linux/arch/riscv/mm/init.c
Linus Torvalds 063df71a57 RISC-V Patches for the 5.15 Merge Window, Part 1
* Support for PC-relative instructions (auipc and branches) in kprobes.
 * Support for forced IRQ threading.
 * Support for the hlt/nohlt kernel command line options, via the generic
   idle loop.
 * Support for showing the edge/level triggered behavior of interrupts in
   /proc/interrupts.
 * A handful of cleanups to our address mapping mechanisms.
 * Support for allocating gigantic hugepages via CMA.
 * Support for the undefined behavior sanitizer.
 * A handful of cleanups to the VDSO that allow the kernel to build with
   LLD.
 * Support for hugepage migration.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAmEzxA4THHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYifuvD/93Tr9oAy6dwkGoa/VIzBc/nklCeTiO
 cv2W9eFQMG+PdRh1Ezi9FrLO6qZoADGOPPcnuc2HTTe58CWWWg0juC862H/N2k3V
 +3LGhHTv3E7NsEZNa4YhQXw6pPmj5OhbHab87HNowHpuNJGpKYE6Q+QbnYl5vorI
 9YS10pRpqvO6tdHUW335Z5N0nW9X3HCHD6NUb1ZV8qd34QzP+XeCJMqVXpoOijNO
 96lhyDYPivM2Rhi+uvtSjUeWzbddnN/P9IywfECddHFJyGvoEtiIROo9d2sR6pla
 lAa1YOw0ybD/UPHtL/diEU+K8ivNVKdRN/YvlzHS4CdCrPyuWSUmBMozsOBMBwf1
 UZCMDwmP2sQkHu1Ht9g1fXwk2R85j1s+qE5cZEXyAEULKfHlmt4vygd1xgm8DTf9
 xgS+np2g0frcmKU8cLPmC7Sr0YI1fPeDMRkBXTYE1SmBF3eHrZCCbeM1H97p2mUC
 zs/Dvyoj7e25HGyYqxN3lHZzhMluqh7wCQSOQMB2YxVwdiA4VjyjxLF4MKAdXL8i
 F1QTETsjLGu6UiMfNIQ4RVs981/fGYSANdOvMfwo447gVH6JaxC51sLo6YIDtXss
 tLzchHNu5IMNqB7XOb1gU8ZKeXruG9lrxwUOyEIYAVi6pHCbkdLV0A8ymwEjj06b
 aGV4xFPaAGvDLQ==
 =rDB3
 -----END PGP SIGNATURE-----

Merge tag 'riscv-for-linus-5.15-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - support PC-relative instructions (auipc and branches) in kprobes

 - support for forced IRQ threading

 - support for the hlt/nohlt kernel command line options, via the
   generic idle loop

 - show the edge/level triggered behavior of interrupts
   in /proc/interrupts

 - a handful of cleanups to our address mapping mechanisms

 - support for allocating gigantic hugepages via CMA

 - support for the undefined behavior sanitizer (UBSAN)

 - a handful of cleanups to the VDSO that allow the kernel to build with
   LLD.

 - support for hugepage migration

* tag 'riscv-for-linus-5.15-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (21 commits)
  riscv: add support for hugepage migration
  RISC-V: Fix VDSO build for !MMU
  riscv: use strscpy to replace strlcpy
  riscv: explicitly use symbol offsets for VDSO
  riscv: Enable Undefined Behavior Sanitizer UBSAN
  riscv: Keep the riscv Kconfig selects sorted
  riscv: Support allocating gigantic hugepages using CMA
  riscv: fix the global name pfn_base confliction error
  riscv: Move early fdt mapping creation in its own function
  riscv: Simplify BUILTIN_DTB device tree mapping handling
  riscv: Use __maybe_unused instead of #ifdefs around variable declarations
  riscv: Get rid of map_size parameter to create_kernel_page_table
  riscv: Introduce va_kernel_pa_offset for 32-bit kernel
  riscv: Optimize kernel virtual address conversion macro
  dt-bindings: riscv: add starfive jh7100 bindings
  riscv: Enable GENERIC_IRQ_SHOW_LEVEL
  riscv: Enable idle generic idle loop
  riscv: Allow forced irq threading
  riscv: Implement thread_struct whitelist for hardened usercopy
  riscv: kprobes: implement the branch instructions
  ...
2021-09-05 11:31:23 -07:00

858 lines
24 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2012 Regents of the University of California
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
* Copyright (C) 2020 FORTH-ICS/CARV
* Nick Kossifidis <mick@ics.forth.gr>
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/memblock.h>
#include <linux/initrd.h>
#include <linux/swap.h>
#include <linux/swiotlb.h>
#include <linux/sizes.h>
#include <linux/of_fdt.h>
#include <linux/of_reserved_mem.h>
#include <linux/libfdt.h>
#include <linux/set_memory.h>
#include <linux/dma-map-ops.h>
#include <linux/crash_dump.h>
#include <linux/hugetlb.h>
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/soc.h>
#include <asm/io.h>
#include <asm/ptdump.h>
#include <asm/numa.h>
#include "../kernel/head.h"
struct kernel_mapping kernel_map __ro_after_init;
EXPORT_SYMBOL(kernel_map);
#ifdef CONFIG_XIP_KERNEL
#define kernel_map (*(struct kernel_mapping *)XIP_FIXUP(&kernel_map))
#endif
phys_addr_t phys_ram_base __ro_after_init;
EXPORT_SYMBOL(phys_ram_base);
#ifdef CONFIG_XIP_KERNEL
extern char _xiprom[], _exiprom[];
#endif
unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
__page_aligned_bss;
EXPORT_SYMBOL(empty_zero_page);
extern char _start[];
#define DTB_EARLY_BASE_VA PGDIR_SIZE
void *_dtb_early_va __initdata;
uintptr_t _dtb_early_pa __initdata;
struct pt_alloc_ops {
pte_t *(*get_pte_virt)(phys_addr_t pa);
phys_addr_t (*alloc_pte)(uintptr_t va);
#ifndef __PAGETABLE_PMD_FOLDED
pmd_t *(*get_pmd_virt)(phys_addr_t pa);
phys_addr_t (*alloc_pmd)(uintptr_t va);
#endif
};
static phys_addr_t dma32_phys_limit __initdata;
static void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
#ifdef CONFIG_ZONE_DMA32
max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
free_area_init(max_zone_pfns);
}
#if defined(CONFIG_MMU) && defined(CONFIG_DEBUG_VM)
static inline void print_mlk(char *name, unsigned long b, unsigned long t)
{
pr_notice("%12s : 0x%08lx - 0x%08lx (%4ld kB)\n", name, b, t,
(((t) - (b)) >> 10));
}
static inline void print_mlm(char *name, unsigned long b, unsigned long t)
{
pr_notice("%12s : 0x%08lx - 0x%08lx (%4ld MB)\n", name, b, t,
(((t) - (b)) >> 20));
}
static void __init print_vm_layout(void)
{
pr_notice("Virtual kernel memory layout:\n");
print_mlk("fixmap", (unsigned long)FIXADDR_START,
(unsigned long)FIXADDR_TOP);
print_mlm("pci io", (unsigned long)PCI_IO_START,
(unsigned long)PCI_IO_END);
print_mlm("vmemmap", (unsigned long)VMEMMAP_START,
(unsigned long)VMEMMAP_END);
print_mlm("vmalloc", (unsigned long)VMALLOC_START,
(unsigned long)VMALLOC_END);
print_mlm("lowmem", (unsigned long)PAGE_OFFSET,
(unsigned long)high_memory);
#ifdef CONFIG_64BIT
print_mlm("kernel", (unsigned long)KERNEL_LINK_ADDR,
(unsigned long)ADDRESS_SPACE_END);
#endif
}
#else
static void print_vm_layout(void) { }
#endif /* CONFIG_DEBUG_VM */
void __init mem_init(void)
{
#ifdef CONFIG_FLATMEM
BUG_ON(!mem_map);
#endif /* CONFIG_FLATMEM */
#ifdef CONFIG_SWIOTLB
if (swiotlb_force == SWIOTLB_FORCE ||
max_pfn > PFN_DOWN(dma32_phys_limit))
swiotlb_init(1);
else
swiotlb_force = SWIOTLB_NO_FORCE;
#endif
high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
memblock_free_all();
print_vm_layout();
}
/*
* The default maximal physical memory size is -PAGE_OFFSET for 32-bit kernel,
* whereas for 64-bit kernel, the end of the virtual address space is occupied
* by the modules/BPF/kernel mappings which reduces the available size of the
* linear mapping.
* Limit the memory size via mem.
*/
#ifdef CONFIG_64BIT
static phys_addr_t memory_limit = -PAGE_OFFSET - SZ_4G;
#else
static phys_addr_t memory_limit = -PAGE_OFFSET;
#endif
static int __init early_mem(char *p)
{
u64 size;
if (!p)
return 1;
size = memparse(p, &p) & PAGE_MASK;
memory_limit = min_t(u64, size, memory_limit);
pr_notice("Memory limited to %lldMB\n", (u64)memory_limit >> 20);
return 0;
}
early_param("mem", early_mem);
static void __init setup_bootmem(void)
{
phys_addr_t vmlinux_end = __pa_symbol(&_end);
phys_addr_t vmlinux_start = __pa_symbol(&_start);
phys_addr_t __maybe_unused max_mapped_addr;
phys_addr_t phys_ram_end;
#ifdef CONFIG_XIP_KERNEL
vmlinux_start = __pa_symbol(&_sdata);
#endif
memblock_enforce_memory_limit(memory_limit);
/*
* Reserve from the start of the kernel to the end of the kernel
*/
#if defined(CONFIG_64BIT) && defined(CONFIG_STRICT_KERNEL_RWX)
/*
* Make sure we align the reservation on PMD_SIZE since we will
* map the kernel in the linear mapping as read-only: we do not want
* any allocation to happen between _end and the next pmd aligned page.
*/
vmlinux_end = (vmlinux_end + PMD_SIZE - 1) & PMD_MASK;
#endif
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
phys_ram_end = memblock_end_of_DRAM();
#ifndef CONFIG_64BIT
#ifndef CONFIG_XIP_KERNEL
phys_ram_base = memblock_start_of_DRAM();
#endif
/*
* memblock allocator is not aware of the fact that last 4K bytes of
* the addressable memory can not be mapped because of IS_ERR_VALUE
* macro. Make sure that last 4k bytes are not usable by memblock
* if end of dram is equal to maximum addressable memory. For 64-bit
* kernel, this problem can't happen here as the end of the virtual
* address space is occupied by the kernel mapping then this check must
* be done as soon as the kernel mapping base address is determined.
*/
max_mapped_addr = __pa(~(ulong)0);
if (max_mapped_addr == (phys_ram_end - 1))
memblock_set_current_limit(max_mapped_addr - 4096);
#endif
min_low_pfn = PFN_UP(phys_ram_base);
max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end);
dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);
reserve_initrd_mem();
/*
* If DTB is built in, no need to reserve its memblock.
* Otherwise, do reserve it but avoid using
* early_init_fdt_reserve_self() since __pa() does
* not work for DTB pointers that are fixmap addresses
*/
if (!IS_ENABLED(CONFIG_BUILTIN_DTB))
memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
early_init_fdt_scan_reserved_mem();
dma_contiguous_reserve(dma32_phys_limit);
if (IS_ENABLED(CONFIG_64BIT))
hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
memblock_allow_resize();
}
#ifdef CONFIG_MMU
static struct pt_alloc_ops _pt_ops __initdata;
#ifdef CONFIG_XIP_KERNEL
#define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&_pt_ops))
#else
#define pt_ops _pt_ops
#endif
unsigned long riscv_pfn_base __ro_after_init;
EXPORT_SYMBOL(riscv_pfn_base);
pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;
pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
#ifdef CONFIG_XIP_KERNEL
#define trampoline_pg_dir ((pgd_t *)XIP_FIXUP(trampoline_pg_dir))
#define fixmap_pte ((pte_t *)XIP_FIXUP(fixmap_pte))
#define early_pg_dir ((pgd_t *)XIP_FIXUP(early_pg_dir))
#endif /* CONFIG_XIP_KERNEL */
void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
{
unsigned long addr = __fix_to_virt(idx);
pte_t *ptep;
BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
ptep = &fixmap_pte[pte_index(addr)];
if (pgprot_val(prot))
set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot));
else
pte_clear(&init_mm, addr, ptep);
local_flush_tlb_page(addr);
}
static inline pte_t *__init get_pte_virt_early(phys_addr_t pa)
{
return (pte_t *)((uintptr_t)pa);
}
static inline pte_t *__init get_pte_virt_fixmap(phys_addr_t pa)
{
clear_fixmap(FIX_PTE);
return (pte_t *)set_fixmap_offset(FIX_PTE, pa);
}
static inline pte_t *__init get_pte_virt_late(phys_addr_t pa)
{
return (pte_t *) __va(pa);
}
static inline phys_addr_t __init alloc_pte_early(uintptr_t va)
{
/*
* We only create PMD or PGD early mappings so we
* should never reach here with MMU disabled.
*/
BUG();
}
static inline phys_addr_t __init alloc_pte_fixmap(uintptr_t va)
{
return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
}
static phys_addr_t __init alloc_pte_late(uintptr_t va)
{
unsigned long vaddr;
vaddr = __get_free_page(GFP_KERNEL);
BUG_ON(!vaddr || !pgtable_pte_page_ctor(virt_to_page(vaddr)));
return __pa(vaddr);
}
static void __init create_pte_mapping(pte_t *ptep,
uintptr_t va, phys_addr_t pa,
phys_addr_t sz, pgprot_t prot)
{
uintptr_t pte_idx = pte_index(va);
BUG_ON(sz != PAGE_SIZE);
if (pte_none(ptep[pte_idx]))
ptep[pte_idx] = pfn_pte(PFN_DOWN(pa), prot);
}
#ifndef __PAGETABLE_PMD_FOLDED
static pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss;
static pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
#ifdef CONFIG_XIP_KERNEL
#define trampoline_pmd ((pmd_t *)XIP_FIXUP(trampoline_pmd))
#define fixmap_pmd ((pmd_t *)XIP_FIXUP(fixmap_pmd))
#define early_pmd ((pmd_t *)XIP_FIXUP(early_pmd))
#endif /* CONFIG_XIP_KERNEL */
static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
{
/* Before MMU is enabled */
return (pmd_t *)((uintptr_t)pa);
}
static pmd_t *__init get_pmd_virt_fixmap(phys_addr_t pa)
{
clear_fixmap(FIX_PMD);
return (pmd_t *)set_fixmap_offset(FIX_PMD, pa);
}
static pmd_t *__init get_pmd_virt_late(phys_addr_t pa)
{
return (pmd_t *) __va(pa);
}
static phys_addr_t __init alloc_pmd_early(uintptr_t va)
{
BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
return (uintptr_t)early_pmd;
}
static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va)
{
return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
}
static phys_addr_t __init alloc_pmd_late(uintptr_t va)
{
unsigned long vaddr;
vaddr = __get_free_page(GFP_KERNEL);
BUG_ON(!vaddr);
return __pa(vaddr);
}
static void __init create_pmd_mapping(pmd_t *pmdp,
uintptr_t va, phys_addr_t pa,
phys_addr_t sz, pgprot_t prot)
{
pte_t *ptep;
phys_addr_t pte_phys;
uintptr_t pmd_idx = pmd_index(va);
if (sz == PMD_SIZE) {
if (pmd_none(pmdp[pmd_idx]))
pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pa), prot);
return;
}
if (pmd_none(pmdp[pmd_idx])) {
pte_phys = pt_ops.alloc_pte(va);
pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pte_phys), PAGE_TABLE);
ptep = pt_ops.get_pte_virt(pte_phys);
memset(ptep, 0, PAGE_SIZE);
} else {
pte_phys = PFN_PHYS(_pmd_pfn(pmdp[pmd_idx]));
ptep = pt_ops.get_pte_virt(pte_phys);
}
create_pte_mapping(ptep, va, pa, sz, prot);
}
#define pgd_next_t pmd_t
#define alloc_pgd_next(__va) pt_ops.alloc_pmd(__va)
#define get_pgd_next_virt(__pa) pt_ops.get_pmd_virt(__pa)
#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \
create_pmd_mapping(__nextp, __va, __pa, __sz, __prot)
#define fixmap_pgd_next fixmap_pmd
#else
#define pgd_next_t pte_t
#define alloc_pgd_next(__va) pt_ops.alloc_pte(__va)
#define get_pgd_next_virt(__pa) pt_ops.get_pte_virt(__pa)
#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \
create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
#define fixmap_pgd_next fixmap_pte
#define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot)
#endif
void __init create_pgd_mapping(pgd_t *pgdp,
uintptr_t va, phys_addr_t pa,
phys_addr_t sz, pgprot_t prot)
{
pgd_next_t *nextp;
phys_addr_t next_phys;
uintptr_t pgd_idx = pgd_index(va);
if (sz == PGDIR_SIZE) {
if (pgd_val(pgdp[pgd_idx]) == 0)
pgdp[pgd_idx] = pfn_pgd(PFN_DOWN(pa), prot);
return;
}
if (pgd_val(pgdp[pgd_idx]) == 0) {
next_phys = alloc_pgd_next(va);
pgdp[pgd_idx] = pfn_pgd(PFN_DOWN(next_phys), PAGE_TABLE);
nextp = get_pgd_next_virt(next_phys);
memset(nextp, 0, PAGE_SIZE);
} else {
next_phys = PFN_PHYS(_pgd_pfn(pgdp[pgd_idx]));
nextp = get_pgd_next_virt(next_phys);
}
create_pgd_next_mapping(nextp, va, pa, sz, prot);
}
static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
{
/* Upgrade to PMD_SIZE mappings whenever possible */
if ((base & (PMD_SIZE - 1)) || (size & (PMD_SIZE - 1)))
return PAGE_SIZE;
return PMD_SIZE;
}
#ifdef CONFIG_XIP_KERNEL
/* called from head.S with MMU off */
asmlinkage void __init __copy_data(void)
{
void *from = (void *)(&_sdata);
void *end = (void *)(&_end);
void *to = (void *)CONFIG_PHYS_RAM_BASE;
size_t sz = (size_t)(end - from + 1);
memcpy(to, from, sz);
}
#endif
#ifdef CONFIG_STRICT_KERNEL_RWX
static __init pgprot_t pgprot_from_va(uintptr_t va)
{
if (is_va_kernel_text(va))
return PAGE_KERNEL_READ_EXEC;
/*
* In 64-bit kernel, the kernel mapping is outside the linear mapping so
* we must protect its linear mapping alias from being executed and
* written.
* And rodata section is marked readonly in mark_rodata_ro.
*/
if (IS_ENABLED(CONFIG_64BIT) && is_va_kernel_lm_alias_text(va))
return PAGE_KERNEL_READ;
return PAGE_KERNEL;
}
void mark_rodata_ro(void)
{
set_kernel_memory(__start_rodata, _data, set_memory_ro);
if (IS_ENABLED(CONFIG_64BIT))
set_kernel_memory(lm_alias(__start_rodata), lm_alias(_data),
set_memory_ro);
debug_checkwx();
}
#else
static __init pgprot_t pgprot_from_va(uintptr_t va)
{
if (IS_ENABLED(CONFIG_64BIT) && !is_kernel_mapping(va))
return PAGE_KERNEL;
return PAGE_KERNEL_EXEC;
}
#endif /* CONFIG_STRICT_KERNEL_RWX */
/*
* setup_vm() is called from head.S with MMU-off.
*
* Following requirements should be honoured for setup_vm() to work
* correctly:
* 1) It should use PC-relative addressing for accessing kernel symbols.
* To achieve this we always use GCC cmodel=medany.
* 2) The compiler instrumentation for FTRACE will not work for setup_vm()
* so disable compiler instrumentation when FTRACE is enabled.
*
* Currently, the above requirements are honoured by using custom CFLAGS
* for init.o in mm/Makefile.
*/
#ifndef __riscv_cmodel_medany
#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
#endif
#ifdef CONFIG_XIP_KERNEL
static void __init create_kernel_page_table(pgd_t *pgdir,
__always_unused bool early)
{
uintptr_t va, end_va;
/* Map the flash resident part */
end_va = kernel_map.virt_addr + kernel_map.xiprom_sz;
for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE)
create_pgd_mapping(pgdir, va,
kernel_map.xiprom + (va - kernel_map.virt_addr),
PMD_SIZE, PAGE_KERNEL_EXEC);
/* Map the data in RAM */
end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size;
for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE)
create_pgd_mapping(pgdir, va,
kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)),
PMD_SIZE, PAGE_KERNEL);
}
#else
static void __init create_kernel_page_table(pgd_t *pgdir, bool early)
{
uintptr_t va, end_va;
end_va = kernel_map.virt_addr + kernel_map.size;
for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE)
create_pgd_mapping(pgdir, va,
kernel_map.phys_addr + (va - kernel_map.virt_addr),
PMD_SIZE,
early ?
PAGE_KERNEL_EXEC : pgprot_from_va(va));
}
#endif
/*
* Setup a 4MB mapping that encompasses the device tree: for 64-bit kernel,
* this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR
* entry.
*/
static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
{
#ifndef CONFIG_BUILTIN_DTB
uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);
create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
IS_ENABLED(CONFIG_64BIT) ? (uintptr_t)early_dtb_pmd : pa,
PGDIR_SIZE,
IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL);
if (IS_ENABLED(CONFIG_64BIT)) {
create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
pa, PMD_SIZE, PAGE_KERNEL);
create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE,
pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
}
dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1));
#else
/*
* For 64-bit kernel, __va can't be used since it would return a linear
* mapping address whereas dtb_early_va will be used before
* setup_vm_final installs the linear mapping. For 32-bit kernel, as the
* kernel is mapped in the linear mapping, that makes no difference.
*/
dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa));
#endif
dtb_early_pa = dtb_pa;
}
asmlinkage void __init setup_vm(uintptr_t dtb_pa)
{
pmd_t __maybe_unused fix_bmap_spmd, fix_bmap_epmd;
kernel_map.virt_addr = KERNEL_LINK_ADDR;
#ifdef CONFIG_XIP_KERNEL
kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
phys_ram_base = CONFIG_PHYS_RAM_BASE;
kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);
kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
#else
kernel_map.phys_addr = (uintptr_t)(&_start);
kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
#endif
kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr);
/* Sanity check alignment and size */
BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
BUG_ON((kernel_map.phys_addr % PMD_SIZE) != 0);
#ifdef CONFIG_64BIT
/*
* The last 4K bytes of the addressable memory can not be mapped because
* of IS_ERR_VALUE macro.
*/
BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
#endif
pt_ops.alloc_pte = alloc_pte_early;
pt_ops.get_pte_virt = get_pte_virt_early;
#ifndef __PAGETABLE_PMD_FOLDED
pt_ops.alloc_pmd = alloc_pmd_early;
pt_ops.get_pmd_virt = get_pmd_virt_early;
#endif
/* Setup early PGD for fixmap */
create_pgd_mapping(early_pg_dir, FIXADDR_START,
(uintptr_t)fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);
#ifndef __PAGETABLE_PMD_FOLDED
/* Setup fixmap PMD */
create_pmd_mapping(fixmap_pmd, FIXADDR_START,
(uintptr_t)fixmap_pte, PMD_SIZE, PAGE_TABLE);
/* Setup trampoline PGD and PMD */
create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
(uintptr_t)trampoline_pmd, PGDIR_SIZE, PAGE_TABLE);
#ifdef CONFIG_XIP_KERNEL
create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
kernel_map.xiprom, PMD_SIZE, PAGE_KERNEL_EXEC);
#else
create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
kernel_map.phys_addr, PMD_SIZE, PAGE_KERNEL_EXEC);
#endif
#else
/* Setup trampoline PGD */
create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
kernel_map.phys_addr, PGDIR_SIZE, PAGE_KERNEL_EXEC);
#endif
/*
* Setup early PGD covering entire kernel which will allow
* us to reach paging_init(). We map all memory banks later
* in setup_vm_final() below.
*/
create_kernel_page_table(early_pg_dir, true);
/* Setup early mapping for FDT early scan */
create_fdt_early_page_table(early_pg_dir, dtb_pa);
/*
* Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap
* range can not span multiple pmds.
*/
BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
!= (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
#ifndef __PAGETABLE_PMD_FOLDED
/*
* Early ioremap fixmap is already created as it lies within first 2MB
* of fixmap region. We always map PMD_SIZE. Thus, both FIX_BTMAP_END
* FIX_BTMAP_BEGIN should lie in the same pmd. Verify that and warn
* the user if not.
*/
fix_bmap_spmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_BEGIN))];
fix_bmap_epmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_END))];
if (pmd_val(fix_bmap_spmd) != pmd_val(fix_bmap_epmd)) {
WARN_ON(1);
pr_warn("fixmap btmap start [%08lx] != end [%08lx]\n",
pmd_val(fix_bmap_spmd), pmd_val(fix_bmap_epmd));
pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
fix_to_virt(FIX_BTMAP_BEGIN));
pr_warn("fix_to_virt(FIX_BTMAP_END): %08lx\n",
fix_to_virt(FIX_BTMAP_END));
pr_warn("FIX_BTMAP_END: %d\n", FIX_BTMAP_END);
pr_warn("FIX_BTMAP_BEGIN: %d\n", FIX_BTMAP_BEGIN);
}
#endif
}
static void __init setup_vm_final(void)
{
uintptr_t va, map_size;
phys_addr_t pa, start, end;
u64 i;
/**
* MMU is enabled at this point. But page table setup is not complete yet.
* fixmap page table alloc functions should be used at this point
*/
pt_ops.alloc_pte = alloc_pte_fixmap;
pt_ops.get_pte_virt = get_pte_virt_fixmap;
#ifndef __PAGETABLE_PMD_FOLDED
pt_ops.alloc_pmd = alloc_pmd_fixmap;
pt_ops.get_pmd_virt = get_pmd_virt_fixmap;
#endif
/* Setup swapper PGD for fixmap */
create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
__pa_symbol(fixmap_pgd_next),
PGDIR_SIZE, PAGE_TABLE);
/* Map all memory banks in the linear mapping */
for_each_mem_range(i, &start, &end) {
if (start >= end)
break;
if (start <= __pa(PAGE_OFFSET) &&
__pa(PAGE_OFFSET) < end)
start = __pa(PAGE_OFFSET);
if (end >= __pa(PAGE_OFFSET) + memory_limit)
end = __pa(PAGE_OFFSET) + memory_limit;
map_size = best_map_size(start, end - start);
for (pa = start; pa < end; pa += map_size) {
va = (uintptr_t)__va(pa);
create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
pgprot_from_va(va));
}
}
#ifdef CONFIG_64BIT
/* Map the kernel */
create_kernel_page_table(swapper_pg_dir, false);
#endif
/* Clear fixmap PTE and PMD mappings */
clear_fixmap(FIX_PTE);
clear_fixmap(FIX_PMD);
/* Move to swapper page table */
csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | SATP_MODE);
local_flush_tlb_all();
/* generic page allocation functions must be used to setup page table */
pt_ops.alloc_pte = alloc_pte_late;
pt_ops.get_pte_virt = get_pte_virt_late;
#ifndef __PAGETABLE_PMD_FOLDED
pt_ops.alloc_pmd = alloc_pmd_late;
pt_ops.get_pmd_virt = get_pmd_virt_late;
#endif
}
#else
asmlinkage void __init setup_vm(uintptr_t dtb_pa)
{
dtb_early_va = (void *)dtb_pa;
dtb_early_pa = dtb_pa;
}
static inline void setup_vm_final(void)
{
}
#endif /* CONFIG_MMU */
#ifdef CONFIG_KEXEC_CORE
/*
* reserve_crashkernel() - reserves memory for crash kernel
*
* This function reserves memory area given in "crashkernel=" kernel command
* line parameter. The memory reserved is used by dump capture kernel when
* primary kernel is crashing.
*/
static void __init reserve_crashkernel(void)
{
unsigned long long crash_base = 0;
unsigned long long crash_size = 0;
unsigned long search_start = memblock_start_of_DRAM();
unsigned long search_end = memblock_end_of_DRAM();
int ret = 0;
/*
* Don't reserve a region for a crash kernel on a crash kernel
* since it doesn't make much sense and we have limited memory
* resources.
*/
#ifdef CONFIG_CRASH_DUMP
if (is_kdump_kernel()) {
pr_info("crashkernel: ignoring reservation request\n");
return;
}
#endif
ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
&crash_size, &crash_base);
if (ret || !crash_size)
return;
crash_size = PAGE_ALIGN(crash_size);
if (crash_base) {
search_start = crash_base;
search_end = crash_base + crash_size;
}
/*
* Current riscv boot protocol requires 2MB alignment for
* RV64 and 4MB alignment for RV32 (hugepage size)
*/
crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
search_start, search_end);
if (crash_base == 0) {
pr_warn("crashkernel: couldn't allocate %lldKB\n",
crash_size >> 10);
return;
}
pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",
crash_base, crash_base + crash_size, crash_size >> 20);
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
}
#endif /* CONFIG_KEXEC_CORE */
void __init paging_init(void)
{
setup_bootmem();
setup_vm_final();
}
void __init misc_mem_init(void)
{
early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
arch_numa_init();
sparse_init();
zone_sizes_init();
#ifdef CONFIG_KEXEC_CORE
reserve_crashkernel();
#endif
memblock_dump_all();
}
#ifdef CONFIG_SPARSEMEM_VMEMMAP
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
return vmemmap_populate_basepages(start, end, node, NULL);
}
#endif