linux_dsm_epyc7002/arch/riscv/include/asm/pgtable-64.h
Anup Patel 671f9a3e2e 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>
2019-07-09 09:08:04 -07:00

82 lines
1.8 KiB
C

/* 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>
#define PGDIR_SHIFT 30
/* Size of region mapped by a page global directory */
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_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 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);
}
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 unsigned long pud_page_vaddr(pud_t pud)
{
return (unsigned long)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
}
#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);
}
static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
{
return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
}
static inline unsigned long _pmd_pfn(pmd_t pmd)
{
return pmd_val(pmd) >> _PAGE_PFN_SHIFT;
}
#define pmd_ERROR(e) \
pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
#endif /* _ASM_RISCV_PGTABLE_64_H */