgd_phys - physical address of new TTB
+ *
+ * It is assumed that:
+ * - we are not using split page tables
+ */
+ENTRY(cpu_v7_switch_mm)
+#ifdef CONFIG_MMU
+ ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id
+ mov r2, #0
+ and r3, r1, #0xff
+ mov r3, r3, lsl #(48 - 32) @ ASID
+ mcrr p15, 0, r0, r3, c2 @ set TTB 0
+ isb
+#endif
+ mov pc, lr
+ENDPROC(cpu_v7_switch_mm)
+
+/*
+ * cpu_v7_set_pte_ext(ptep, pte)
+ *
+ * Set a level 2 translation table entry.
+ *
+ * - ptep - pointer to level 2 translation table entry
+ * (hardware version is stored at +2048 bytes)
+ * - pte - PTE value to store
+ * - ext - value for extended PTE bits
+ */
+ENTRY(cpu_v7_set_pte_ext)
+#ifdef CONFIG_MMU
+ tst r2, #L_PTE_PRESENT
+ beq 1f
+ tst r3, #1 << (55 - 32) @ L_PTE_DIRTY
+ orreq r2, #L_PTE_RDONLY
+1: strd r2, r3, [r0]
+ mcr p15, 0, r0, c7, c10, 1 @ flush_pte
+#endif
+ mov pc, lr
+ENDPROC(cpu_v7_set_pte_ext)
+
+cpu_v7_name:
+ .ascii "ARMv7 Processor"
+ .align
+
+ /*
+ * Memory region attributes for LPAE (defined in pgtable-3level.h):
+ *
+ * n = AttrIndx[2:0]
+ *
+ * n MAIR
+ * UNCACHED 000 00000000
+ * BUFFERABLE 001 01000100
+ * DEV_WC 001 01000100
+ * WRITETHROUGH 010 10101010
+ * WRITEBACK 011 11101110
+ * DEV_CACHED 011 11101110
+ * DEV_SHARED 100 00000100
+ * DEV_NONSHARED 100 00000100
+ * unused 101
+ * unused 110
+ * WRITEALLOC 111 11111111
+ */
+.equ MAIR0, 0xeeaa4400 @ MAIR0
+.equ MAIR1, 0xff000004 @ MAIR1
+
+/* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
+.globl cpu_v7_suspend_size
+.equ cpu_v7_suspend_size, 4 * 10
+#ifdef CONFIG_PM_SLEEP
+ENTRY(cpu_v7_do_suspend)
+ stmfd sp!, {r4 - r11, lr}
+ mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID
+ mrc p15, 0, r5, c13, c0, 1 @ Context ID
+ mrc p15, 0, r6, c3, c0, 0 @ Domain ID
+ mrrc p15, 0, r7, r8, c2 @ TTB 0
+ mrrc p15, 1, r2, r3, c2 @ TTB 1
+ mrc p15, 0, r9, c1, c0, 0 @ Control register
+ mrc p15, 0, r10, c1, c0, 1 @ Auxiliary control register
+ mrc p15, 0, r11, c1, c0, 2 @ Co-processor access control
+ stmia r0, {r2 - r11}
+ ldmfd sp!, {r4 - r11, pc}
+ENDPROC(cpu_v7_do_suspend)
+
+ENTRY(cpu_v7_do_resume)
+ mov ip, #0
+ mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs
+ mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache
+ ldmia r0, {r2 - r11}
+ mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID
+ mcr p15, 0, r5, c13, c0, 1 @ Context ID
+ mcr p15, 0, r6, c3, c0, 0 @ Domain ID
+ mcrr p15, 0, r7, r8, c2 @ TTB 0
+ mcrr p15, 1, r2, r3, c2 @ TTB 1
+ mcr p15, 0, ip, c2, c0, 2 @ TTB control register
+ mcr p15, 0, r10, c1, c0, 1 @ Auxiliary control register
+ mcr p15, 0, r11, c1, c0, 2 @ Co-processor access control
+ ldr r4, =MAIR0
+ ldr r5, =MAIR1
+ mcr p15, 0, r4, c10, c2, 0 @ write MAIR0
+ mcr p15, 0, r5, c10, c2, 1 @ write MAIR1
+ isb
+ mov r0, r9 @ control register
+ mov r2, r7, lsr #14 @ get TTB0 base
+ mov r2, r2, lsl #14
+ ldr r3, cpu_resume_l1_flags
+ b cpu_resume_mmu
+ENDPROC(cpu_v7_do_resume)
+cpu_resume_l1_flags:
+ ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP)
+ ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP)
+#else
+#define cpu_v7_do_suspend 0
+#define cpu_v7_do_resume 0
+#endif
+
+ __CPUINIT
+
+/*
+ * __v7_setup
+ *
+ * Initialise TLB, Caches, and MMU state ready to switch the MMU
+ * on. Return in r0 the new CP15 C1 control register setting.
+ *
+ * This should be able to cover all ARMv7 cores with LPAE.
+ *
+ * It is assumed that:
+ * - cache type register is implemented
+ */
+__v7_ca15mp_setup:
+ mov r10, #0
+1:
+#ifdef CONFIG_SMP
+ ALT_SMP(mrc p15, 0, r0, c1, c0, 1)
+ ALT_UP(mov r0, #(1 << 6)) @ fake it for UP
+ tst r0, #(1 << 6) @ SMP/nAMP mode enabled?
+ orreq r0, r0, #(1 << 6) @ Enable SMP/nAMP mode
+ orreq r0, r0, r10 @ Enable CPU-specific SMP bits
+ mcreq p15, 0, r0, c1, c0, 1
+#endif
+__v7_setup:
+ adr r12, __v7_setup_stack @ the local stack
+ stmia r12, {r0-r5, r7, r9, r11, lr}
+ bl v7_flush_dcache_all
+ ldmia r12, {r0-r5, r7, r9, r11, lr}
+
+ mov r10, #0
+ mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate
+ dsb
+#ifdef CONFIG_MMU
+ mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs
+ mov r5, #TTB_EAE
+ ALT_SMP(orr r5, r5, #TTB_FLAGS_SMP)
+ ALT_SMP(orr r5, r5, #TTB_FLAGS_SMP << 16)
+ ALT_UP(orr r5, r5, #TTB_FLAGS_UP)
+ ALT_UP(orr r5, r5, #TTB_FLAGS_UP << 16)
+ mrc p15, 0, r10, c2, c0, 2
+ orr r10, r10, r5
+#if PHYS_OFFSET <= PAGE_OFFSET
+ /*
+ * TTBR0/TTBR1 split (PAGE_OFFSET):
+ * 0x40000000: T0SZ = 2, T1SZ = 0 (not used)
+ * 0x80000000: T0SZ = 0, T1SZ = 1
+ * 0xc0000000: T0SZ = 0, T1SZ = 2
+ *
+ * Only use this feature if PAGE_OFFSET <= PAGE_OFFSET, otherwise
+ * booting secondary CPUs would end up using TTBR1 for the identity
+ * mapping set up in TTBR0.
+ */
+ orr r10, r10, #(((PAGE_OFFSET >> 30) - 1) << 16) @ TTBCR.T1SZ
+#endif
+ mcr p15, 0, r10, c2, c0, 2 @ TTB control register
+ mov r5, #0
+#if defined CONFIG_VMSPLIT_2G
+ /* PAGE_OFFSET == 0x80000000, T1SZ == 1 */
+ add r6, r8, #1 << 4 @ skip two L1 entries
+#elif defined CONFIG_VMSPLIT_3G
+ /* PAGE_OFFSET == 0xc0000000, T1SZ == 2 */
+ add r6, r8, #4096 * (1 + 3) @ only L2 used, skip pgd+3*pmd
+#else
+ mov r6, r8
+#endif
+ mcrr p15, 1, r6, r5, c2 @ load TTBR1
+ ldr r5, =MAIR0
+ ldr r6, =MAIR1
+ mcr p15, 0, r5, c10, c2, 0 @ write MAIR0
+ mcr p15, 0, r6, c10, c2, 1 @ write MAIR1
+#endif
+ adr r5, v7_crval
+ ldmia r5, {r5, r6}
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ orr r6, r6, #1 << 25 @ big-endian page tables
+#endif
+#ifdef CONFIG_SWP_EMULATE
+ orr r5, r5, #(1 << 10) @ set SW bit in "clear"
+ bic r6, r6, #(1 << 10) @ clear it in "mmuset"
+#endif
+ mrc p15, 0, r0, c1, c0, 0 @ read control register
+ bic r0, r0, r5 @ clear bits them
+ orr r0, r0, r6 @ set them
+ THUMB( orr r0, r0, #1 << 30 ) @ Thumb exceptions
+ mov pc, lr @ return to head.S:__ret
+ENDPROC(__v7_setup)
+
+ /* AT
+ * TFR EV X F IHD LR S
+ * .EEE ..EE PUI. .TAT 4RVI ZWRS BLDP WCAM
+ * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
+ * 11 0 110 1 0011 1100 .111 1101 < we want
+ */
+ .type v7_crval, #object
+v7_crval:
+ crval clear=0x0120c302, mmuset=0x30c23c7d, ucset=0x00c01c7c
+
+__v7_setup_stack:
+ .space 4 * 11 @ 11 registers
+
+ __INITDATA
+
+ .type v7_processor_functions, #object
+ENTRY(v7_processor_functions)
+ .word v7_early_abort
+ .word v7_pabort
+ .word cpu_v7_proc_init
+ .word cpu_v7_proc_fin
+ .word cpu_v7_reset
+ .word cpu_v7_do_idle
+ .word cpu_v7_dcache_clean_area
+ .word cpu_v7_switch_mm
+ .word cpu_v7_set_pte_ext
+ .word 0
+ .word 0
+ .word 0
+ .size v7_processor_functions, . - v7_processor_functions
+
+ .section ".rodata"
+
+ .type cpu_arch_name, #object
+cpu_arch_name:
+ .asciz "armv7"
+ .size cpu_arch_name, . - cpu_arch_name
+
+ .type cpu_elf_name, #object
+cpu_elf_name:
+ .asciz "v7"
+ .size cpu_elf_name, . - cpu_elf_name
+ .align
+
+ .section ".proc.info.init", #alloc, #execinstr
+
+ .type __v7_ca15mp_proc_info, #object
+__v7_ca15mp_proc_info:
+ .long 0x410fc0f0 @ Required ID value
+ .long 0xff0ffff0 @ Mask for ID
+ ALT_SMP(.long \
+ PMD_TYPE_SECT | \
+ PMD_SECT_AP_WRITE | \
+ PMD_SECT_AP_READ | \
+ PMD_SECT_AF | \
+ PMD_FLAGS_SMP)
+ ALT_UP(.long \
+ PMD_TYPE_SECT | \
+ PMD_SECT_AP_WRITE | \
+ PMD_SECT_AP_READ | \
+ PMD_SECT_AF | \
+ PMD_FLAGS_UP)
+ /* PMD_SECT_XN is set explicitly in head.S for LPAE */
+ .long PMD_TYPE_SECT | \
+ PMD_SECT_XN | \
+ PMD_SECT_AP_WRITE | \
+ PMD_SECT_AP_READ | \
+ PMD_SECT_AF
+ b __v7_ca15mp_setup
+ .long cpu_arch_name
+ .long cpu_elf_name
+ .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
+ .long cpu_v7_name
+ .long v7_processor_functions
+ .long v7wbi_tlb_fns
+ .long v6_user_fns
+ .long v7_cache_fns
+ .size __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
+
+ /*
+ * Match any ARMv7 processor core.
+ */
+ .type __v7_proc_info, #object
+__v7_proc_info:
+ .long 0x000f0000 @ Required ID value
+ .long 0x000f0000 @ Mask for ID
+ ALT_SMP(.long \
+ PMD_TYPE_SECT | \
+ PMD_SECT_AP_WRITE | \
+ PMD_SECT_AP_READ | \
+ PMD_SECT_AF | \
+ PMD_FLAGS_SMP)
+ ALT_UP(.long \
+ PMD_TYPE_SECT | \
+ PMD_SECT_AP_WRITE | \
+ PMD_SECT_AP_READ | \
+ PMD_SECT_AF | \
+ PMD_FLAGS_UP)
+ /* PMD_SECT_XN is set explicitly in head.S for LPAE */
+ .long PMD_TYPE_SECT | \
+ PMD_SECT_XN | \
+ PMD_SECT_AP_WRITE | \
+ PMD_SECT_AP_READ | \
+ PMD_SECT_AF
+ W(b) __v7_setup
+ .long cpu_arch_name
+ .long cpu_elf_name
+ .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
+ .long cpu_v7_name
+ .long v7_processor_functions
+ .long v7wbi_tlb_fns
+ .long v6_user_fns
+ .long v7_cache_fns
+ .size __v7_proc_info, . - __v7_proc_info
Similar to the PTE freeing, this patch introduced __pmd_free_tlb() which
invalidates the TLB before freeing a PMD page. This is needed because on
newer processors the entry in the upper page table may be cached by the
TLB and point to random data after the PMD has been freed.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/include/asm/tlb.h | 11 ++++++++++-
1 files changed, 10 insertions(+), 1 deletions(-)
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index f9f6ecd..033ba0d 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -181,8 +181,17 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
tlb_remove_page(tlb, pte);
}
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
+ unsigned long addr)
+{
+#ifdef CONFIG_ARM_LPAE
+ tlb_add_flush(tlb, addr);
+ tlb_remove_page(tlb, virt_to_page(pmdp));
+#endif
+}
+
#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, pmdp)
+#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)
#define tlb_migrate_finish(mm) do { } while (0)
The DFSR and IFSR register format is different when LPAE is enabled. In
addition, DFSR and IFSR have the similar definitions for the fault type.
This modifies modifies the fault code to correctly handle the new
format.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/mm/alignment.c | 8 ++++-
arch/arm/mm/fault.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 87 insertions(+), 1 deletions(-)
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 724ba3b..bc98a6e 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -906,6 +906,12 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
return 0;
}
+#ifdef CONFIG_ARM_LPAE
+#define ALIGNMENT_FAULT 33
+#else
+#define ALIGNMENT_FAULT 1
+#endif
+
/*
* This needs to be done after sysctl_init, otherwise sys/ will be
* overwritten. Actually, this shouldn't be in sys/ at all since
@@ -939,7 +945,7 @@ static int __init alignment_init(void)
ai_usermode = UM_FIXUP;
}
- hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,
+ hook_fault_code(ALIGNMENT_FAULT, do_alignment, SIGBUS, BUS_ADRALN,
"alignment exception");
/*
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index ee76923..e06918b 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -33,10 +33,15 @@
#define FSR_WRITE (1 << 11)
#define FSR_FS4 (1 << 10)
#define FSR_FS3_0 (15)
+#define FSR_FS5_0 (0x3f)
static inline int fsr_fs(unsigned int fsr)
{
+#ifdef CONFIG_ARM_LPAE
+ return fsr & FSR_FS5_0;
+#else
return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
+#endif
}
#ifdef CONFIG_MMU
@@ -122,8 +127,10 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
pte = pte_offset_map(pmd, addr);
printk(", *pte=%08llx", (long long)pte_val(*pte));
+#ifndef CONFIG_ARM_LPAE
printk(", *ppte=%08llx",
(long long)pte_val(pte[PTE_HWTABLE_PTRS]));
+#endif
pte_unmap(pte);
} while(0);
@@ -490,6 +497,72 @@ static struct fsr_info {
int code;
const char *name;
} fsr_info[] = {
+#ifdef CONFIG_ARM_LPAE
+ { do_bad, SIGBUS, 0, "unknown 0" },
+ { do_bad, SIGBUS, 0, "unknown 1" },
+ { do_bad, SIGBUS, 0, "unknown 2" },
+ { do_bad, SIGBUS, 0, "unknown 3" },
+ { do_bad, SIGBUS, 0, "reserved translation fault" },
+ { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" },
+ { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
+ { 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 3 access flag fault" },
+ { do_bad, SIGBUS, 0, "reserved permission fault" },
+ { do_bad, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
+ { do_sect_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
+ { do_bad, SIGBUS, 0, "synchronous external abort" },
+ { do_bad, SIGBUS, 0, "asynchronous external abort" },
+ { do_bad, SIGBUS, 0, "unknown 18" },
+ { do_bad, SIGBUS, 0, "unknown 19" },
+ { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
+ { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
+ { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
+ { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
+ { do_bad, SIGBUS, 0, "synchronous parity error" },
+ { do_bad, SIGBUS, 0, "asynchronous parity error" },
+ { do_bad, SIGBUS, 0, "unknown 26" },
+ { do_bad, SIGBUS, 0, "unknown 27" },
+ { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" },
+ { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" },
+ { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" },
+ { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" },
+ { do_bad, SIGBUS, 0, "unknown 32" },
+ { do_bad, SIGBUS, BUS_ADRALN, "alignment fault" },
+ { do_bad, SIGBUS, 0, "debug event" },
+ { do_bad, SIGBUS, 0, "unknown 35" },
+ { do_bad, SIGBUS, 0, "unknown 36" },
+ { do_bad, SIGBUS, 0, "unknown 37" },
+ { do_bad, SIGBUS, 0, "unknown 38" },
+ { do_bad, SIGBUS, 0, "unknown 39" },
+ { do_bad, SIGBUS, 0, "unknown 40" },
+ { do_bad, SIGBUS, 0, "unknown 41" },
+ { do_bad, SIGBUS, 0, "unknown 42" },
+ { do_bad, SIGBUS, 0, "unknown 43" },
+ { do_bad, SIGBUS, 0, "unknown 44" },
+ { do_bad, SIGBUS, 0, "unknown 45" },
+ { do_bad, SIGBUS, 0, "unknown 46" },
+ { do_bad, SIGBUS, 0, "unknown 47" },
+ { do_bad, SIGBUS, 0, "unknown 48" },
+ { do_bad, SIGBUS, 0, "unknown 49" },
+ { do_bad, SIGBUS, 0, "unknown 50" },
+ { do_bad, SIGBUS, 0, "unknown 51" },
+ { do_bad, SIGBUS, 0, "implementation fault (lockdown abort)" },
+ { do_bad, SIGBUS, 0, "unknown 53" },
+ { do_bad, SIGBUS, 0, "unknown 54" },
+ { do_bad, SIGBUS, 0, "unknown 55" },
+ { do_bad, SIGBUS, 0, "unknown 56" },
+ { do_bad, SIGBUS, 0, "unknown 57" },
+ { do_bad, SIGBUS, 0, "implementation fault (coprocessor abort)" },
+ { do_bad, SIGBUS, 0, "unknown 59" },
+ { do_bad, SIGBUS, 0, "unknown 60" },
+ { do_bad, SIGBUS, 0, "unknown 61" },
+ { do_bad, SIGBUS, 0, "unknown 62" },
+ { do_bad, SIGBUS, 0, "unknown 63" },
+#else /* !CONFIG_ARM_LPAE */
/*
* The following are the standard ARMv3 and ARMv4 aborts. ARMv5
* defines these to be "precise" aborts.
@@ -531,6 +604,7 @@ static struct fsr_info {
{ do_bad, SIGBUS, 0, "unknown 29" },
{ do_bad, SIGBUS, 0, "unknown 30" },
{ do_bad, SIGBUS, 0, "unknown 31" }
+#endif /* CONFIG_ARM_LPAE */
};
void __init
@@ -569,6 +643,9 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
}
+#ifdef CONFIG_ARM_LPAE
+#define ifsr_info fsr_info
+#else /* !CONFIG_ARM_LPAE */
static struct fsr_info ifsr_info[] = {
{ do_bad, SIGBUS, 0, "unknown 0" },
{ do_bad, SIGBUS, 0, "unknown 1" },
@@ -603,6 +680,7 @@ static struct fsr_info ifsr_info[] = {
{ do_bad, SIGBUS, 0, "unknown 30" },
{ do_bad, SIGBUS, 0, "unknown 31" },
};
+#endif /* CONFIG_ARM_LPAE */
void __init
hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
@@ -638,6 +716,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
static int __init exceptions_init(void)
{
+#ifndef CONFIG_ARM_LPAE
if (cpu_architecture() >= CPU_ARCH_ARMv6) {
hook_fault_code(4, do_translation_fault, SIGSEGV, SEGV_MAPERR,
"I-cache maintenance fault");
@@ -653,6 +732,7 @@ static int __init exceptions_init(void)
hook_fault_code(6, do_bad, SIGSEGV, SEGV_MAPERR,
"section access flag fault");
}
+#endif
return 0;
}
With LPAE, TTBRx registers are 64-bit. The ASID is stored in TTBR0
rather than a separate Context ID register. This patch makes the
necessary changes to handle context switching on LPAE.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/mm/context.c | 34 +++++++++++++++++++++++++++++-----
1 files changed, 29 insertions(+), 5 deletions(-)
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 2352395..2dff1cf 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -22,6 +22,34 @@ unsigned int cpu_last_asid = ASID_FIRST_VERSION;
DEFINE_PER_CPU(struct mm_struct *, current_mm);
#endif
+#ifdef CONFIG_ARM_LPAE
+static void cpu_set_reserved_ttbr0(void)
+{
+ unsigned long ttbl = __pa(swapper_pg_dir);
+ unsigned long ttbh = 0;
+
+ /*
+ * Set TTBR0 to swapper_pg_dir. Note that swapper_pg_dir only contains
+ * global entries so the ASID value is not relevant.
+ */
+ asm(
+ " mcrr p15, 0, %0, %1, c2 @ set TTBR0\n"
+ :
+ : "r" (ttbl), "r" (ttbh));
+}
+#else
+static void cpu_set_reserved_ttbr0(void)
+{
+ u32 ttb;
+
+ /* Copy TTBR1 into TTBR0 */
+ asm volatile(
+ " mrc p15, 0, %0, c2, c0, 1 @ read TTBR1\n"
+ " mcr p15, 0, %0, c2, c0, 0 @ set TTBR0\n"
+ : "=r" (ttb));
+}
+#endif
+
/*
* We fork()ed a process, and we need a new context for the child
* to run in.
@@ -34,11 +62,7 @@ void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
static void flush_context(void)
{
- u32 ttb;
- /* Copy TTBR1 into TTBR0 */
- asm volatile("mrc p15, 0, %0, c2, c0, 1\n"
- "mcr p15, 0, %0, c2, c0, 0"
- : "=r" (ttb));
+ cpu_set_reserved_ttbr0();
isb();
local_flush_tlb_all();
if (icache_is_vivt_asid_tagged()) {
With LPAE, the pgd is a separate page table with entries pointing to the
pmd. The identity_mapping_add() function needs to ensure that the pgd is
populated before populating the pmd level. The do..while blocks now loop
over the pmd in order to have the same implementation for the two page
table formats. The pmd_addr_end() definition has been removed and the
generic one used instead. The pmd clean-up is done in the pgd_free()
function.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/include/asm/pgtable.h | 4 ----
arch/arm/mm/idmap.c | 36 ++++++++++++++++++++++++++++++++++--
2 files changed, 34 insertions(+), 6 deletions(-)
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 1db9ad6..9645e52 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -263,10 +263,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
-/* we don't need complex calculations here as the pmd is folded into the pgd */
-#define pmd_addr_end(addr,end) (end)
-
-
#ifndef CONFIG_HIGHPTE
#define __pte_map(pmd) pmd_page_vaddr(*(pmd))
#define __pte_unmap(pte) do { } while (0)
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 2be9139..24e0655 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -1,9 +1,36 @@
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/kernel.h>
#include <asm/cputype.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
+#ifdef CONFIG_ARM_LPAE
+static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
+ unsigned long prot)
+{
+ pmd_t *pmd;
+ unsigned long next;
+
+ if (pud_none_or_clear_bad(pud) || (pud_val(*pud) & L_PGD_SWAPPER)) {
+ pmd = pmd_alloc_one(NULL, addr);
+ if (!pmd) {
+ pr_warning("Failed to allocate identity pmd.\n");
+ return;
+ }
+ pud_populate(NULL, pud, pmd);
+ pmd += pmd_index(addr);
+ } else
+ pmd = pmd_offset(pud, addr);
+
+ do {
+ next = pmd_addr_end(addr, end);
+ *pmd = __pmd((addr & PMD_MASK) | prot);
+ flush_pmd_entry(pmd);
+ } while (pmd++, addr = next, addr != end);
+}
+#else /* !CONFIG_ARM_LPAE */
static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
unsigned long prot)
{
@@ -15,6 +42,7 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
pmd[1] = __pmd(addr);
flush_pmd_entry(pmd);
}
+#endif /* CONFIG_ARM_LPAE */
static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
unsigned long prot)
@@ -32,7 +60,7 @@ void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
{
unsigned long prot, next;
- prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE;
+ prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF;
if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale())
prot |= PMD_BIT4;
@@ -46,7 +74,11 @@ void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
#ifdef CONFIG_SMP
static void idmap_del_pmd(pud_t *pud, unsigned long addr, unsigned long end)
{
- pmd_t *pmd = pmd_offset(pud, addr);
+ pmd_t *pmd;
+
+ if (pud_none_or_clear_bad(pud))
+ return;
+ pmd = pmd_offset(pud, addr);
pmd_clear(pmd);
}
From: Will Deacon <[email protected]>
This patch uses the types.h implementation in asm-generic to define the
dma_addr_t type as the same width as phys_addr_t.
NOTE: this is a temporary patch until the corresponding patches unifying
the dma_addr_t and removing the dma64_addr_t are merged into mainline.
Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/include/asm/types.h | 11 +----------
1 files changed, 1 insertions(+), 10 deletions(-)
diff --git a/arch/arm/include/asm/types.h b/arch/arm/include/asm/types.h
index 48192ac..dc1bdbb 100644
--- a/arch/arm/include/asm/types.h
+++ b/arch/arm/include/asm/types.h
@@ -1,17 +1,8 @@
#ifndef __ASM_ARM_TYPES_H
#define __ASM_ARM_TYPES_H
-#include <asm-generic/int-ll64.h>
+#include <asm-generic/types.h>
-#ifndef __ASSEMBLY__
-
-typedef unsigned short umode_t;
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
#ifdef __KERNEL__
#define BITS_PER_LONG 32
From: Will Deacon <[email protected]>
Memory banks living outside of the 32-bit physical address
space do not have a 1:1 pa <-> va mapping and therefore the
__va macro may wrap.
This patch ensures that such banks are marked as highmem so
that the Kernel doesn't try to split them up when it sees that
the wrapped virtual address overlaps the vmalloc space.
Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/mm/mmu.c | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 139beb7..749475e 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -792,7 +792,8 @@ static void __init sanity_check_meminfo(void)
*bank = meminfo.bank[i];
#ifdef CONFIG_HIGHMEM
- if (__va(bank->start) >= vmalloc_min ||
+ if (bank->start > ULONG_MAX ||
+ __va(bank->start) >= vmalloc_min ||
__va(bank->start) < (void *)PAGE_OFFSET)
highmem = 1;
@@ -802,7 +803,7 @@ static void __init sanity_check_meminfo(void)
* Split those memory banks which are partially overlapping
* the vmalloc area greatly simplifying things later.
*/
- if (__va(bank->start) < vmalloc_min &&
+ if (!highmem && __va(bank->start) < vmalloc_min &&
bank->size > vmalloc_min - __va(bank->start)) {
if (meminfo.nr_banks >= NR_BANKS) {
printk(KERN_CRIT "NR_BANKS too low, "
From: Will Deacon <[email protected]>
LPAE provides support for memory banks with physical addresses of up
to 40 bits.
This patch adds a new atag, ATAG_MEM64, so that the Kernel can be
informed about memory that exists above the 4GB boundary.
Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/include/asm/setup.h | 10 +++++++++-
arch/arm/kernel/compat.c | 4 ++--
arch/arm/kernel/setup.c | 12 +++++++++++-
3 files changed, 22 insertions(+), 4 deletions(-)
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 95176af..5e3587c 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -43,6 +43,13 @@ struct tag_mem32 {
__u32 start; /* physical start address */
};
+#define ATAG_MEM64 0x54420002
+
+struct tag_mem64 {
+ __u64 size;
+ __u64 start; /* physical start address */
+};
+
/* VGA text type displays */
#define ATAG_VIDEOTEXT 0x54410003
@@ -147,7 +154,8 @@ struct tag {
struct tag_header hdr;
union {
struct tag_core core;
- struct tag_mem32 mem;
+ struct tag_mem32 mem32;
+ struct tag_mem64 mem64;
struct tag_videotext videotext;
struct tag_ramdisk ramdisk;
struct tag_initrd initrd;
diff --git a/arch/arm/kernel/compat.c b/arch/arm/kernel/compat.c
index 9256523..f224d95 100644
--- a/arch/arm/kernel/compat.c
+++ b/arch/arm/kernel/compat.c
@@ -86,8 +86,8 @@ static struct tag * __init memtag(struct tag *tag, unsigned long start, unsigned
tag = tag_next(tag);
tag->hdr.tag = ATAG_MEM;
tag->hdr.size = tag_size(tag_mem32);
- tag->u.mem.size = size;
- tag->u.mem.start = start;
+ tag->u.mem32.size = size;
+ tag->u.mem32.start = start;
return tag;
}
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 006c1e8..4158e4d 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -611,11 +611,21 @@ __tagtable(ATAG_CORE, parse_tag_core);
static int __init parse_tag_mem32(const struct tag *tag)
{
- return arm_add_memory(tag->u.mem.start, tag->u.mem.size);
+ return arm_add_memory(tag->u.mem32.start, tag->u.mem32.size);
}
__tagtable(ATAG_MEM, parse_tag_mem32);
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+static int __init parse_tag_mem64(const struct tag *tag)
+{
+ /* We only use 32-bits for the size. */
+ return arm_add_memory(tag->u.mem64.start, (unsigned long)tag->u.mem64.size);
+}
+
+__tagtable(ATAG_MEM64, parse_tag_mem64);
+#endif /* CONFIG_PHYS_ADDR_T_64BIT */
+
#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE)
struct screen_info screen_info = {
.orig_video_lines = 30,
This patch adds the ARM_LPAE and ARCH_PHYS_ADDR_T_64BIT Kconfig entries
allowing LPAE support to be compiled into the kernel.
Signed-off-by: Catalin Marinas <[email protected]>
---
arch/arm/Kconfig | 2 +-
arch/arm/mm/Kconfig | 13 +++++++++++++
2 files changed, 14 insertions(+), 1 deletions(-)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e18c2c2..c7b01b0 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1774,7 +1774,7 @@ config CMDLINE_FORCE
config XIP_KERNEL
bool "Kernel Execute-In-Place from ROM"
- depends on !ZBOOT_ROM
+ depends on !ZBOOT_ROM && !ARM_LPAE
help
Execute-In-Place allows the kernel to run from non-volatile storage
directly addressable by the CPU, such as NOR flash. This saves RAM
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 490c231..afb5231 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -629,6 +629,19 @@ config IO_36
comment "Processor Features"
+config ARM_LPAE
+ bool "Support for the Large Physical Address Extension"
+ depends on MMU && CPU_V7
+ help
+ Say Y if you have an ARMv7 processor supporting the LPAE page table
+ format and you would like to access memory beyond the 4GB limit.
+
+config ARCH_PHYS_ADDR_T_64BIT
+ def_bool ARM_LPAE
+
+config ARCH_DMA_ADDR_T_64BIT
+ def_bool ARM_LPAE
+
config ARM_THUMB
bool "Support Thumb user binaries"
depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
On Tue, May 24 2011, Catalin Marinas wrote:
> This set of patches adds support for the Large Physical Extensions on
> the ARM architecture (available with the Cortex-A15 processor). LPAE
> comes with a 3-level page table format (compared to 2-level for the
> classic one), allowing up to 40-bit physical address space.
Do you expect non LPAE targets to be able to boot with these changes
applied (and LPAE enabled)? I am able to build this tree for the
MSM8660 (with a minor patch below), but it fails to boot with LPAE
enabled. It seems to work fine with LPAE not enabled.
I did have to fix the msm timer code to get the branch you mentioned to
compile. The return type of the function changed back to 'void' without
changing the returns:
---
arch/arm/mach-msm/timer.c | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 50cc0bc..6e659e4 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -268,7 +268,7 @@ static void __cpuinit msm_local_timer_setup(struct clock_event_device *evt)
/* Use existing clock_event for cpu 0 */
if (!smp_processor_id())
- return 0;
+ return;
writel(DGT_CLK_CTL_DIV_4, MSM_TMR_BASE + DGT_CLK_CTL);
@@ -296,7 +296,8 @@ static void __cpuinit msm_local_timer_setup(struct clock_event_device *evt)
if (res) {
pr_err("local_timer_setup: request_irq failed for %s\n",
clock->clockevent.name);
- return res;
+ /* TODO: How to handle this error. */
+ return;
}
clockevents_register_device(evt);
--
Sent by an employee of the Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum.
On Tue, 24 May 2011, David Brown wrote:
> On Tue, May 24 2011, Catalin Marinas wrote:
>
> > This set of patches adds support for the Large Physical Extensions on
> > the ARM architecture (available with the Cortex-A15 processor). LPAE
> > comes with a 3-level page table format (compared to 2-level for the
> > classic one), allowing up to 40-bit physical address space.
>
> Do you expect non LPAE targets to be able to boot with these changes
> applied (and LPAE enabled)? I am able to build this tree for the
> MSM8660 (with a minor patch below), but it fails to boot with LPAE
> enabled. It seems to work fine with LPAE not enabled.
I wouldn't expect a LPAE kernel to boot on non LPAE capable hardware.
And I don't think we'll ever try to support both LPAE and non-LPAE modes
in the same kernel binary either since this has implications all over
the place in core kernel mm code.
Nicolas
On Wed, 2011-05-25 at 00:56 +0100, David Brown wrote:
> On Tue, May 24 2011, Catalin Marinas wrote:
>
> > This set of patches adds support for the Large Physical Extensions on
> > the ARM architecture (available with the Cortex-A15 processor). LPAE
> > comes with a 3-level page table format (compared to 2-level for the
> > classic one), allowing up to 40-bit physical address space.
>
> Do you expect non LPAE targets to be able to boot with these changes
> applied (and LPAE enabled)? I am able to build this tree for the
> MSM8660 (with a minor patch below), but it fails to boot with LPAE
> enabled. It seems to work fine with LPAE not enabled.
As Nicolas replied already, we can't run an LPAE kernel on non-LPAE
hardware. We could add some checks in head.S and branch to __error_p but
it only works if you have CONFIG_DEBUG_LL enabled.
> I did have to fix the msm timer code to get the branch you mentioned to
> compile. The return type of the function changed back to 'void' without
> changing the returns:
I cc'ed Marc since he's maintaining the timer patches.
> ---
> arch/arm/mach-msm/timer.c | 5 +++--
> 1 files changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
> index 50cc0bc..6e659e4 100644
> --- a/arch/arm/mach-msm/timer.c
> +++ b/arch/arm/mach-msm/timer.c
> @@ -268,7 +268,7 @@ static void __cpuinit msm_local_timer_setup(struct clock_event_device *evt)
>
> /* Use existing clock_event for cpu 0 */
> if (!smp_processor_id())
> - return 0;
> + return;
>
> writel(DGT_CLK_CTL_DIV_4, MSM_TMR_BASE + DGT_CLK_CTL);
>
> @@ -296,7 +296,8 @@ static void __cpuinit msm_local_timer_setup(struct clock_event_device *evt)
> if (res) {
> pr_err("local_timer_setup: request_irq failed for %s\n",
> clock->clockevent.name);
> - return res;
> + /* TODO: How to handle this error. */
> + return;
> }
>
> clockevents_register_device(evt);
Thanks.
--
Catalin
On Wednesday 25 May 2011, Nicolas Pitre wrote:
> > Do you expect non LPAE targets to be able to boot with these changes
> > applied (and LPAE enabled)? I am able to build this tree for the
> > MSM8660 (with a minor patch below), but it fails to boot with LPAE
> > enabled. It seems to work fine with LPAE not enabled.
>
> I wouldn't expect a LPAE kernel to boot on non LPAE capable hardware.
>
> And I don't think we'll ever try to support both LPAE and non-LPAE modes
> in the same kernel binary either since this has implications all over
> the place in core kernel mm code.
Just for information and to complete the picture, what other of these
combinations are possible?
* Non-LPAE kernel on LPAE-capable hardware
* LPAE kernel as KVM guest of LPAE kernel
* non-LPAE kernel as KVM guest of LPAE kernel
* LPAE kernel as KVM guest of non-LPAE kernel
* non-LPAE kernel as KVM guest of non-LPAE kernel on LPAE-enabled hardware
Arnd
On Wed, 2011-05-25 at 12:10 +0100, Arnd Bergmann wrote:
> On Wednesday 25 May 2011, Nicolas Pitre wrote:
> > > Do you expect non LPAE targets to be able to boot with these changes
> > > applied (and LPAE enabled)? I am able to build this tree for the
> > > MSM8660 (with a minor patch below), but it fails to boot with LPAE
> > > enabled. It seems to work fine with LPAE not enabled.
> >
> > I wouldn't expect a LPAE kernel to boot on non LPAE capable hardware.
> >
> > And I don't think we'll ever try to support both LPAE and non-LPAE modes
> > in the same kernel binary either since this has implications all over
> > the place in core kernel mm code.
>
> Just for information and to complete the picture, what other of these
> combinations are possible?
>
> * Non-LPAE kernel on LPAE-capable hardware
Works fine. The LPAE-capable processors like A15 support the classic
page table format as well, it's only a configuration bit to switch to
LPAE.
> * LPAE kernel as KVM guest of LPAE kernel
Should work when KVM for A15 becomes available
> * non-LPAE kernel as KVM guest of LPAE kernel
Same as above. KVM shouldn't care much about the underlying OS, it just
sets up the IPA (Intermediate Physical Address) translations and you can
have classic page tables on top.
> * LPAE kernel as KVM guest of non-LPAE kernel
No. KMV without LPAE uses a shadow page tables mechanism and I'm not
aware of any plans to make it (guest) LPAE-aware.
> * non-LPAE kernel as KVM guest of non-LPAE kernel on LPAE-enabled
> hardware
Would work as the current KVM implementation for ARMv7 with classic page
tables (but I don't know what the status it).
--
Catalin
On 25 May 2011 12:22, Catalin Marinas <[email protected]> wrote:
> On Wed, 2011-05-25 at 12:10 +0100, Arnd Bergmann wrote:
>> On Wednesday 25 May 2011, Nicolas Pitre wrote:
>> > > Do you expect non LPAE targets to be able to boot with these changes
>> > > applied (and LPAE enabled)? ?I am able to build this tree for the
>> > > MSM8660 (with a minor patch below), but it fails to boot with LPAE
>> > > enabled. ?It seems to work fine with LPAE not enabled.
>> >
>> > I wouldn't expect a LPAE kernel to boot on non LPAE capable hardware.
>> >
>> > And I don't think we'll ever try to support both LPAE and non-LPAE modes
>> > in the same kernel binary either since this has implications all over
>> > the place in core kernel mm code.
>>
>> Just for information and to complete the picture, what other of these
>> combinations are possible?
>>
>> * Non-LPAE kernel on LPAE-capable hardware
>
> Works fine. The LPAE-capable processors like A15 support the classic
> page table format as well, it's only a configuration bit to switch to
> LPAE.
>
>> * LPAE kernel as KVM guest of LPAE kernel
>
> Should work when KVM for A15 becomes available
>
>> * non-LPAE kernel as KVM guest of LPAE kernel
>
> Same as above. KVM shouldn't care much about the underlying OS, it just
> sets up the IPA (Intermediate Physical Address) translations and you can
> have classic page tables on top.
Just a clarification here - KVM with support for LPAE also requires
the virtualisation extensions (which are present in Cortex-A15). The
virtualisation extensions require LPAE in hardware but I'm not sure
the opposite is true.
--
Catalin