linux/arch/riscv/include/asm/pgtable-64.h

194 lines
4.1 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2012 Regents of the University of California
*/
#ifndef _ASM_RISCV_PGTABLE_64_H
#define _ASM_RISCV_PGTABLE_64_H
#include <linux/const.h>
extern bool pgtable_l4_enabled;
#define PGDIR_SHIFT_L3 30
#define PGDIR_SHIFT_L4 39
#define PGDIR_SIZE_L3 (_AC(1, UL) << PGDIR_SHIFT_L3)
#define PGDIR_SHIFT (pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3)
/* Size of region mapped by a page global directory */
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
/* pud is folded into pgd in case of 3-level page table */
#define PUD_SHIFT 30
#define PUD_SIZE (_AC(1, UL) << PUD_SHIFT)
#define PUD_MASK (~(PUD_SIZE - 1))
#define PMD_SHIFT 21
/* Size of region mapped by a page middle directory */
#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT)
#define PMD_MASK (~(PMD_SIZE - 1))
/* Page Upper Directory entry */
typedef struct {
unsigned long pud;
} pud_t;
#define pud_val(x) ((x).pud)
#define __pud(x) ((pud_t) { (x) })
#define PTRS_PER_PUD (PAGE_SIZE / sizeof(pud_t))
/* Page Middle Directory entry */
typedef struct {
unsigned long pmd;
} pmd_t;
#define pmd_val(x) ((x).pmd)
#define __pmd(x) ((pmd_t) { (x) })
#define PTRS_PER_PMD (PAGE_SIZE / sizeof(pmd_t))
static inline int pud_present(pud_t pud)
{
return (pud_val(pud) & _PAGE_PRESENT);
}
static inline int pud_none(pud_t pud)
{
return (pud_val(pud) == 0);
}
static inline int pud_bad(pud_t pud)
{
return !pud_present(pud);
}
riscv: mm: add p?d_leaf() definitions walk_page_range() is going to be allowed to walk page tables other than those of user space. For this it needs to know when it has reached a 'leaf' entry in the page tables. This information is provided by the p?d_leaf() functions/macros. For riscv a page is a leaf page when it has a read, write or execute bit set on it. Link: http://lkml.kernel.org/r/20191218162402.45610-8-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Reviewed-by: Alexandre Ghiti <alex@ghiti.fr> Reviewed-by: Zong Li <zong.li@sifive.com> Acked-by: Paul Walmsley <paul.walmsley@sifive.com> [arch/riscv] Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:28 +00:00
#define pud_leaf pud_leaf
static inline int pud_leaf(pud_t pud)
{
return pud_present(pud) && (pud_val(pud) & _PAGE_LEAF);
riscv: mm: add p?d_leaf() definitions walk_page_range() is going to be allowed to walk page tables other than those of user space. For this it needs to know when it has reached a 'leaf' entry in the page tables. This information is provided by the p?d_leaf() functions/macros. For riscv a page is a leaf page when it has a read, write or execute bit set on it. Link: http://lkml.kernel.org/r/20191218162402.45610-8-steven.price@arm.com Signed-off-by: Steven Price <steven.price@arm.com> Reviewed-by: Alexandre Ghiti <alex@ghiti.fr> Reviewed-by: Zong Li <zong.li@sifive.com> Acked-by: Paul Walmsley <paul.walmsley@sifive.com> [arch/riscv] Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Hogan <jhogan@kernel.org> Cc: James Morse <james.morse@arm.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: "Liang, Kan" <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Paul Burton <paul.burton@mips.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 01:35:28 +00:00
}
static inline void set_pud(pud_t *pudp, pud_t pud)
{
*pudp = pud;
}
static inline void pud_clear(pud_t *pudp)
{
set_pud(pudp, __pud(0));
}
static inline pud_t pfn_pud(unsigned long pfn, pgprot_t prot)
{
return __pud((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
}
static inline unsigned long _pud_pfn(pud_t pud)
{
return pud_val(pud) >> _PAGE_PFN_SHIFT;
}
static inline pmd_t *pud_pgtable(pud_t pud)
{
return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
}
static inline struct page *pud_page(pud_t pud)
{
return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT);
}
#define mm_pud_folded mm_pud_folded
static inline bool mm_pud_folded(struct mm_struct *mm)
{
if (pgtable_l4_enabled)
return false;
return true;
}
#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
{
return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
}
RISC-V: Setup initial page tables in two stages Currently, the setup_vm() does initial page table setup in one-shot very early before enabling MMU. Due to this, the setup_vm() has to map all possible kernel virtual addresses since it does not know size and location of RAM. This means we have kernel mappings for non-existent RAM and any buggy driver (or kernel) code doing out-of-bound access to RAM will not fault and cause underterministic behaviour. Further, the setup_vm() creates PMD mappings (i.e. 2M mappings) for RV64 systems. This means for PAGE_OFFSET=0xffffffe000000000 (i.e. MAXPHYSMEM_128GB=y), the setup_vm() will require 129 pages (i.e. 516 KB) of memory for initial page tables which is never freed. The memory required for initial page tables will further increase if we chose a lower value of PAGE_OFFSET (e.g. 0xffffff0000000000) This patch implements two-staged initial page table setup, as follows: 1. Early (i.e. setup_vm()): This stage maps kernel image and DTB in a early page table (i.e. early_pg_dir). The early_pg_dir will be used only by boot HART so it can be freed as-part of init memory free-up. 2. Final (i.e. setup_vm_final()): This stage maps all possible RAM banks in the final page table (i.e. swapper_pg_dir). The boot HART will start using swapper_pg_dir at the end of setup_vm_final(). All non-boot HARTs directly use the swapper_pg_dir created by boot HART. We have following advantages with this new approach: 1. Kernel mappings for non-existent RAM don't exists anymore. 2. Memory consumed by initial page tables is now indpendent of the chosen PAGE_OFFSET. 3. Memory consumed by initial page tables on RV64 system is 2 pages (i.e. 8 KB) which has significantly reduced and these pages will be freed as-part of the init memory free-up. The patch also provides a foundation for implementing strict kernel mappings where we protect kernel text and rodata using PTE permissions. Suggested-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Anup Patel <anup.patel@wdc.com> [paul.walmsley@sifive.com: updated to apply; fixed a checkpatch warning] Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
2019-06-28 20:36:21 +00:00
static inline unsigned long _pmd_pfn(pmd_t pmd)
{
return pmd_val(pmd) >> _PAGE_PFN_SHIFT;
}
#define mk_pmd(page, prot) pfn_pmd(page_to_pfn(page), prot)
#define pmd_ERROR(e) \
pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
#define pud_ERROR(e) \
pr_err("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e))
static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
{
if (pgtable_l4_enabled)
*p4dp = p4d;
else
set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
}
static inline int p4d_none(p4d_t p4d)
{
if (pgtable_l4_enabled)
return (p4d_val(p4d) == 0);
return 0;
}
static inline int p4d_present(p4d_t p4d)
{
if (pgtable_l4_enabled)
return (p4d_val(p4d) & _PAGE_PRESENT);
return 1;
}
static inline int p4d_bad(p4d_t p4d)
{
if (pgtable_l4_enabled)
return !p4d_present(p4d);
return 0;
}
static inline void p4d_clear(p4d_t *p4d)
{
if (pgtable_l4_enabled)
set_p4d(p4d, __p4d(0));
}
static inline pud_t *p4d_pgtable(p4d_t p4d)
{
if (pgtable_l4_enabled)
return (pud_t *)pfn_to_virt(p4d_val(p4d) >> _PAGE_PFN_SHIFT);
return (pud_t *)pud_pgtable((pud_t) { p4d_val(p4d) });
}
static inline struct page *p4d_page(p4d_t p4d)
{
return pfn_to_page(p4d_val(p4d) >> _PAGE_PFN_SHIFT);
}
#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
#define pud_offset pud_offset
static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
{
if (pgtable_l4_enabled)
return p4d_pgtable(*p4d) + pud_index(address);
return (pud_t *)p4d;
}
#endif /* _ASM_RISCV_PGTABLE_64_H */