linux/arch/arm64/include/asm/pgtable-hwdef.h

326 lines
11 KiB
C
Raw Normal View History

/*
* Copyright (C) 2012 ARM Ltd.
*
* 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, see <http://www.gnu.org/licenses/>.
*/
#ifndef __ASM_PGTABLE_HWDEF_H
#define __ASM_PGTABLE_HWDEF_H
#include <asm/memory.h>
/*
* Number of page-table levels required to address 'va_bits' wide
* address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
* bits with (PAGE_SHIFT - 3) bits at each page table level. Hence:
*
* levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), (PAGE_SHIFT - 3))
*
* where DIV_ROUND_UP(n, d) => (((n) + (d) - 1) / (d))
*
* We cannot include linux/kernel.h which defines DIV_ROUND_UP here
* due to build issues. So we open code DIV_ROUND_UP here:
*
* ((((va_bits) - PAGE_SHIFT) + (PAGE_SHIFT - 3) - 1) / (PAGE_SHIFT - 3))
*
* which gets simplified as :
*/
#define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3))
/*
* Size mapped by an entry at level n ( 0 <= n <= 3)
* We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
* in the final page. The maximum number of translation levels supported by
* the architecture is 4. Hence, starting at at level n, we have further
* ((4 - n) - 1) levels of translation excluding the offset within the page.
* So, the total number of bits mapped by an entry at level n is :
*
* ((4 - n) - 1) * (PAGE_SHIFT - 3) + PAGE_SHIFT
*
* Rearranging it a bit we get :
* (4 - n) * (PAGE_SHIFT - 3) + 3
*/
#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n) ((PAGE_SHIFT - 3) * (4 - (n)) + 3)
#define PTRS_PER_PTE (1 << (PAGE_SHIFT - 3))
/*
* PMD_SHIFT determines the size a level 2 page table entry can map.
*/
#if CONFIG_PGTABLE_LEVELS > 2
#define PMD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT)
#define PMD_MASK (~(PMD_SIZE-1))
#define PTRS_PER_PMD PTRS_PER_PTE
#endif
/*
* PUD_SHIFT determines the size a level 1 page table entry can map.
*/
#if CONFIG_PGTABLE_LEVELS > 3
#define PUD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
#define PUD_SIZE (_AC(1, UL) << PUD_SHIFT)
#define PUD_MASK (~(PUD_SIZE-1))
#define PTRS_PER_PUD PTRS_PER_PTE
#endif
/*
* PGDIR_SHIFT determines the size a top-level page table entry can map
* (depending on the configuration, this level can be 0, 1 or 2).
*/
#define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS)
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE-1))
#define PTRS_PER_PGD (1 << (MAX_USER_VA_BITS - PGDIR_SHIFT))
/*
* Section address mask and size definitions.
*/
#define SECTION_SHIFT PMD_SHIFT
#define SECTION_SIZE (_AC(1, UL) << SECTION_SHIFT)
#define SECTION_MASK (~(SECTION_SIZE-1))
/*
* Contiguous page definitions.
*/
#ifdef CONFIG_ARM64_64K_PAGES
#define CONT_PTE_SHIFT 5
#define CONT_PMD_SHIFT 5
#elif defined(CONFIG_ARM64_16K_PAGES)
#define CONT_PTE_SHIFT 7
#define CONT_PMD_SHIFT 5
#else
#define CONT_PTE_SHIFT 4
#define CONT_PMD_SHIFT 4
#endif
#define CONT_PTES (1 << CONT_PTE_SHIFT)
#define CONT_PTE_SIZE (CONT_PTES * PAGE_SIZE)
#define CONT_PTE_MASK (~(CONT_PTE_SIZE - 1))
#define CONT_PMDS (1 << CONT_PMD_SHIFT)
#define CONT_PMD_SIZE (CONT_PMDS * PMD_SIZE)
#define CONT_PMD_MASK (~(CONT_PMD_SIZE - 1))
/* the the numerical offset of the PTE within a range of CONT_PTES */
#define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
/*
* Hardware page table definitions.
*
* Level 1 descriptor (PUD).
*/
arm64: mm: Implement 4 levels of translation tables This patch implements 4 levels of translation tables since 3 levels of page tables with 4KB pages cannot support 40-bit physical address space described in [1] due to the following issue. It is a restriction that kernel logical memory map with 4KB + 3 levels (0xffffffc000000000-0xffffffffffffffff) cannot cover RAM region from 544GB to 1024GB in [1]. Specifically, ARM64 kernel fails to create mapping for this region in map_mem function since __phys_to_virt for this region reaches to address overflow. If SoC design follows the document, [1], over 32GB RAM would be placed from 544GB. Even 64GB system is supposed to use the region from 544GB to 576GB for only 32GB RAM. Naturally, it would reach to enable 4 levels of page tables to avoid hacking __virt_to_phys and __phys_to_virt. However, it is recommended 4 levels of page table should be only enabled if memory map is too sparse or there is about 512GB RAM. References ---------- [1]: Principles of ARM Memory Maps, White Paper, Issue C Signed-off-by: Jungseok Lee <jays.lee@samsung.com> Reviewed-by: Sungjinn Chung <sungjinn.chung@samsung.com> Acked-by: Kukjin Kim <kgene.kim@samsung.com> Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Reviewed-by: Steve Capper <steve.capper@linaro.org> [catalin.marinas@arm.com: MEMBLOCK_INITIAL_LIMIT removed, same as PUD_SIZE] [catalin.marinas@arm.com: early_ioremap_init() updated for 4 levels] [catalin.marinas@arm.com: 48-bit VA depends on BROKEN until KVM is fixed] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Tested-by: Jungseok Lee <jungseoklee85@gmail.com>
2014-05-12 09:40:51 +00:00
#define PUD_TYPE_TABLE (_AT(pudval_t, 3) << 0)
#define PUD_TABLE_BIT (_AT(pudval_t, 1) << 1)
#define PUD_TYPE_MASK (_AT(pudval_t, 3) << 0)
#define PUD_TYPE_SECT (_AT(pudval_t, 1) << 0)
/*
* Level 2 descriptor (PMD).
*/
#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_TABLE_BIT (_AT(pmdval_t, 1) << 1)
/*
* Section
*/
#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0)
#define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */
#define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */
#define PMD_SECT_S (_AT(pmdval_t, 3) << 8)
#define PMD_SECT_AF (_AT(pmdval_t, 1) << 10)
#define PMD_SECT_NG (_AT(pmdval_t, 1) << 11)
#define PMD_SECT_CONT (_AT(pmdval_t, 1) << 52)
#define PMD_SECT_PXN (_AT(pmdval_t, 1) << 53)
#define PMD_SECT_UXN (_AT(pmdval_t, 1) << 54)
/*
* AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
*/
#define PMD_ATTRINDX(t) (_AT(pmdval_t, (t)) << 2)
#define PMD_ATTRINDX_MASK (_AT(pmdval_t, 7) << 2)
/*
* 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_TABLE_BIT (_AT(pteval_t, 1) << 1)
#define PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */
#define PTE_RDONLY (_AT(pteval_t, 1) << 7) /* AP[2] */
#define PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */
#define PTE_AF (_AT(pteval_t, 1) << 10) /* Access Flag */
#define PTE_NG (_AT(pteval_t, 1) << 11) /* nG */
#define PTE_DBM (_AT(pteval_t, 1) << 51) /* Dirty Bit Management */
#define PTE_CONT (_AT(pteval_t, 1) << 52) /* Contiguous range */
#define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */
#define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */
#define PTE_HYP_XN (_AT(pteval_t, 1) << 54) /* HYP XN */
#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
#ifdef CONFIG_ARM64_PA_BITS_52
#define PTE_ADDR_HIGH (_AT(pteval_t, 0xf) << 12)
#define PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH)
#else
#define PTE_ADDR_MASK PTE_ADDR_LOW
#endif
/*
* AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
*/
#define PTE_ATTRINDX(t) (_AT(pteval_t, (t)) << 2)
#define PTE_ATTRINDX_MASK (_AT(pteval_t, 7) << 2)
/*
* 2nd stage PTE definitions
*/
#define PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[2:1] */
#define PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */
#define PTE_S2_XN (_AT(pteval_t, 2) << 53) /* XN[1:0] */
#define PMD_S2_RDONLY (_AT(pmdval_t, 1) << 6) /* HAP[2:1] */
#define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */
#define PMD_S2_XN (_AT(pmdval_t, 2) << 53) /* XN[1:0] */
#define PUD_S2_RDONLY (_AT(pudval_t, 1) << 6) /* HAP[2:1] */
#define PUD_S2_RDWR (_AT(pudval_t, 3) << 6) /* HAP[2:1] */
#define PUD_S2_XN (_AT(pudval_t, 2) << 53) /* XN[1:0] */
/*
* Memory Attribute override for Stage-2 (MemAttr[3:0])
*/
#define PTE_S2_MEMATTR(t) (_AT(pteval_t, (t)) << 2)
#define PTE_S2_MEMATTR_MASK (_AT(pteval_t, 0xf) << 2)
/*
* EL2/HYP PTE/PMD definitions
*/
#define PMD_HYP PMD_SECT_USER
#define PTE_HYP PTE_USER
/*
* Highest possible physical address supported.
*/
#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS)
#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1)
arm64: mm: Support Common Not Private translations Common Not Private (CNP) is a feature of ARMv8.2 extension which allows translation table entries to be shared between different PEs in the same inner shareable domain, so the hardware can use this fact to optimise the caching of such entries in the TLB. CNP occupies one bit in TTBRx_ELy and VTTBR_EL2, which advertises to the hardware that the translation table entries pointed to by this TTBR are the same as every PE in the same inner shareable domain for which the equivalent TTBR also has CNP bit set. In case CNP bit is set but TTBR does not point at the same translation table entries for a given ASID and VMID, then the system is mis-configured, so the results of translations are UNPREDICTABLE. For kernel we postpone setting CNP till all cpus are up and rely on cpufeature framework to 1) patch the code which is sensitive to CNP and 2) update TTBR1_EL1 with CNP bit set. TTBR1_EL1 can be reprogrammed as result of hibernation or cpuidle (via __enable_mmu). For these two cases we restore CnP bit via __cpu_suspend_exit(). There are a few cases we need to care of changes in TTBR0_EL1: - a switch to idmap - software emulated PAN we rule out latter via Kconfig options and for the former we make sure that CNP is set for non-zero ASIDs only. Reviewed-by: James Morse <james.morse@arm.com> Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com> [catalin.marinas@arm.com: default y for CONFIG_ARM64_CNP] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2018-07-31 13:08:56 +00:00
#define TTBR_CNP_BIT (UL(1) << 0)
/*
* TCR flags.
*/
#define TCR_T0SZ_OFFSET 0
#define TCR_T1SZ_OFFSET 16
#define TCR_T0SZ(x) ((UL(64) - (x)) << TCR_T0SZ_OFFSET)
#define TCR_T1SZ(x) ((UL(64) - (x)) << TCR_T1SZ_OFFSET)
#define TCR_TxSZ(x) (TCR_T0SZ(x) | TCR_T1SZ(x))
#define TCR_TxSZ_WIDTH 6
#define TCR_T0SZ_MASK (((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
#define TCR_EPD0_SHIFT 7
#define TCR_EPD0_MASK (UL(1) << TCR_EPD0_SHIFT)
#define TCR_IRGN0_SHIFT 8
#define TCR_IRGN0_MASK (UL(3) << TCR_IRGN0_SHIFT)
#define TCR_IRGN0_NC (UL(0) << TCR_IRGN0_SHIFT)
#define TCR_IRGN0_WBWA (UL(1) << TCR_IRGN0_SHIFT)
#define TCR_IRGN0_WT (UL(2) << TCR_IRGN0_SHIFT)
#define TCR_IRGN0_WBnWA (UL(3) << TCR_IRGN0_SHIFT)
#define TCR_EPD1_SHIFT 23
#define TCR_EPD1_MASK (UL(1) << TCR_EPD1_SHIFT)
#define TCR_IRGN1_SHIFT 24
#define TCR_IRGN1_MASK (UL(3) << TCR_IRGN1_SHIFT)
#define TCR_IRGN1_NC (UL(0) << TCR_IRGN1_SHIFT)
#define TCR_IRGN1_WBWA (UL(1) << TCR_IRGN1_SHIFT)
#define TCR_IRGN1_WT (UL(2) << TCR_IRGN1_SHIFT)
#define TCR_IRGN1_WBnWA (UL(3) << TCR_IRGN1_SHIFT)
#define TCR_IRGN_NC (TCR_IRGN0_NC | TCR_IRGN1_NC)
#define TCR_IRGN_WBWA (TCR_IRGN0_WBWA | TCR_IRGN1_WBWA)
#define TCR_IRGN_WT (TCR_IRGN0_WT | TCR_IRGN1_WT)
#define TCR_IRGN_WBnWA (TCR_IRGN0_WBnWA | TCR_IRGN1_WBnWA)
#define TCR_IRGN_MASK (TCR_IRGN0_MASK | TCR_IRGN1_MASK)
#define TCR_ORGN0_SHIFT 10
#define TCR_ORGN0_MASK (UL(3) << TCR_ORGN0_SHIFT)
#define TCR_ORGN0_NC (UL(0) << TCR_ORGN0_SHIFT)
#define TCR_ORGN0_WBWA (UL(1) << TCR_ORGN0_SHIFT)
#define TCR_ORGN0_WT (UL(2) << TCR_ORGN0_SHIFT)
#define TCR_ORGN0_WBnWA (UL(3) << TCR_ORGN0_SHIFT)
#define TCR_ORGN1_SHIFT 26
#define TCR_ORGN1_MASK (UL(3) << TCR_ORGN1_SHIFT)
#define TCR_ORGN1_NC (UL(0) << TCR_ORGN1_SHIFT)
#define TCR_ORGN1_WBWA (UL(1) << TCR_ORGN1_SHIFT)
#define TCR_ORGN1_WT (UL(2) << TCR_ORGN1_SHIFT)
#define TCR_ORGN1_WBnWA (UL(3) << TCR_ORGN1_SHIFT)
#define TCR_ORGN_NC (TCR_ORGN0_NC | TCR_ORGN1_NC)
#define TCR_ORGN_WBWA (TCR_ORGN0_WBWA | TCR_ORGN1_WBWA)
#define TCR_ORGN_WT (TCR_ORGN0_WT | TCR_ORGN1_WT)
#define TCR_ORGN_WBnWA (TCR_ORGN0_WBnWA | TCR_ORGN1_WBnWA)
#define TCR_ORGN_MASK (TCR_ORGN0_MASK | TCR_ORGN1_MASK)
#define TCR_SH0_SHIFT 12
#define TCR_SH0_MASK (UL(3) << TCR_SH0_SHIFT)
#define TCR_SH0_INNER (UL(3) << TCR_SH0_SHIFT)
#define TCR_SH1_SHIFT 28
#define TCR_SH1_MASK (UL(3) << TCR_SH1_SHIFT)
#define TCR_SH1_INNER (UL(3) << TCR_SH1_SHIFT)
#define TCR_SHARED (TCR_SH0_INNER | TCR_SH1_INNER)
#define TCR_TG0_SHIFT 14
#define TCR_TG0_MASK (UL(3) << TCR_TG0_SHIFT)
#define TCR_TG0_4K (UL(0) << TCR_TG0_SHIFT)
#define TCR_TG0_64K (UL(1) << TCR_TG0_SHIFT)
#define TCR_TG0_16K (UL(2) << TCR_TG0_SHIFT)
#define TCR_TG1_SHIFT 30
#define TCR_TG1_MASK (UL(3) << TCR_TG1_SHIFT)
#define TCR_TG1_16K (UL(1) << TCR_TG1_SHIFT)
#define TCR_TG1_4K (UL(2) << TCR_TG1_SHIFT)
#define TCR_TG1_64K (UL(3) << TCR_TG1_SHIFT)
#define TCR_IPS_SHIFT 32
#define TCR_IPS_MASK (UL(7) << TCR_IPS_SHIFT)
#define TCR_A1 (UL(1) << 22)
#define TCR_ASID16 (UL(1) << 36)
#define TCR_TBI0 (UL(1) << 37)
#define TCR_TBI1 (UL(1) << 38)
#define TCR_HA (UL(1) << 39)
#define TCR_HD (UL(1) << 40)
#define TCR_NFD0 (UL(1) << 53)
#define TCR_NFD1 (UL(1) << 54)
/*
* TTBR.
*/
#ifdef CONFIG_ARM64_PA_BITS_52
/*
* This should be GENMASK_ULL(47, 2).
* TTBR_ELx[1] is RES0 in this configuration.
*/
#define TTBR_BADDR_MASK_52 (((UL(1) << 46) - 1) << 2)
#endif
#ifdef CONFIG_ARM64_USER_VA_BITS_52
arm64: mm: Offset TTBR1 to allow 52-bit PTRS_PER_PGD Enabling 52-bit VAs on arm64 requires that the PGD table expands from 64 entries (for the 48-bit case) to 1024 entries. This quantity, PTRS_PER_PGD is used as follows to compute which PGD entry corresponds to a given virtual address, addr: pgd_index(addr) -> (addr >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1) Userspace addresses are prefixed by 0's, so for a 48-bit userspace address, uva, the following is true: (uva >> PGDIR_SHIFT) & (1024 - 1) == (uva >> PGDIR_SHIFT) & (64 - 1) In other words, a 48-bit userspace address will have the same pgd_index when using PTRS_PER_PGD = 64 and 1024. Kernel addresses are prefixed by 1's so, given a 48-bit kernel address, kva, we have the following inequality: (kva >> PGDIR_SHIFT) & (1024 - 1) != (kva >> PGDIR_SHIFT) & (64 - 1) In other words a 48-bit kernel virtual address will have a different pgd_index when using PTRS_PER_PGD = 64 and 1024. If, however, we note that: kva = 0xFFFF << 48 + lower (where lower[63:48] == 0b) and, PGDIR_SHIFT = 42 (as we are dealing with 64KB PAGE_SIZE) We can consider: (kva >> PGDIR_SHIFT) & (1024 - 1) - (kva >> PGDIR_SHIFT) & (64 - 1) = (0xFFFF << 6) & 0x3FF - (0xFFFF << 6) & 0x3F // "lower" cancels out = 0x3C0 In other words, one can switch PTRS_PER_PGD to the 52-bit value globally provided that they increment ttbr1_el1 by 0x3C0 * 8 = 0x1E00 bytes when running with 48-bit kernel VAs (TCR_EL1.T1SZ = 16). For kernel configuration where 52-bit userspace VAs are possible, this patch offsets ttbr1_el1 and sets PTRS_PER_PGD corresponding to the 52-bit value. Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com> Suggested-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Steve Capper <steve.capper@arm.com> [will: added comment to TTBR1_BADDR_4852_OFFSET calculation] Signed-off-by: Will Deacon <will.deacon@arm.com>
2018-12-06 22:50:39 +00:00
/* Must be at least 64-byte aligned to prevent corruption of the TTBR */
#define TTBR1_BADDR_4852_OFFSET (((UL(1) << (52 - PGDIR_SHIFT)) - \
(UL(1) << (48 - PGDIR_SHIFT))) * 8)
#endif
#endif