diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-13 09:15:42 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-13 09:15:42 -0800 |
commit | b89f311d7e25eb246376ac10de46d6ecc6b6ed5c (patch) | |
tree | c90e6ae9ec72551b0b0fae57d9670e144452d559 /arch/riscv/kernel | |
parent | 4218a96faf917b13ddc6af505bfb9b6a4e60bbc4 (diff) | |
parent | ffa7a9141bb70702744a312f904b190ca064bdd7 (diff) | |
download | linux-b89f311d7e25eb246376ac10de46d6ecc6b6ed5c.tar.gz linux-b89f311d7e25eb246376ac10de46d6ecc6b6ed5c.tar.bz2 linux-b89f311d7e25eb246376ac10de46d6ecc6b6ed5c.zip |
Merge tag 'riscv-for-linus-5.16-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux
Pull RISC-V updates from Palmer Dabbelt:
- Support for time namespaces in the VDSO, along with some associated
cleanups.
- Support for building rv32 randconfigs.
- Improvements to the XIP port that allow larger kernels to function
- Various device tree cleanups for both the SiFive and Microchip boards
- A handful of defconfig updates, including enabling Nouveau.
There are also various small cleanups.
* tag 'riscv-for-linus-5.16-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
riscv: defconfig: enable DRM_NOUVEAU
riscv/vdso: Drop unneeded part due to merge issue
riscv: remove .text section size limitation for XIP
riscv: dts: sifive: add missing compatible for plic
riscv: dts: microchip: add missing compatibles for clint and plic
riscv: dts: sifive: drop duplicated nodes and properties in sifive
riscv: dts: sifive: fix Unleashed board compatible
riscv: dts: sifive: use only generic JEDEC SPI NOR flash compatible
riscv: dts: microchip: use vendor compatible for Cadence SD4HC
riscv: dts: microchip: drop unused pinctrl-names
riscv: dts: microchip: drop duplicated MMC/SDHC node
riscv: dts: microchip: fix board compatible
riscv: dts: microchip: drop duplicated nodes
dt-bindings: mmc: cdns: document Microchip MPFS MMC/SDHCI controller
riscv: add rv32 and rv64 randconfig build targets
riscv: mm: don't advertise 1 num_asid for 0 asid bits
riscv: set default pm_power_off to NULL
riscv/vdso: Add support for time namespaces
Diffstat (limited to 'arch/riscv/kernel')
-rw-r--r-- | arch/riscv/kernel/head.S | 12 | ||||
-rw-r--r-- | arch/riscv/kernel/reset.c | 12 | ||||
-rw-r--r-- | arch/riscv/kernel/vdso.c | 250 | ||||
-rw-r--r-- | arch/riscv/kernel/vdso/vdso.lds.S | 3 | ||||
-rw-r--r-- | arch/riscv/kernel/vmlinux-xip.lds.S | 10 |
5 files changed, 228 insertions, 59 deletions
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 25ec50573957..f52f01ecbeea 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -20,10 +20,20 @@ REG_L t0, _xip_fixup add \reg, \reg, t0 .endm +.macro XIP_FIXUP_FLASH_OFFSET reg + la t1, __data_loc + li t0, XIP_OFFSET_MASK + and t1, t1, t0 + li t1, XIP_OFFSET + sub t0, t0, t1 + sub \reg, \reg, t0 +.endm _xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET #else .macro XIP_FIXUP_OFFSET reg .endm +.macro XIP_FIXUP_FLASH_OFFSET reg +.endm #endif /* CONFIG_XIP_KERNEL */ __HEAD @@ -267,6 +277,7 @@ pmp_done: la a3, hart_lottery mv a2, a3 XIP_FIXUP_OFFSET a2 + XIP_FIXUP_FLASH_OFFSET a3 lw t1, (a3) amoswap.w t0, t1, (a2) /* first time here if hart_lottery in RAM is not set */ @@ -305,6 +316,7 @@ clear_bss_done: XIP_FIXUP_OFFSET sp #ifdef CONFIG_BUILTIN_DTB la a0, __dtb_start + XIP_FIXUP_OFFSET a0 #else mv a0, s1 #endif /* CONFIG_BUILTIN_DTB */ diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c index ee5878d968cc..9c842c41684a 100644 --- a/arch/riscv/kernel/reset.c +++ b/arch/riscv/kernel/reset.c @@ -12,7 +12,7 @@ static void default_power_off(void) wait_for_interrupt(); } -void (*pm_power_off)(void) = default_power_off; +void (*pm_power_off)(void) = NULL; EXPORT_SYMBOL(pm_power_off); void machine_restart(char *cmd) @@ -23,10 +23,16 @@ void machine_restart(char *cmd) void machine_halt(void) { - pm_power_off(); + if (pm_power_off != NULL) + pm_power_off(); + else + default_power_off(); } void machine_power_off(void) { - pm_power_off(); + if (pm_power_off != NULL) + pm_power_off(); + else + default_power_off(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index b70956d80408..a9436a65161a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <asm/page.h> #include <asm/vdso.h> +#include <linux/time_namespace.h> #ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> @@ -25,14 +26,12 @@ extern char vdso_start[], vdso_end[]; enum vvar_pages { VVAR_DATA_PAGE_OFFSET, + VVAR_TIMENS_PAGE_OFFSET, VVAR_NR_PAGES, }; #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) -static unsigned int vdso_pages __ro_after_init; -static struct page **vdso_pagelist __ro_after_init; - /* * The vDSO data page. */ @@ -42,83 +41,228 @@ static union { } vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; -static int __init vdso_init(void) +struct __vdso_info { + const char *name; + const char *vdso_code_start; + const char *vdso_code_end; + unsigned long vdso_pages; + /* Data Mapping */ + struct vm_special_mapping *dm; + /* Code Mapping */ + struct vm_special_mapping *cm; +}; + +static struct __vdso_info vdso_info __ro_after_init = { + .name = "vdso", + .vdso_code_start = vdso_start, + .vdso_code_end = vdso_end, +}; + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + current->mm->context.vdso = (void *)new_vma->vm_start; + + return 0; +} + +static int __init __vdso_init(void) { unsigned int i; + struct page **vdso_pagelist; + unsigned long pfn; - vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; - vdso_pagelist = - kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL); - if (unlikely(vdso_pagelist == NULL)) { - pr_err("vdso: pagelist allocation failed\n"); - return -ENOMEM; + if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) { + pr_err("vDSO is not a valid ELF object!\n"); + return -EINVAL; } - for (i = 0; i < vdso_pages; i++) { - struct page *pg; + vdso_info.vdso_pages = ( + vdso_info.vdso_code_end - + vdso_info.vdso_code_start) >> + PAGE_SHIFT; + + vdso_pagelist = kcalloc(vdso_info.vdso_pages, + sizeof(struct page *), + GFP_KERNEL); + if (vdso_pagelist == NULL) + return -ENOMEM; + + /* Grab the vDSO code pages. */ + pfn = sym_to_pfn(vdso_info.vdso_code_start); + + for (i = 0; i < vdso_info.vdso_pages; i++) + vdso_pagelist[i] = pfn_to_page(pfn + i); + + vdso_info.cm->pages = vdso_pagelist; + + return 0; +} + +#ifdef CONFIG_TIME_NS +struct vdso_data *arch_get_vdso_data(void *vvar_page) +{ + return (struct vdso_data *)(vvar_page); +} + +/* + * The vvar mapping contains data for a specific time namespace, so when a task + * changes namespace we must unmap its vvar data for the old namespace. + * Subsequent faults will map in data for the new namespace. + * + * For more details see timens_setup_vdso_data(). + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + + mmap_read_lock(mm); - pg = virt_to_page(vdso_start + (i << PAGE_SHIFT)); - vdso_pagelist[i] = pg; + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long size = vma->vm_end - vma->vm_start; + + if (vma_is_special_mapping(vma, vdso_info.dm)) + zap_page_range(vma, vma->vm_start, size); } - vdso_pagelist[i] = virt_to_page(vdso_data); + mmap_read_unlock(mm); return 0; } + +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + if (likely(vma->vm_mm == current->mm)) + return current->nsproxy->time_ns->vvar_page; + + /* + * VM_PFNMAP | VM_IO protect .fault() handler from being called + * through interfaces like /proc/$pid/mem or + * process_vm_{readv,writev}() as long as there's no .access() + * in special_mapping_vmops. + * For more details check_vma_flags() and __access_remote_vm() + */ + WARN(1, "vvar_page accessed remotely"); + + return NULL; +} +#else +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + return NULL; +} +#endif + +static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *timens_page = find_timens_vvar_page(vma); + unsigned long pfn; + + switch (vmf->pgoff) { + case VVAR_DATA_PAGE_OFFSET: + if (timens_page) + pfn = page_to_pfn(timens_page); + else + pfn = sym_to_pfn(vdso_data); + break; +#ifdef CONFIG_TIME_NS + case VVAR_TIMENS_PAGE_OFFSET: + /* + * If a task belongs to a time namespace then a namespace + * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and + * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET + * offset. + * See also the comment near timens_setup_vdso_data(). + */ + if (!timens_page) + return VM_FAULT_SIGBUS; + pfn = sym_to_pfn(vdso_data); + break; +#endif /* CONFIG_TIME_NS */ + default: + return VM_FAULT_SIGBUS; + } + + return vmf_insert_pfn(vma, vmf->address, pfn); +} + +enum rv_vdso_map { + RV_VDSO_MAP_VVAR, + RV_VDSO_MAP_VDSO, +}; + +static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { + [RV_VDSO_MAP_VVAR] = { + .name = "[vvar]", + .fault = vvar_fault, + }, + [RV_VDSO_MAP_VDSO] = { + .name = "[vdso]", + .mremap = vdso_mremap, + }, +}; + +static int __init vdso_init(void) +{ + vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR]; + vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO]; + + return __vdso_init(); +} arch_initcall(vdso_init); -int arch_setup_additional_pages(struct linux_binprm *bprm, - int uses_interp) +static int __setup_additional_pages(struct mm_struct *mm, + struct linux_binprm *bprm, + int uses_interp) { - struct mm_struct *mm = current->mm; - unsigned long vdso_base, vdso_len; - int ret; + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; + void *ret; BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); - vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT; + vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT; + /* Be sure to map the data page */ + vdso_mapping_len = vdso_text_len + VVAR_SIZE; - if (mmap_write_lock_killable(mm)) - return -EINTR; - - vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { - ret = vdso_base; - goto end; + ret = ERR_PTR(vdso_base); + goto up_fail; } - mm->context.vdso = NULL; - ret = install_special_mapping(mm, vdso_base, VVAR_SIZE, - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); - if (unlikely(ret)) - goto end; + ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm); + if (IS_ERR(ret)) + goto up_fail; + vdso_base += VVAR_SIZE; + mm->context.vdso = (void *)vdso_base; ret = - install_special_mapping(mm, vdso_base + VVAR_SIZE, - vdso_pages << PAGE_SHIFT, + _install_special_mapping(mm, vdso_base, vdso_text_len, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), - vdso_pagelist); + vdso_info.cm); - if (unlikely(ret)) - goto end; + if (IS_ERR(ret)) + goto up_fail; - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ - mm->context.vdso = (void *)vdso_base + VVAR_SIZE; + return 0; -end: - mmap_write_unlock(mm); - return ret; +up_fail: + mm->context.vdso = NULL; + return PTR_ERR(ret); } -const char *arch_vma_name(struct vm_area_struct *vma) +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) - return "[vdso]"; - if (vma->vm_mm && (vma->vm_start == - (long)vma->vm_mm->context.vdso - VVAR_SIZE)) - return "[vdso_data]"; - return NULL; + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp); + mmap_write_unlock(mm); + + return ret; } diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index e9111f700af0..01d94aae5bf5 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -10,6 +10,9 @@ OUTPUT_ARCH(riscv) SECTIONS { PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); +#ifdef CONFIG_TIME_NS + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); +#endif . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S index 9c9f35091ef0..f5ed08262139 100644 --- a/arch/riscv/kernel/vmlinux-xip.lds.S +++ b/arch/riscv/kernel/vmlinux-xip.lds.S @@ -64,8 +64,11 @@ SECTIONS /* * From this point, stuff is considered writable and will be copied to RAM */ - __data_loc = ALIGN(16); /* location in file */ - . = LOAD_OFFSET + XIP_OFFSET; /* location in memory */ + __data_loc = ALIGN(PAGE_SIZE); /* location in file */ + . = KERNEL_LINK_ADDR + XIP_OFFSET; /* location in memory */ + +#undef LOAD_OFFSET +#define LOAD_OFFSET (KERNEL_LINK_ADDR + XIP_OFFSET - (__data_loc & XIP_OFFSET_MASK)) _sdata = .; /* Start of data section */ _data = .; @@ -96,7 +99,6 @@ SECTIONS KEEP(*(__soc_builtin_dtb_table)) __soc_builtin_dtb_table_end = .; } - PERCPU_SECTION(L1_CACHE_BYTES) . = ALIGN(8); .alternative : { @@ -122,6 +124,8 @@ SECTIONS BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + PERCPU_SECTION(L1_CACHE_BYTES) + .rel.dyn : AT(ADDR(.rel.dyn) - LOAD_OFFSET) { *(.rel.dyn*) } |