diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-20 03:18:30 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-20 03:18:30 +0200 |
commit | 270315b8235e3d10c2e360cff56c2f9e0915a252 (patch) | |
tree | 17a178c0f6c08026579c6c9f510a3dc0a01785da /arch | |
parent | Merge tag 'm68knommu-for-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/... (diff) | |
parent | RISC-V: Add page table dump support for uefi (diff) | |
download | linux-270315b8235e3d10c2e360cff56c2f9e0915a252.tar.xz linux-270315b8235e3d10c2e360cff56c2f9e0915a252.zip |
Merge tag 'riscv-for-linus-5.10-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux
Pull RISC-V updates from Palmer Dabbelt:
"A handful of cleanups and new features:
- A handful of cleanups for our page fault handling
- Improvements to how we fill out cacheinfo
- Support for EFI-based systems"
* tag 'riscv-for-linus-5.10-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (22 commits)
RISC-V: Add page table dump support for uefi
RISC-V: Add EFI runtime services
RISC-V: Add EFI stub support.
RISC-V: Add PE/COFF header for EFI stub
RISC-V: Implement late mapping page table allocation functions
RISC-V: Add early ioremap support
RISC-V: Move DT mapping outof fixmap
RISC-V: Fix duplicate included thread_info.h
riscv/mm/fault: Set FAULT_FLAG_INSTRUCTION flag in do_page_fault()
riscv/mm/fault: Fix inline placement in vmalloc_fault() declaration
riscv: Add cache information in AUX vector
riscv: Define AT_VECTOR_SIZE_ARCH for ARCH_DLINFO
riscv: Set more data to cacheinfo
riscv/mm/fault: Move access error check to function
riscv/mm/fault: Move FAULT_FLAG_WRITE handling in do_page_fault()
riscv/mm/fault: Simplify mm_fault_error()
riscv/mm/fault: Move fault error handling to mm_fault_error()
riscv/mm/fault: Simplify fault error handling
riscv/mm/fault: Move vmalloc fault handling to vmalloc_fault()
riscv/mm/fault: Move bad area handling to bad_area()
...
Diffstat (limited to 'arch')
-rw-r--r-- | arch/riscv/Kconfig | 25 | ||||
-rw-r--r-- | arch/riscv/Makefile | 1 | ||||
-rw-r--r-- | arch/riscv/configs/defconfig | 1 | ||||
-rw-r--r-- | arch/riscv/include/asm/Kbuild | 1 | ||||
-rw-r--r-- | arch/riscv/include/asm/cacheinfo.h | 5 | ||||
-rw-r--r-- | arch/riscv/include/asm/efi.h | 55 | ||||
-rw-r--r-- | arch/riscv/include/asm/elf.h | 13 | ||||
-rw-r--r-- | arch/riscv/include/asm/fixmap.h | 16 | ||||
-rw-r--r-- | arch/riscv/include/asm/io.h | 1 | ||||
-rw-r--r-- | arch/riscv/include/asm/mmu.h | 2 | ||||
-rw-r--r-- | arch/riscv/include/asm/pgtable.h | 5 | ||||
-rw-r--r-- | arch/riscv/include/asm/sections.h | 13 | ||||
-rw-r--r-- | arch/riscv/include/uapi/asm/auxvec.h | 24 | ||||
-rw-r--r-- | arch/riscv/kernel/Makefile | 2 | ||||
-rw-r--r-- | arch/riscv/kernel/cacheinfo.c | 98 | ||||
-rw-r--r-- | arch/riscv/kernel/efi-header.S | 111 | ||||
-rw-r--r-- | arch/riscv/kernel/efi.c | 96 | ||||
-rw-r--r-- | arch/riscv/kernel/head.S | 18 | ||||
-rw-r--r-- | arch/riscv/kernel/head.h | 2 | ||||
-rw-r--r-- | arch/riscv/kernel/image-vars.h | 51 | ||||
-rw-r--r-- | arch/riscv/kernel/setup.c | 18 | ||||
-rw-r--r-- | arch/riscv/kernel/vmlinux.lds.S | 23 | ||||
-rw-r--r-- | arch/riscv/mm/fault.c | 356 | ||||
-rw-r--r-- | arch/riscv/mm/init.c | 190 | ||||
-rw-r--r-- | arch/riscv/mm/ptdump.c | 48 |
25 files changed, 936 insertions, 239 deletions
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b7821ac36d28..483fc555fc34 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -38,6 +38,7 @@ config RISCV select GENERIC_ARCH_TOPOLOGY if SMP select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS + select GENERIC_EARLY_IOREMAP select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO select GENERIC_IOREMAP select GENERIC_IRQ_MULTI_HANDLER @@ -388,6 +389,28 @@ config CMDLINE_FORCE endchoice +config EFI_STUB + bool + +config EFI + bool "UEFI runtime support" + depends on OF + select LIBFDT + select UCS2_STRING + select EFI_PARAMS_FROM_FDT + select EFI_STUB + select EFI_GENERIC_STUB + select EFI_RUNTIME_WRAPPERS + select RISCV_ISA_C + depends on MMU + default y + help + This option provides support for runtime services provided + by UEFI firmware (such as non-volatile variables, realtime + clock, and platform reset). A UEFI stub is also provided to + allow the kernel to be booted as an EFI application. This + is only useful on systems that have UEFI firmware. + endmenu config BUILTIN_DTB @@ -400,3 +423,5 @@ menu "Power management options" source "kernel/power/Kconfig" endmenu + +source "drivers/firmware/Kconfig" diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index fb6e37db836d..10df59f28add 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -80,6 +80,7 @@ head-y := arch/riscv/kernel/head.o core-y += arch/riscv/ libs-y += arch/riscv/lib/ +libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a PHONY += vdso_install vdso_install: diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index d58c93efb603..d222d353d86d 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -130,3 +130,4 @@ CONFIG_DEBUG_BLOCK_EXT_DEVT=y # CONFIG_RUNTIME_TESTING_MENU is not set CONFIG_MEMTEST=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_EFI=y diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 3d9410bb4de0..59dd7be55005 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +generic-y += early_ioremap.h generic-y += extable.h generic-y += flat.h generic-y += kvm_para.h diff --git a/arch/riscv/include/asm/cacheinfo.h b/arch/riscv/include/asm/cacheinfo.h index 5d9662e9aba8..d1a365215ec0 100644 --- a/arch/riscv/include/asm/cacheinfo.h +++ b/arch/riscv/include/asm/cacheinfo.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 SiFive + */ #ifndef _ASM_RISCV_CACHEINFO_H #define _ASM_RISCV_CACHEINFO_H @@ -11,5 +14,7 @@ struct riscv_cacheinfo_ops { }; void riscv_set_cacheinfo_ops(struct riscv_cacheinfo_ops *ops); +uintptr_t get_cache_size(u32 level, enum cache_type type); +uintptr_t get_cache_geometry(u32 level, enum cache_type type); #endif /* _ASM_RISCV_CACHEINFO_H */ diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h new file mode 100644 index 000000000000..7542282f1141 --- /dev/null +++ b/arch/riscv/include/asm/efi.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef _ASM_EFI_H +#define _ASM_EFI_H + +#include <asm/csr.h> +#include <asm/io.h> +#include <asm/mmu_context.h> +#include <asm/ptrace.h> +#include <asm/tlbflush.h> + +#ifdef CONFIG_EFI +extern void efi_init(void); +#else +#define efi_init() +#endif + +int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); +int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); + +#define arch_efi_call_virt_setup() efi_virtmap_load() +#define arch_efi_call_virt_teardown() efi_virtmap_unload() + +#define arch_efi_call_virt(p, f, args...) p->f(args) + +#define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE) + +/* on RISC-V, the FDT may be located anywhere in system RAM */ +static inline unsigned long efi_get_max_fdt_addr(unsigned long image_addr) +{ + return ULONG_MAX; +} + +/* Load initrd at enough distance from DRAM start */ +static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr) +{ + return image_addr + SZ_256M; +} + +#define alloc_screen_info(x...) (&screen_info) + +static inline void free_screen_info(struct screen_info *si) +{ +} + +static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) +{ +} + +void efi_virtmap_load(void); +void efi_virtmap_unload(void); + +#endif /* _ASM_EFI_H */ diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index d83a4efd052b..5c725e1df58b 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -11,6 +11,7 @@ #include <uapi/asm/elf.h> #include <asm/auxvec.h> #include <asm/byteorder.h> +#include <asm/cacheinfo.h> /* * These are used to set parameters in the core dumps. @@ -61,6 +62,18 @@ extern unsigned long elf_hwcap; do { \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ (elf_addr_t)current->mm->context.vdso); \ + NEW_AUX_ENT(AT_L1I_CACHESIZE, \ + get_cache_size(1, CACHE_TYPE_INST)); \ + NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, \ + get_cache_geometry(1, CACHE_TYPE_INST)); \ + NEW_AUX_ENT(AT_L1D_CACHESIZE, \ + get_cache_size(1, CACHE_TYPE_DATA)); \ + NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, \ + get_cache_geometry(1, CACHE_TYPE_DATA)); \ + NEW_AUX_ENT(AT_L2_CACHESIZE, \ + get_cache_size(2, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, \ + get_cache_geometry(2, CACHE_TYPE_UNIFIED)); \ } while (0) #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h index 1ff075a8dfc7..54cbf07fb4e9 100644 --- a/arch/riscv/include/asm/fixmap.h +++ b/arch/riscv/include/asm/fixmap.h @@ -22,14 +22,24 @@ */ enum fixed_addresses { FIX_HOLE, -#define FIX_FDT_SIZE SZ_1M - FIX_FDT_END, - FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1, FIX_PTE, FIX_PMD, FIX_TEXT_POKE1, FIX_TEXT_POKE0, FIX_EARLYCON_MEM_BASE, + + __end_of_permanent_fixed_addresses, + /* + * Temporary boot-time mappings, used by early_ioremap(), + * before ioremap() is functional. + */ +#define NR_FIX_BTMAPS (SZ_256K / PAGE_SIZE) +#define FIX_BTMAPS_SLOTS 7 +#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) + + FIX_BTMAP_END = __end_of_permanent_fixed_addresses, + FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1, + __end_of_fixed_addresses }; diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 3835c3295dc5..c025a746a148 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/pgtable.h> #include <asm/mmiowb.h> +#include <asm/early_ioremap.h> /* * MMIO access functions are separated out to break dependency cycles diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index 967eacb01ab5..dabcf2cfb3dc 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -20,6 +20,8 @@ typedef struct { #endif } mm_context_t; +void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, + phys_addr_t sz, pgprot_t prot); #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_MMU_H */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index eaea1f717010..183f1f4b2ae6 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -100,6 +100,10 @@ #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) +#define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) +#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) +#define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \ + | _PAGE_EXEC) #define PAGE_TABLE __pgprot(_PAGE_TABLE) @@ -464,6 +468,7 @@ static inline void __kernel_map_pages(struct page *page, int numpages, int enabl #define kern_addr_valid(addr) (1) /* FIXME */ extern void *dtb_early_va; +extern uintptr_t dtb_early_pa; void setup_bootmem(void); void paging_init(void); diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h new file mode 100644 index 000000000000..3a9971b1210f --- /dev/null +++ b/arch/riscv/include/asm/sections.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef __ASM_SECTIONS_H +#define __ASM_SECTIONS_H + +#include <asm-generic/sections.h> + +extern char _start[]; +extern char _start_kernel[]; + +#endif /* __ASM_SECTIONS_H */ diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index d86cb17bbabe..32c73ba1d531 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -10,4 +10,28 @@ /* vDSO location */ #define AT_SYSINFO_EHDR 33 +/* + * The set of entries below represent more extensive information + * about the caches, in the form of two entry per cache type, + * one entry containing the cache size in bytes, and the other + * containing the cache line size in bytes in the bottom 16 bits + * and the cache associativity in the next 16 bits. + * + * The associativity is such that if N is the 16-bit value, the + * cache is N way set associative. A value if 0xffff means fully + * associative, a value of 1 means directly mapped. + * + * For all these fields, a value of 0 means that the information + * is not known. + */ +#define AT_L1I_CACHESIZE 40 +#define AT_L1I_CACHEGEOMETRY 41 +#define AT_L1D_CACHESIZE 42 +#define AT_L1D_CACHEGEOMETRY 43 +#define AT_L2_CACHESIZE 44 +#define AT_L2_CACHEGEOMETRY 45 + +/* entries in ARCH_DLINFO */ +#define AT_VECTOR_SIZE_ARCH 7 + #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index dc93710f0b2f..fa896c5f7ccb 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -55,4 +55,6 @@ obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o +obj-$(CONFIG_EFI) += efi.o + clean: diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index bd0f122965c3..de59dd457b41 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -3,7 +3,6 @@ * Copyright (C) 2017 SiFive */ -#include <linux/cacheinfo.h> #include <linux/cpu.h> #include <linux/of.h> #include <linux/of_device.h> @@ -25,12 +24,84 @@ cache_get_priv_group(struct cacheinfo *this_leaf) return NULL; } -static void ci_leaf_init(struct cacheinfo *this_leaf, - struct device_node *node, - enum cache_type type, unsigned int level) +static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) +{ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id()); + struct cacheinfo *this_leaf; + int index; + + for (index = 0; index < this_cpu_ci->num_leaves; index++) { + this_leaf = this_cpu_ci->info_list + index; + if (this_leaf->level == level && this_leaf->type == type) + return this_leaf; + } + + return NULL; +} + +uintptr_t get_cache_size(u32 level, enum cache_type type) +{ + struct cacheinfo *this_leaf = get_cacheinfo(level, type); + + return this_leaf ? this_leaf->size : 0; +} + +uintptr_t get_cache_geometry(u32 level, enum cache_type type) +{ + struct cacheinfo *this_leaf = get_cacheinfo(level, type); + + return this_leaf ? (this_leaf->ways_of_associativity << 16 | + this_leaf->coherency_line_size) : + 0; +} + +static void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type, + unsigned int level, unsigned int size, + unsigned int sets, unsigned int line_size) { this_leaf->level = level; this_leaf->type = type; + this_leaf->size = size; + this_leaf->number_of_sets = sets; + this_leaf->coherency_line_size = line_size; + + /* + * If the cache is fully associative, there is no need to + * check the other properties. + */ + if (sets == 1) + return; + + /* + * Set the ways number for n-ways associative, make sure + * all properties are big than zero. + */ + if (sets > 0 && size > 0 && line_size > 0) + this_leaf->ways_of_associativity = (size / sets) / line_size; +} + +static void fill_cacheinfo(struct cacheinfo **this_leaf, + struct device_node *node, unsigned int level) +{ + unsigned int size, sets, line_size; + + if (!of_property_read_u32(node, "cache-size", &size) && + !of_property_read_u32(node, "cache-block-size", &line_size) && + !of_property_read_u32(node, "cache-sets", &sets)) { + ci_leaf_init((*this_leaf)++, CACHE_TYPE_UNIFIED, level, size, sets, line_size); + } + + if (!of_property_read_u32(node, "i-cache-size", &size) && + !of_property_read_u32(node, "i-cache-sets", &sets) && + !of_property_read_u32(node, "i-cache-block-size", &line_size)) { + ci_leaf_init((*this_leaf)++, CACHE_TYPE_INST, level, size, sets, line_size); + } + + if (!of_property_read_u32(node, "d-cache-size", &size) && + !of_property_read_u32(node, "d-cache-sets", &sets) && + !of_property_read_u32(node, "d-cache-block-size", &line_size)) { + ci_leaf_init((*this_leaf)++, CACHE_TYPE_DATA, level, size, sets, line_size); + } } static int __init_cache_level(unsigned int cpu) @@ -83,29 +154,24 @@ static int __populate_cache_leaves(unsigned int cpu) struct device_node *prev = NULL; int levels = 1, level = 1; - if (of_property_read_bool(np, "cache-size")) - ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level); - if (of_property_read_bool(np, "i-cache-size")) - ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level); - if (of_property_read_bool(np, "d-cache-size")) - ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level); + /* Level 1 caches in cpu node */ + fill_cacheinfo(&this_leaf, np, level); + /* Next level caches in cache nodes */ prev = np; while ((np = of_find_next_cache_node(np))) { of_node_put(prev); prev = np; + if (!of_device_is_compatible(np, "cache")) break; if (of_property_read_u32(np, "cache-level", &level)) break; if (level <= levels) break; - if (of_property_read_bool(np, "cache-size")) - ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level); - if (of_property_read_bool(np, "i-cache-size")) - ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level); - if (of_property_read_bool(np, "d-cache-size")) - ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level); + + fill_cacheinfo(&this_leaf, np, level); + levels = level; } of_node_put(np); diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S new file mode 100644 index 000000000000..8e733aa48ba6 --- /dev/null +++ b/arch/riscv/kernel/efi-header.S @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Adapted from arch/arm64/kernel/efi-header.S + */ + +#include <linux/pe.h> +#include <linux/sizes.h> + + .macro __EFI_PE_HEADER + .long PE_MAGIC +coff_header: +#ifdef CONFIG_64BIT + .short IMAGE_FILE_MACHINE_RISCV64 // Machine +#else + .short IMAGE_FILE_MACHINE_RISCV32 // Machine +#endif + .short section_count // NumberOfSections + .long 0 // TimeDateStamp + .long 0 // PointerToSymbolTable + .long 0 // NumberOfSymbols + .short section_table - optional_header // SizeOfOptionalHeader + .short IMAGE_FILE_DEBUG_STRIPPED | \ + IMAGE_FILE_EXECUTABLE_IMAGE | \ + IMAGE_FILE_LINE_NUMS_STRIPPED // Characteristics + +optional_header: +#ifdef CONFIG_64BIT + .short PE_OPT_MAGIC_PE32PLUS // PE32+ format +#else + .short PE_OPT_MAGIC_PE32 // PE32 format +#endif + .byte 0x02 // MajorLinkerVersion + .byte 0x14 // MinorLinkerVersion + .long __pecoff_text_end - efi_header_end // SizeOfCode + .long __pecoff_data_virt_size // SizeOfInitializedData + .long 0 // SizeOfUninitializedData + .long __efistub_efi_pe_entry - _start // AddressOfEntryPoint + .long efi_header_end - _start // BaseOfCode +#ifdef CONFIG_32BIT + .long __pecoff_text_end - _start // BaseOfData +#endif + +extra_header_fields: + .quad 0 // ImageBase + .long PECOFF_SECTION_ALIGNMENT // SectionAlignment + .long PECOFF_FILE_ALIGNMENT // FileAlignment + .short 0 // MajorOperatingSystemVersion + .short 0 // MinorOperatingSystemVersion + .short LINUX_EFISTUB_MAJOR_VERSION // MajorImageVersion + .short LINUX_EFISTUB_MINOR_VERSION // MinorImageVersion + .short 0 // MajorSubsystemVersion + .short 0 // MinorSubsystemVersion + .long 0 // Win32VersionValue + + .long _end - _start // SizeOfImage + + // Everything before the kernel image is considered part of the header + .long efi_header_end - _start // SizeOfHeaders + .long 0 // CheckSum + .short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem + .short 0 // DllCharacteristics + .quad 0 // SizeOfStackReserve + .quad 0 // SizeOfStackCommit + .quad 0 // SizeOfHeapReserve + .quad 0 // SizeOfHeapCommit + .long 0 // LoaderFlags + .long (section_table - .) / 8 // NumberOfRvaAndSizes + + .quad 0 // ExportTable + .quad 0 // ImportTable + .quad 0 // ResourceTable + .quad 0 // ExceptionTable + .quad 0 // CertificationTable + .quad 0 // BaseRelocationTable + + // Section table +section_table: + .ascii ".text\0\0\0" + .long __pecoff_text_end - efi_header_end // VirtualSize + .long efi_header_end - _start // VirtualAddress + .long __pecoff_text_end - efi_header_end // SizeOfRawData + .long efi_header_end - _start // PointerToRawData + + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long IMAGE_SCN_CNT_CODE | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_EXECUTE // Characteristics + + .ascii ".data\0\0\0" + .long __pecoff_data_virt_size // VirtualSize + .long __pecoff_text_end - _start // VirtualAddress + .long __pecoff_data_raw_size // SizeOfRawData + .long __pecoff_text_end - _start // PointerToRawData + + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_WRITE // Characteristics + + .set section_count, (. - section_table) / 40 + + .balign 0x1000 +efi_header_end: + .endm diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c new file mode 100644 index 000000000000..024159298231 --- /dev/null +++ b/arch/riscv/kernel/efi.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Adapted from arch/arm64/kernel/efi.c + */ + +#include <linux/efi.h> +#include <linux/init.h> + +#include <asm/efi.h> +#include <asm/pgtable.h> +#include <asm/pgtable-bits.h> + +/* + * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be + * executable, everything else can be mapped with the XN bits + * set. Also take the new (optional) RO/XP bits into account. + */ +static __init pgprot_t efimem_to_pgprot_map(efi_memory_desc_t *md) +{ + u64 attr = md->attribute; + u32 type = md->type; + + if (type == EFI_MEMORY_MAPPED_IO) + return PAGE_KERNEL; + + /* R-- */ + if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) == + (EFI_MEMORY_XP | EFI_MEMORY_RO)) + return PAGE_KERNEL_READ; + + /* R-X */ + if (attr & EFI_MEMORY_RO) + return PAGE_KERNEL_READ_EXEC; + + /* RW- */ + if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) == + EFI_MEMORY_XP) || + type != EFI_RUNTIME_SERVICES_CODE) + return PAGE_KERNEL; + + /* RWX */ + return PAGE_KERNEL_EXEC; +} + +int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) +{ + pgprot_t prot = __pgprot(pgprot_val(efimem_to_pgprot_map(md)) & + ~(_PAGE_GLOBAL)); + int i; + + /* RISC-V maps one page at a time */ + for (i = 0; i < md->num_pages; i++) + create_pgd_mapping(mm->pgd, md->virt_addr + i * PAGE_SIZE, + md->phys_addr + i * PAGE_SIZE, + PAGE_SIZE, prot); + return 0; +} + +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) +{ + efi_memory_desc_t *md = data; + pte_t pte = READ_ONCE(*ptep); + unsigned long val; + + if (md->attribute & EFI_MEMORY_RO) { + val = pte_val(pte) & ~_PAGE_WRITE; + val = pte_val(pte) | _PAGE_READ; + pte = __pte(val); + } + if (md->attribute & EFI_MEMORY_XP) { + val = pte_val(pte) & ~_PAGE_EXEC; + pte = __pte(val); + } + set_pte(ptep, pte); + + return 0; +} + +int __init efi_set_mapping_permissions(struct mm_struct *mm, + efi_memory_desc_t *md) +{ + BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_DATA); + + /* + * Calling apply_to_page_range() is only safe on regions that are + * guaranteed to be mapped down to pages. Since we are only called + * for regions that have been mapped using efi_create_mapping() above + * (and this is checked by the generic Memory Attributes table parsing + * routines), there is no need to check that again here. + */ + return apply_to_page_range(mm, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + set_permissions, md); +} diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 0a4e81b8dc79..11e2a4fe66e0 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -3,7 +3,6 @@ * Copyright (C) 2012 Regents of the University of California */ -#include <asm/thread_info.h> #include <asm/asm-offsets.h> #include <asm/asm.h> #include <linux/init.h> @@ -13,6 +12,7 @@ #include <asm/csr.h> #include <asm/hwcap.h> #include <asm/image.h> +#include "efi-header.S" __HEAD ENTRY(_start) @@ -22,10 +22,18 @@ ENTRY(_start) * Do not modify it without modifying the structure and all bootloaders * that expects this header format!! */ +#ifdef CONFIG_EFI + /* + * This instruction decodes to "MZ" ASCII required by UEFI. + */ + c.li s4,-13 + j _start_kernel +#else /* jump to start kernel */ j _start_kernel /* reserved */ .word 0 +#endif .balign 8 #if __riscv_xlen == 64 /* Image load offset(2MB) from start of RAM */ @@ -43,7 +51,14 @@ ENTRY(_start) .ascii RISCV_IMAGE_MAGIC .balign 4 .ascii RISCV_IMAGE_MAGIC2 +#ifdef CONFIG_EFI + .word pe_head_start - _start +pe_head_start: + + __EFI_PE_HEADER +#else .word 0 +#endif .align 2 #ifdef CONFIG_MMU @@ -259,7 +274,6 @@ clear_bss_done: #endif /* Start the kernel */ call soc_early_init - call parse_dtb tail start_kernel .Lsecondary_start: diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h index 105fb0496b24..b48dda3d04f6 100644 --- a/arch/riscv/kernel/head.h +++ b/arch/riscv/kernel/head.h @@ -16,6 +16,4 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa); extern void *__cpu_up_stack_pointer[]; extern void *__cpu_up_task_pointer[]; -void __init parse_dtb(void); - #endif /* __ASM_HEAD_H */ diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h new file mode 100644 index 000000000000..8c212efb37a6 --- /dev/null +++ b/arch/riscv/kernel/image-vars.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Linker script variables to be set after section resolution, as + * ld.lld does not like variables assigned before SECTIONS is processed. + * Based on arch/arm64/kerne/image-vars.h + */ +#ifndef __RISCV_KERNEL_IMAGE_VARS_H +#define __RISCV_KERNEL_IMAGE_VARS_H + +#ifndef LINKER_SCRIPT +#error This file should only be included in vmlinux.lds.S +#endif + +#ifdef CONFIG_EFI + +/* + * The EFI stub has its own symbol namespace prefixed by __efistub_, to + * isolate it from the kernel proper. The following symbols are legally + * accessed by the stub, so provide some aliases to make them accessible. + * Only include data symbols here, or text symbols of functions that are + * guaranteed to be safe when executed at another offset than they were + * linked at. The routines below are all implemented in assembler in a + * position independent manner + */ +__efistub_memcmp = memcmp; +__efistub_memchr = memchr; +__efistub_memcpy = memcpy; +__efistub_memmove = memmove; +__efistub_memset = memset; +__efistub_strlen = strlen; +__efistub_strnlen = strnlen; +__efistub_strcmp = strcmp; +__efistub_strncmp = strncmp; +__efistub_strrchr = strrchr; + +#ifdef CONFIG_KASAN +__efistub___memcpy = memcpy; +__efistub___memmove = memmove; +__efistub___memset = memset; +#endif + +__efistub__start = _start; +__efistub__start_kernel = _start_kernel; +__efistub__end = _end; +__efistub__edata = _edata; +__efistub_screen_info = screen_info; + +#endif + +#endif /* __RISCV_KERNEL_IMAGE_VARS_H */ diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 2c6dd329312b..4c96ac198e14 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -17,19 +17,22 @@ #include <linux/sched/task.h> #include <linux/swiotlb.h> #include <linux/smp.h> +#include <linux/efi.h> #include <asm/cpu_ops.h> +#include <asm/early_ioremap.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/thread_info.h> #include <asm/kasan.h> +#include <asm/efi.h> #include "head.h" -#ifdef CONFIG_DUMMY_CONSOLE -struct screen_info screen_info = { +#if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI) +struct screen_info screen_info __section(.data) = { .orig_video_lines = 30, .orig_video_cols = 80, .orig_video_mode = 0, @@ -48,8 +51,9 @@ atomic_t hart_lottery __section(.sdata); unsigned long boot_cpu_hartid; static DEFINE_PER_CPU(struct cpu, cpu_devices); -void __init parse_dtb(void) +static void __init parse_dtb(void) { + /* Early scan of device tree from init memory */ if (early_init_dt_scan(dtb_early_va)) return; @@ -62,6 +66,7 @@ void __init parse_dtb(void) void __init setup_arch(char **cmdline_p) { + parse_dtb(); init_mm.start_code = (unsigned long) _stext; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; @@ -69,14 +74,19 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; + early_ioremap_setup(); parse_early_param(); + efi_init(); setup_bootmem(); paging_init(); #if IS_ENABLED(CONFIG_BUILTIN_DTB) unflatten_and_copy_device_tree(); #else - unflatten_device_tree(); + if (early_init_dt_verify(__va(dtb_early_pa))) + unflatten_device_tree(); + else + pr_err("No DTB found in kernel mappings\n"); #endif #ifdef CONFIG_SWIOTLB diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 67db80e12d1f..3ffbd6cbdb86 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -10,6 +10,7 @@ #include <asm/cache.h> #include <asm/thread_info.h> #include <asm/set_memory.h> +#include "image-vars.h" #include <linux/sizes.h> OUTPUT_ARCH(riscv) @@ -17,6 +18,9 @@ ENTRY(_start) jiffies = jiffies_64; +PECOFF_SECTION_ALIGNMENT = 0x1000; +PECOFF_FILE_ALIGNMENT = 0x200; + SECTIONS { /* Beginning of code and text segment */ @@ -66,6 +70,11 @@ SECTIONS _etext = .; } +#ifdef CONFIG_EFI + . = ALIGN(PECOFF_SECTION_ALIGNMENT); + __pecoff_text_end = .; +#endif + INIT_DATA_SECTION(16) /* Start of data section */ @@ -84,16 +93,26 @@ SECTIONS .sdata : { __global_pointer$ = . + 0x800; *(.sdata*) - /* End of data section */ - _edata = .; } +#ifdef CONFIG_EFI + .pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); } + __pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end); +#endif + + /* End of data section */ + _edata = .; + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) .rel.dyn : { *(.rel.dyn*) } +#ifdef CONFIG_EFI + . = ALIGN(PECOFF_SECTION_ALIGNMENT); + __pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end); +#endif _end = .; STABS_DEBUG diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 716d64e36f83..1359e21c0c62 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -19,6 +19,167 @@ #include "../kernel/head.h" +static inline void no_context(struct pt_regs *regs, unsigned long addr) +{ + /* Are we prepared to handle this kernel fault? */ + if (fixup_exception(regs)) + return; + + /* + * Oops. The kernel tried to access some bad page. We'll have to + * terminate things with extreme prejudice. + */ + bust_spinlocks(1); + pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n", + (addr < PAGE_SIZE) ? "NULL pointer dereference" : + "paging request", addr); + die(regs, "Oops"); + do_exit(SIGKILL); +} + +static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) +{ + if (fault & VM_FAULT_OOM) { + /* + * We ran out of memory, call the OOM killer, and return the userspace + * (which will retry the fault, or kill us if we got oom-killed). + */ + if (!user_mode(regs)) { + no_context(regs, addr); + return; + } + pagefault_out_of_memory(); + return; + } else if (fault & VM_FAULT_SIGBUS) { + /* Kernel mode? Handle exceptions or die */ + if (!user_mode(regs)) { + no_context(regs, addr); + return; + } + do_trap(regs, SIGBUS, BUS_ADRERR, addr); + return; + } + BUG(); +} + +static inline void bad_area(struct pt_regs *regs, struct mm_struct *mm, int code, unsigned long addr) +{ + /* + * Something tried to access memory that isn't in our memory map. + * Fix it, but check if it's kernel or user first. + */ + mmap_read_unlock(mm); + /* User mode accesses just cause a SIGSEGV */ + if (user_mode(regs)) { + do_trap(regs, SIGSEGV, code, addr); + return; + } + + no_context(regs, addr); +} + +static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long addr) +{ + pgd_t *pgd, *pgd_k; + pud_t *pud, *pud_k; + p4d_t *p4d, *p4d_k; + pmd_t *pmd, *pmd_k; + pte_t *pte_k; + int index; + + /* User mode accesses just cause a SIGSEGV */ + if (user_mode(regs)) + return do_trap(regs, SIGSEGV, code, addr); + + /* + * Synchronize this task's top level page-table + * with the 'reference' page table. + * + * Do _not_ use "tsk->active_mm->pgd" here. + * We might be inside an interrupt in the middle + * of a task switch. + */ + index = pgd_index(addr); + pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index; + pgd_k = init_mm.pgd + index; + + if (!pgd_present(*pgd_k)) { + no_context(regs, addr); + return; + } + set_pgd(pgd, *pgd_k); + + p4d = p4d_offset(pgd, addr); + p4d_k = p4d_offset(pgd_k, addr); + if (!p4d_present(*p4d_k)) { + no_context(regs, addr); + return; + } + + pud = pud_offset(p4d, addr); + pud_k = pud_offset(p4d_k, addr); + if (!pud_present(*pud_k)) { + no_context(regs, addr); + return; + } + + /* + * Since the vmalloc area is global, it is unnecessary + * to copy individual PTEs + */ + pmd = pmd_offset(pud, addr); + pmd_k = pmd_offset(pud_k, addr); + if (!pmd_present(*pmd_k)) { + no_context(regs, addr); + return; + } + set_pmd(pmd, *pmd_k); + + /* + * Make sure the actual PTE exists as well to + * catch kernel vmalloc-area accesses to non-mapped + * addresses. If we don't do this, this will just + * silently loop forever. + */ + pte_k = pte_offset_kernel(pmd_k, addr); + if (!pte_present(*pte_k)) { + no_context(regs, addr); + return; + } + + /* + * The kernel assumes that TLBs don't cache invalid + * entries, but in RISC-V, SFENCE.VMA specifies an + * ordering constraint, not a cache flush; it is + * necessary even after writing invalid entries. + */ + local_flush_tlb_page(addr); +} + +static inline bool access_error(unsigned long cause, struct vm_area_struct *vma) +{ + switch (cause) { + case EXC_INST_PAGE_FAULT: + if (!(vma->vm_flags & VM_EXEC)) { + return true; + } + break; + case EXC_LOAD_PAGE_FAULT: + if (!(vma->vm_flags & VM_READ)) { + return true; + } + break; + case EXC_STORE_PAGE_FAULT: + if (!(vma->vm_flags & VM_WRITE)) { + return true; + } + break; + default: + panic("%s: unhandled cause %lu", __func__, cause); + } + return false; +} + /* * This routine handles page faults. It determines the address and the * problem, and then passes it off to one of the appropriate routines. @@ -48,8 +209,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs) * only copy the information from the master page table, * nothing more. */ - if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END))) - goto vmalloc_fault; + if (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END))) { + vmalloc_fault(regs, code, addr); + return; + } /* Enable interrupts if they were enabled in the parent context. */ if (likely(regs->status & SR_PIE)) @@ -59,25 +222,37 @@ asmlinkage void do_page_fault(struct pt_regs *regs) * If we're in an interrupt, have no user context, or are running * in an atomic region, then we must not take the fault. */ - if (unlikely(faulthandler_disabled() || !mm)) - goto no_context; + if (unlikely(faulthandler_disabled() || !mm)) { + no_context(regs, addr); + return; + } if (user_mode(regs)) flags |= FAULT_FLAG_USER; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); + if (cause == EXC_STORE_PAGE_FAULT) + flags |= FAULT_FLAG_WRITE; + else if (cause == EXC_INST_PAGE_FAULT) + flags |= FAULT_FLAG_INSTRUCTION; retry: mmap_read_lock(mm); vma = find_vma(mm, addr); - if (unlikely(!vma)) - goto bad_area; + if (unlikely(!vma)) { + bad_area(regs, mm, code, addr); + return; + } if (likely(vma->vm_start <= addr)) goto good_area; - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) - goto bad_area; - if (unlikely(expand_stack(vma, addr))) - goto bad_area; + if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { + bad_area(regs, mm, code, addr); + return; + } + if (unlikely(expand_stack(vma, addr))) { + bad_area(regs, mm, code, addr); + return; + } /* * Ok, we have a good vm_area for this memory access, so @@ -86,22 +261,9 @@ retry: good_area: code = SEGV_ACCERR; - switch (cause) { - case EXC_INST_PAGE_FAULT: - if (!(vma->vm_flags & VM_EXEC)) - goto bad_area; - break; - case EXC_LOAD_PAGE_FAULT: - if (!(vma->vm_flags & VM_READ)) - goto bad_area; - break; - case EXC_STORE_PAGE_FAULT: - if (!(vma->vm_flags & VM_WRITE)) - goto bad_area; - flags |= FAULT_FLAG_WRITE; - break; - default: - panic("%s: unhandled cause %lu", __func__, cause); + if (unlikely(access_error(cause, vma))) { + bad_area(regs, mm, code, addr); + return; } /* @@ -119,144 +281,22 @@ good_area: if (fault_signal_pending(fault, regs)) return; - if (unlikely(fault & VM_FAULT_ERROR)) { - if (fault & VM_FAULT_OOM) - goto out_of_memory; - else if (fault & VM_FAULT_SIGBUS) - goto do_sigbus; - BUG(); - } - - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; + if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { + flags |= FAULT_FLAG_TRIED; - /* - * No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ - goto retry; - } + /* + * No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + goto retry; } mmap_read_unlock(mm); - return; - /* - * Something tried to access memory that isn't in our memory map. - * Fix it, but check if it's kernel or user first. - */ -bad_area: - mmap_read_unlock(mm); - /* User mode accesses just cause a SIGSEGV */ - if (user_mode(regs)) { - do_trap(regs, SIGSEGV, code, addr); + if (unlikely(fault & VM_FAULT_ERROR)) { + mm_fault_error(regs, addr, fault); return; } - -no_context: - /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs)) - return; - - /* - * Oops. The kernel tried to access some bad page. We'll have to - * terminate things with extreme prejudice. - */ - bust_spinlocks(1); - pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n", - (addr < PAGE_SIZE) ? "NULL pointer dereference" : - "paging request", addr); - die(regs, "Oops"); - do_exit(SIGKILL); - - /* - * We ran out of memory, call the OOM killer, and return the userspace - * (which will retry the fault, or kill us if we got oom-killed). - */ -out_of_memory: - mmap_read_unlock(mm); - if (!user_mode(regs)) - goto no_context; - pagefault_out_of_memory(); - return; - -do_sigbus: - mmap_read_unlock(mm); - /* Kernel mode? Handle exceptions or die */ - if (!user_mode(regs)) - goto no_context; - do_trap(regs, SIGBUS, BUS_ADRERR, addr); return; - -vmalloc_fault: - { - pgd_t *pgd, *pgd_k; - pud_t *pud, *pud_k; - p4d_t *p4d, *p4d_k; - pmd_t *pmd, *pmd_k; - pte_t *pte_k; - int index; - - /* User mode accesses just cause a SIGSEGV */ - if (user_mode(regs)) - return do_trap(regs, SIGSEGV, code, addr); - - /* - * Synchronize this task's top level page-table - * with the 'reference' page table. - * - * Do _not_ use "tsk->active_mm->pgd" here. - * We might be inside an interrupt in the middle - * of a task switch. - */ - index = pgd_index(addr); - pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index; - pgd_k = init_mm.pgd + index; - - if (!pgd_present(*pgd_k)) - goto no_context; - set_pgd(pgd, *pgd_k); - - p4d = p4d_offset(pgd, addr); - p4d_k = p4d_offset(pgd_k, addr); - if (!p4d_present(*p4d_k)) - goto no_context; - - pud = pud_offset(p4d, addr); - pud_k = pud_offset(p4d_k, addr); - if (!pud_present(*pud_k)) - goto no_context; - - /* - * Since the vmalloc area is global, it is unnecessary - * to copy individual PTEs - */ - pmd = pmd_offset(pud, addr); - pmd_k = pmd_offset(pud_k, addr); - if (!pmd_present(*pmd_k)) - goto no_context; - set_pmd(pmd, *pmd_k); - - /* - * Make sure the actual PTE exists as well to - * catch kernel vmalloc-area accesses to non-mapped - * addresses. If we don't do this, this will just - * silently loop forever. - */ - pte_k = pte_offset_kernel(pmd_k, addr); - if (!pte_present(*pte_k)) - goto no_context; - - /* - * The kernel assumes that TLBs don't cache invalid - * entries, but in RISC-V, SFENCE.VMA specifies an - * ordering constraint, not a cache flush; it is - * necessary even after writing invalid entries. - */ - local_flush_tlb_page(addr); - - return; - } } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 1dc89303b679..ea933b789a88 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -28,7 +28,18 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] EXPORT_SYMBOL(empty_zero_page); extern char _start[]; -void *dtb_early_va; +#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 void __init zone_sizes_init(void) { @@ -141,8 +152,6 @@ disable: } #endif /* CONFIG_BLK_DEV_INITRD */ -static phys_addr_t dtb_early_pa __initdata; - void __init setup_bootmem(void) { phys_addr_t mem_size = 0; @@ -194,6 +203,8 @@ void __init setup_bootmem(void) } #ifdef CONFIG_MMU +static struct pt_alloc_ops pt_ops; + unsigned long va_pa_offset; EXPORT_SYMBOL(va_pa_offset); unsigned long pfn_base; @@ -202,7 +213,6 @@ EXPORT_SYMBOL(pfn_base); pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss; -static bool mmu_enabled; #define MAX_EARLY_MAPPING_SIZE SZ_128M @@ -224,27 +234,46 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) local_flush_tlb_page(addr); } -static pte_t *__init get_pte_virt(phys_addr_t pa) +static inline pte_t *__init get_pte_virt_early(phys_addr_t pa) { - if (mmu_enabled) { - clear_fixmap(FIX_PTE); - return (pte_t *)set_fixmap_offset(FIX_PTE, pa); - } else { - return (pte_t *)((uintptr_t)pa); - } + return (pte_t *)((uintptr_t)pa); } -static phys_addr_t __init alloc_pte(uintptr_t va) +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 *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_ON(!mmu_enabled); + 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 alloc_pte_late(uintptr_t va) +{ + unsigned long vaddr; + + vaddr = __get_free_page(GFP_KERNEL); + if (!vaddr || !pgtable_pte_page_ctor(virt_to_page(vaddr))) + BUG(); + 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) @@ -269,28 +298,46 @@ pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss; #endif pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE); -static pmd_t *__init get_pmd_virt(phys_addr_t pa) +static pmd_t *__init get_pmd_virt_early(phys_addr_t pa) { - if (mmu_enabled) { - clear_fixmap(FIX_PMD); - return (pmd_t *)set_fixmap_offset(FIX_PMD, pa); - } else { - return (pmd_t *)((uintptr_t)pa); - } + /* Before MMU is enabled */ + return (pmd_t *)((uintptr_t)pa); } -static phys_addr_t __init alloc_pmd(uintptr_t va) +static pmd_t *__init get_pmd_virt_fixmap(phys_addr_t pa) { - uintptr_t pmd_num; + clear_fixmap(FIX_PMD); + return (pmd_t *)set_fixmap_offset(FIX_PMD, pa); +} - if (mmu_enabled) - return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); +static pmd_t *get_pmd_virt_late(phys_addr_t pa) +{ + return (pmd_t *) __va(pa); +} + +static phys_addr_t __init alloc_pmd_early(uintptr_t va) +{ + uintptr_t pmd_num; pmd_num = (va - PAGE_OFFSET) >> PGDIR_SHIFT; BUG_ON(pmd_num >= NUM_EARLY_PMDS); return (uintptr_t)&early_pmd[pmd_num * PTRS_PER_PMD]; } +static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va) +{ + return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); +} + +static phys_addr_t 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) @@ -306,34 +353,34 @@ static void __init create_pmd_mapping(pmd_t *pmdp, } if (pmd_none(pmdp[pmd_idx])) { - pte_phys = alloc_pte(va); + pte_phys = pt_ops.alloc_pte(va); pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pte_phys), PAGE_TABLE); - ptep = get_pte_virt(pte_phys); + ptep = pt_ops.get_pte_virt(pte_phys); memset(ptep, 0, PAGE_SIZE); } else { pte_phys = PFN_PHYS(_pmd_pfn(pmdp[pmd_idx])); - ptep = get_pte_virt(pte_phys); + 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) alloc_pmd(__va) -#define get_pgd_next_virt(__pa) get_pmd_virt(__pa) +#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) alloc_pte(__va) -#define get_pgd_next_virt(__pa) get_pte_virt(__pa) +#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 #endif -static void __init create_pgd_mapping(pgd_t *pgdp, +void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, pgprot_t prot) { @@ -389,10 +436,13 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size) asmlinkage void __init setup_vm(uintptr_t dtb_pa) { - uintptr_t va, end_va; + uintptr_t va, pa, end_va; uintptr_t load_pa = (uintptr_t)(&_start); uintptr_t load_sz = (uintptr_t)(&_end) - load_pa; uintptr_t map_size = best_map_size(load_pa, MAX_EARLY_MAPPING_SIZE); +#ifndef __PAGETABLE_PMD_FOLDED + pmd_t fix_bmap_spmd, fix_bmap_epmd; +#endif va_pa_offset = PAGE_OFFSET - load_pa; pfn_base = PFN_DOWN(load_pa); @@ -408,6 +458,12 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) BUG_ON((load_pa % map_size) != 0); BUG_ON(load_sz > MAX_EARLY_MAPPING_SIZE); + 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); @@ -438,17 +494,44 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) load_pa + (va - PAGE_OFFSET), map_size, PAGE_KERNEL_EXEC); - /* Create fixed mapping for early FDT parsing */ - end_va = __fix_to_virt(FIX_FDT) + FIX_FDT_SIZE; - for (va = __fix_to_virt(FIX_FDT); va < end_va; va += PAGE_SIZE) - create_pte_mapping(fixmap_pte, va, - dtb_pa + (va - __fix_to_virt(FIX_FDT)), - PAGE_SIZE, PAGE_KERNEL); - - /* Save pointer to DTB for early FDT parsing */ - dtb_early_va = (void *)fix_to_virt(FIX_FDT) + (dtb_pa & ~PAGE_MASK); - /* Save physical address for memblock reservation */ + /* Create two consecutive PGD mappings for FDT early scan */ + pa = dtb_pa & ~(PGDIR_SIZE - 1); + create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, + pa, PGDIR_SIZE, PAGE_KERNEL); + create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE, + pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL); + dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1)); dtb_early_pa = 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) @@ -457,9 +540,16 @@ static void __init setup_vm_final(void) phys_addr_t pa, start, end; u64 i; - /* Set mmu_enabled flag */ - mmu_enabled = true; - + /** + * 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), @@ -488,6 +578,14 @@ static void __init setup_vm_final(void) /* 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) diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 0831c2e61a8f..ace74dec7492 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -3,6 +3,7 @@ * Copyright (C) 2019 SiFive */ +#include <linux/efi.h> #include <linux/init.h> #include <linux/debugfs.h> #include <linux/seq_file.h> @@ -49,6 +50,14 @@ struct addr_marker { const char *name; }; +/* Private information for debugfs */ +struct ptd_mm_info { + struct mm_struct *mm; + const struct addr_marker *markers; + unsigned long base_addr; + unsigned long end; +}; + static struct addr_marker address_markers[] = { #ifdef CONFIG_KASAN {KASAN_SHADOW_START, "Kasan shadow start"}, @@ -68,6 +77,28 @@ static struct addr_marker address_markers[] = { {-1, NULL}, }; +static struct ptd_mm_info kernel_ptd_info = { + .mm = &init_mm, + .markers = address_markers, + .base_addr = KERN_VIRT_START, + .end = ULONG_MAX, +}; + +#ifdef CONFIG_EFI +static struct addr_marker efi_addr_markers[] = { + { 0, "UEFI runtime start" }, + { SZ_1G, "UEFI runtime end" }, + { -1, NULL } +}; + +static struct ptd_mm_info efi_ptd_info = { + .mm = &efi_mm, + .markers = efi_addr_markers, + .base_addr = 0, + .end = SZ_2G, +}; +#endif + /* Page Table Entry */ struct prot_bits { u64 mask; @@ -245,22 +276,22 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, } } -static void ptdump_walk(struct seq_file *s) +static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo) { struct pg_state st = { .seq = s, - .marker = address_markers, + .marker = pinfo->markers, .level = -1, .ptdump = { .note_page = note_page, .range = (struct ptdump_range[]) { - {KERN_VIRT_START, ULONG_MAX}, + {pinfo->base_addr, pinfo->end}, {0, 0} } } }; - ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); + ptdump_walk_pgd(&st.ptdump, pinfo->mm, NULL); } void ptdump_check_wx(void) @@ -293,7 +324,7 @@ void ptdump_check_wx(void) static int ptdump_show(struct seq_file *m, void *v) { - ptdump_walk(m); + ptdump_walk(m, m->private); return 0; } @@ -308,8 +339,13 @@ static int ptdump_init(void) for (j = 0; j < ARRAY_SIZE(pte_bits); j++) pg_level[i].mask |= pte_bits[j].mask; - debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, + debugfs_create_file("kernel_page_tables", 0400, NULL, &kernel_ptd_info, &ptdump_fops); +#ifdef CONFIG_EFI + if (efi_enabled(EFI_RUNTIME_SERVICES)) + debugfs_create_file("efi_page_tables", 0400, NULL, &efi_ptd_info, + &ptdump_fops); +#endif return 0; } |