diff options
125 files changed, 1397 insertions, 1573 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 3b5fa8436987..8dc826e00a0d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9792,6 +9792,7 @@ F: include/asm-generic/vdso/vsyscall.h F: include/vdso/ F: kernel/time/vsyscall.c F: lib/vdso/ +F: tools/testing/selftests/vDSO/ GENWQE (IBM Generic Workqueue Card) M: Frank Haverkamp <haver@linux.ibm.com> diff --git a/arch/Kconfig b/arch/Kconfig index b8a4ff365582..9f6eb09ef12d 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1584,6 +1584,10 @@ config HAVE_SPARSE_SYSCALL_NR entries at 4000, 5000 and 6000 locations. This option turns on syscall related optimizations for a given architecture. +config ARCH_HAS_VDSO_ARCH_DATA + depends on GENERIC_VDSO_DATA_STORE + bool + config ARCH_HAS_VDSO_TIME_DATA bool diff --git a/arch/arm/include/asm/vdso.h b/arch/arm/include/asm/vdso.h index 5b85889f82ee..88364a6727ff 100644 --- a/arch/arm/include/asm/vdso.h +++ b/arch/arm/include/asm/vdso.h @@ -4,6 +4,8 @@ #ifdef __KERNEL__ +#define __VDSO_PAGES 4 + #ifndef __ASSEMBLY__ struct mm_struct; diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h index 592d3d015ca7..1e9f81639c88 100644 --- a/arch/arm/include/asm/vdso/gettimeofday.h +++ b/arch/arm/include/asm/vdso/gettimeofday.h @@ -112,7 +112,7 @@ static inline bool arm_vdso_hres_capable(void) #define __arch_vdso_hres_capable arm_vdso_hres_capable static __always_inline u64 __arch_get_hw_counter(int clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { #ifdef CONFIG_ARM_ARCH_TIMER u64 cycle_now; @@ -135,11 +135,6 @@ static __always_inline u64 __arch_get_hw_counter(int clock_mode, #endif } -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) -{ - return _vdso_data; -} - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm/include/asm/vdso/vsyscall.h b/arch/arm/include/asm/vdso/vsyscall.h index 705414710dcd..4e7226ad02ec 100644 --- a/arch/arm/include/asm/vdso/vsyscall.h +++ b/arch/arm/include/asm/vdso/vsyscall.h @@ -7,22 +7,14 @@ #include <vdso/datapage.h> #include <asm/cacheflush.h> -extern struct vdso_data *vdso_data; extern bool cntvct_ok; static __always_inline -struct vdso_data *__arm_get_k_vdso_data(void) -{ - return vdso_data; -} -#define __arch_get_k_vdso_data __arm_get_k_vdso_data - -static __always_inline -void __arm_sync_vdso_data(struct vdso_data *vdata) +void __arch_sync_vdso_time_data(struct vdso_time_data *vdata) { flush_dcache_page(virt_to_page(vdata)); } -#define __arch_sync_vdso_data __arm_sync_vdso_data +#define __arch_sync_vdso_time_data __arch_sync_vdso_time_data /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 4853875740d0..123f4a8ef446 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -153,10 +153,6 @@ int main(void) DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER); DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE); BLANK(); -#ifdef CONFIG_VDSO - DEFINE(VDSO_DATA_SIZE, sizeof(union vdso_data_store)); -#endif - BLANK(); #ifdef CONFIG_ARM_MPU DEFINE(MPU_RNG_INFO_RNGS, offsetof(struct mpu_rgn_info, rgns)); DEFINE(MPU_RNG_INFO_USED, offsetof(struct mpu_rgn_info, used)); diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index 29dd2f3c62fe..325448ffbba0 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -7,6 +7,7 @@ */ #include <linux/cache.h> +#include <linux/vdso_datastore.h> #include <linux/elf.h> #include <linux/err.h> #include <linux/kernel.h> @@ -33,15 +34,6 @@ extern char vdso_start[], vdso_end[]; /* Total number of pages needed for the data and text portions of the VDSO. */ unsigned int vdso_total_pages __ro_after_init; -static union vdso_data_store vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = vdso_data_store.data; - -static struct page *vdso_data_page __ro_after_init; -static const struct vm_special_mapping vdso_data_mapping = { - .name = "[vvar]", - .pages = &vdso_data_page, -}; - static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { @@ -192,9 +184,6 @@ static int __init vdso_init(void) if (vdso_text_pagelist == NULL) return -ENOMEM; - /* Grab the VDSO data page. */ - vdso_data_page = virt_to_page(vdso_data); - /* Grab the VDSO text pages. */ for (i = 0; i < text_pages; i++) { struct page *page; @@ -205,7 +194,7 @@ static int __init vdso_init(void) vdso_text_mapping.pages = vdso_text_pagelist; - vdso_total_pages = 1; /* for the data/vvar page */ + vdso_total_pages = VDSO_NR_PAGES; /* for the data/vvar pages */ vdso_total_pages += text_pages; cntvct_ok = cntvct_functional(); @@ -216,16 +205,7 @@ static int __init vdso_init(void) } arch_initcall(vdso_init); -static int install_vvar(struct mm_struct *mm, unsigned long addr) -{ - struct vm_area_struct *vma; - - vma = _install_special_mapping(mm, addr, PAGE_SIZE, - VM_READ | VM_MAYREAD, - &vdso_data_mapping); - - return PTR_ERR_OR_ZERO(vma); -} +static_assert(__VDSO_PAGES == VDSO_NR_PAGES); /* assumes mmap_lock is write-locked */ void arm_install_vdso(struct mm_struct *mm, unsigned long addr) @@ -238,12 +218,12 @@ void arm_install_vdso(struct mm_struct *mm, unsigned long addr) if (vdso_text_pagelist == NULL) return; - if (install_vvar(mm, addr)) + if (IS_ERR(vdso_install_vvar_mapping(mm, addr))) return; - /* Account for vvar page. */ - addr += PAGE_SIZE; - len = (vdso_total_pages - 1) << PAGE_SHIFT; + /* Account for vvar pages. */ + addr += VDSO_NR_PAGES * PAGE_SIZE; + len = (vdso_total_pages - VDSO_NR_PAGES) << PAGE_SHIFT; vma = _install_special_mapping(mm, addr, len, VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 2b6f50dd5478..5c1023a6d78c 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -928,6 +928,7 @@ config VDSO select GENERIC_TIME_VSYSCALL select GENERIC_VDSO_32 select GENERIC_GETTIMEOFDAY + select GENERIC_VDSO_DATA_STORE help Place in the process address space an ELF shared object providing fast implementations of gettimeofday and diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index 8a306bbec4a0..cb044bfd145d 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include hostprogs := vdsomunge diff --git a/arch/arm/vdso/vdso.lds.S b/arch/arm/vdso/vdso.lds.S index 9bfa0f52923c..7c08371f4400 100644 --- a/arch/arm/vdso/vdso.lds.S +++ b/arch/arm/vdso/vdso.lds.S @@ -11,16 +11,16 @@ */ #include <linux/const.h> -#include <asm/asm-offsets.h> #include <asm/page.h> #include <asm/vdso.h> +#include <vdso/datapage.h> OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm") OUTPUT_ARCH(arm) SECTIONS { - PROVIDE(_vdso_data = . - VDSO_DATA_SIZE); + VDSO_VVAR_SYMS . = SIZEOF_HEADERS; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3e7483ad5276..c9fe3e7566a6 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -162,6 +162,7 @@ config ARM64 select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY + select GENERIC_VDSO_DATA_STORE select GENERIC_VDSO_TIME_NS select HARDIRQS_SW_RESEND select HAS_IOPORT diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 06a4670bdb0b..99cd6546e72e 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -35,7 +35,7 @@ #define ARCH_DMA_MINALIGN (128) #define ARCH_KMALLOC_MINALIGN (8) -#ifndef __ASSEMBLY__ +#if !defined(__ASSEMBLY__) && !defined(BUILD_VDSO) #include <linux/bitops.h> #include <linux/kasan-enabled.h> @@ -118,6 +118,6 @@ static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void) return ctr; } -#endif /* __ASSEMBLY__ */ +#endif /* !defined(__ASSEMBLY__) && !defined(BUILD_VDSO) */ #endif diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h index 3e3c3fdb1842..61679070f595 100644 --- a/arch/arm64/include/asm/vdso.h +++ b/arch/arm64/include/asm/vdso.h @@ -5,7 +5,7 @@ #ifndef __ASM_VDSO_H #define __ASM_VDSO_H -#define __VVAR_PAGES 2 +#define __VDSO_PAGES 4 #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index 778c1202bbbf..d60ea7a72a9c 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -104,7 +104,7 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) } static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { u64 res; @@ -131,45 +131,33 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return res; } -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) +static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void) { - const struct vdso_data *ret; + const struct vdso_time_data *ret; /* - * This simply puts &_vdso_data into ret. The reason why we don't use - * `ret = _vdso_data` is that the compiler tends to optimise this in a - * very suboptimal way: instead of keeping &_vdso_data in a register, - * it goes through a relocation almost every time _vdso_data must be + * This simply puts &_vdso_time_data into ret. The reason why we don't use + * `ret = _vdso_time_data` is that the compiler tends to optimise this in a + * very suboptimal way: instead of keeping &_vdso_time_data in a register, + * it goes through a relocation almost every time _vdso_time_data must be * accessed (even in subfunctions). This is both time and space * consuming: each relocation uses a word in the code section, and it * has to be loaded at runtime. * * This trick hides the assignment from the compiler. Since it cannot * track where the pointer comes from, it will only use one relocation - * where __arch_get_vdso_data() is called, and then keep the result in - * a register. + * where __aarch64_get_vdso_u_time_data() is called, and then keep the + * result in a register. */ - asm volatile("mov %0, %1" : "=r"(ret) : "r"(_vdso_data)); + asm volatile("mov %0, %1" : "=r"(ret) : "r"(&vdso_u_time_data)); return ret; } +#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - const struct vdso_data *ret; - - /* See __arch_get_vdso_data(). */ - asm volatile("mov %0, %1" : "=r"(ret) : "r"(_timens_data)); - - return ret; -} -#endif - -static inline bool vdso_clocksource_ok(const struct vdso_data *vd) +static inline bool vdso_clocksource_ok(const struct vdso_clock *vc) { - return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER; + return vc->clock_mode == VDSO_CLOCKMODE_ARCHTIMER; } #define vdso_clocksource_ok vdso_clocksource_ok diff --git a/arch/arm64/include/asm/vdso/getrandom.h b/arch/arm64/include/asm/vdso/getrandom.h index 342f807e2044..a2197da1951b 100644 --- a/arch/arm64/include/asm/vdso/getrandom.h +++ b/arch/arm64/include/asm/vdso/getrandom.h @@ -33,18 +33,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns return ret; } -static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void) -{ - /* - * The RNG data is in the real VVAR data page, but if a task belongs to a time namespace - * then VVAR_DATA_PAGE_OFFSET points to the namespace-specific VVAR page and VVAR_TIMENS_ - * PAGE_OFFSET points to the real VVAR page. - */ - if (IS_ENABLED(CONFIG_TIME_NS) && _vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS) - return (void *)&_vdso_rng_data + VVAR_TIMENS_PAGE_OFFSET * (1UL << CONFIG_PAGE_SHIFT); - return &_vdso_rng_data; -} - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h index 764d13e2916c..92a2b59a9f3d 100644 --- a/arch/arm64/include/asm/vdso/gettimeofday.h +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -67,7 +67,7 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) } static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { u64 res; @@ -99,20 +99,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return res; } -static __always_inline -const struct vdso_data *__arch_get_vdso_data(void) -{ - return _vdso_data; -} - -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - return _timens_data; -} -#endif - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h index eea51946d45a..de58951b8df6 100644 --- a/arch/arm64/include/asm/vdso/vsyscall.h +++ b/arch/arm64/include/asm/vdso/vsyscall.h @@ -2,44 +2,21 @@ #ifndef __ASM_VDSO_VSYSCALL_H #define __ASM_VDSO_VSYSCALL_H -#define __VDSO_RND_DATA_OFFSET 480 - #ifndef __ASSEMBLY__ #include <vdso/datapage.h> -enum vvar_pages { - VVAR_DATA_PAGE_OFFSET, - VVAR_TIMENS_PAGE_OFFSET, - VVAR_NR_PAGES, -}; - #define VDSO_PRECISION_MASK ~(0xFF00ULL<<48) -extern struct vdso_data *vdso_data; /* * Update the vDSO data page to keep in sync with kernel timekeeping. */ static __always_inline -struct vdso_data *__arm64_get_k_vdso_data(void) -{ - return vdso_data; -} -#define __arch_get_k_vdso_data __arm64_get_k_vdso_data - -static __always_inline -struct vdso_rng_data *__arm64_get_k_vdso_rnd_data(void) -{ - return (void *)vdso_data + __VDSO_RND_DATA_OFFSET; -} -#define __arch_get_k_vdso_rng_data __arm64_get_k_vdso_rnd_data - -static __always_inline -void __arm64_update_vsyscall(struct vdso_data *vdata) +void __arm64_update_vsyscall(struct vdso_time_data *vdata) { - vdata[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK; - vdata[CS_RAW].mask = VDSO_PRECISION_MASK; + vdata->clock_data[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK; + vdata->clock_data[CS_RAW].mask = VDSO_PRECISION_MASK; } #define __arch_update_vsyscall __arm64_update_vsyscall diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index e8ed8e5b713b..887ac0b05961 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -18,7 +18,7 @@ #include <linux/sched.h> #include <linux/signal.h> #include <linux/slab.h> -#include <linux/time_namespace.h> +#include <linux/vdso_datastore.h> #include <linux/vmalloc.h> #include <vdso/datapage.h> #include <vdso/helpers.h> @@ -57,12 +57,6 @@ static struct vdso_abi_info vdso_info[] __ro_after_init = { #endif /* CONFIG_COMPAT_VDSO */ }; -/* - * The vDSO data page. - */ -static union vdso_data_store vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = vdso_data_store.data; - static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { @@ -104,78 +98,6 @@ static int __init __vdso_init(enum vdso_abi abi) return 0; } -#ifdef CONFIG_TIME_NS -struct vdso_data *arch_get_vdso_data(void *vvar_page) -{ - return (struct vdso_data *)(vvar_page); -} - -static const struct vm_special_mapping vvar_map; - -/* - * 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; - VMA_ITERATOR(vmi, mm, 0); - - mmap_read_lock(mm); - - for_each_vma(vmi, vma) { - if (vma_is_special_mapping(vma, &vvar_map)) - zap_vma_pages(vma); - } - - mmap_read_unlock(mm); - return 0; -} -#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); -} - -static const struct vm_special_mapping vvar_map = { - .name = "[vvar]", - .fault = vvar_fault, -}; - static int __setup_additional_pages(enum vdso_abi abi, struct mm_struct *mm, struct linux_binprm *bprm, @@ -185,11 +107,11 @@ static int __setup_additional_pages(enum vdso_abi abi, unsigned long gp_flags = 0; void *ret; - BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); + BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES); vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT; /* Be sure to map the data page */ - vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE; + vdso_mapping_len = vdso_text_len + VDSO_NR_PAGES * PAGE_SIZE; vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { @@ -197,16 +119,14 @@ static int __setup_additional_pages(enum vdso_abi abi, goto up_fail; } - ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE, - VM_READ|VM_MAYREAD|VM_PFNMAP, - &vvar_map); + ret = vdso_install_vvar_mapping(mm, vdso_base); if (IS_ERR(ret)) goto up_fail; if (system_supports_bti_kernel()) gp_flags = VM_ARM64_BTI; - vdso_base += VVAR_NR_PAGES * PAGE_SIZE; + vdso_base += VDSO_NR_PAGES * PAGE_SIZE; mm->context.vdso = (void *)vdso_base; ret = _install_special_mapping(mm, vdso_base, vdso_text_len, VM_READ|VM_EXEC|gp_flags| diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 35685c036044..5e27e46aa496 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -7,7 +7,7 @@ # # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include obj-vdso := vgettimeofday.o note.o sigreturn.o vgetrandom.o vgetrandom-chacha.o diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 47ad6944f9f0..52314be29191 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -20,11 +20,8 @@ OUTPUT_ARCH(aarch64) SECTIONS { - PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); - PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET); -#ifdef CONFIG_TIME_NS - PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); -#endif + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 25a2cb6317f3..f2dfdc7dc818 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -3,7 +3,7 @@ # Makefile for vdso32 # -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include # Same as cc-*option, but using CC_COMPAT instead of CC ifeq ($(CONFIG_CC_IS_CLANG), y) diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S index 732702a187e9..e02b27487ce8 100644 --- a/arch/arm64/kernel/vdso32/vdso.lds.S +++ b/arch/arm64/kernel/vdso32/vdso.lds.S @@ -12,16 +12,15 @@ #include <asm/page.h> #include <asm/vdso.h> #include <asm-generic/vmlinux.lds.h> +#include <vdso/datapage.h> OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm") OUTPUT_ARCH(arm) SECTIONS { - PROVIDE_HIDDEN(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); -#ifdef CONFIG_TIME_NS - PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE); -#endif + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/csky/kernel/vdso/Makefile b/arch/csky/kernel/vdso/Makefile index 069ef0b17fe5..a3042287a070 100644 --- a/arch/csky/kernel/vdso/Makefile +++ b/arch/csky/kernel/vdso/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include # Symbols present in the vdso vdso-syms += rt_sigreturn diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 15aaa2e6757e..687502917ae2 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -30,6 +30,7 @@ config LOONGARCH select ARCH_HAS_SET_MEMORY select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAS_VDSO_ARCH_DATA select ARCH_INLINE_READ_LOCK if !PREEMPTION select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPTION @@ -106,6 +107,7 @@ config LOONGARCH select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL + select GENERIC_VDSO_DATA_STORE select GENERIC_VDSO_TIME_NS select GPIOLIB select HAS_IOPORT diff --git a/arch/loongarch/include/asm/vdso.h b/arch/loongarch/include/asm/vdso.h index d3ba35eb23e7..f72ec79e2dde 100644 --- a/arch/loongarch/include/asm/vdso.h +++ b/arch/loongarch/include/asm/vdso.h @@ -31,7 +31,6 @@ struct loongarch_vdso_info { unsigned long size; unsigned long offset_sigreturn; struct vm_special_mapping code_mapping; - struct vm_special_mapping data_mapping; }; extern struct loongarch_vdso_info vdso_info; diff --git a/arch/loongarch/include/asm/vdso/arch_data.h b/arch/loongarch/include/asm/vdso/arch_data.h new file mode 100644 index 000000000000..322d0a5f1c84 --- /dev/null +++ b/arch/loongarch/include/asm/vdso/arch_data.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Author: Huacai Chen <chenhuacai@loongson.cn> + * Copyright (C) 2020-2022 Loongson Technology Corporation Limited + */ + +#ifndef _VDSO_ARCH_DATA_H +#define _VDSO_ARCH_DATA_H + +#ifndef __ASSEMBLY__ + +#include <asm/asm.h> +#include <asm/vdso.h> + +struct vdso_pcpu_data { + u32 node; +} ____cacheline_aligned_in_smp; + +struct vdso_arch_data { + struct vdso_pcpu_data pdata[NR_CPUS]; +}; + +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h index e80f3c4ac748..48c43f55b039 100644 --- a/arch/loongarch/include/asm/vdso/getrandom.h +++ b/arch/loongarch/include/asm/vdso/getrandom.h @@ -28,11 +28,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns return ret; } -static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void) -{ - return &_loongarch_data.rng_data; -} - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h index 7eb3f041af76..88cfcf133116 100644 --- a/arch/loongarch/include/asm/vdso/gettimeofday.h +++ b/arch/loongarch/include/asm/vdso/gettimeofday.h @@ -72,7 +72,7 @@ static __always_inline int clock_getres_fallback( } static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { uint64_t count; @@ -89,18 +89,6 @@ static inline bool loongarch_vdso_hres_capable(void) } #define __arch_vdso_hres_capable loongarch_vdso_hres_capable -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) -{ - return _vdso_data; -} - -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - return _timens_data; -} -#endif #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h index 1c183a9b2115..50c65fb29daf 100644 --- a/arch/loongarch/include/asm/vdso/vdso.h +++ b/arch/loongarch/include/asm/vdso/vdso.h @@ -12,43 +12,9 @@ #include <asm/asm.h> #include <asm/page.h> #include <asm/vdso.h> +#include <vdso/datapage.h> -struct vdso_pcpu_data { - u32 node; -} ____cacheline_aligned_in_smp; - -struct loongarch_vdso_data { - struct vdso_pcpu_data pdata[NR_CPUS]; - struct vdso_rng_data rng_data; -}; - -/* - * The layout of vvar: - * - * high - * +---------------------+--------------------------+ - * | loongarch vdso data | LOONGARCH_VDSO_DATA_SIZE | - * +---------------------+--------------------------+ - * | time-ns vdso data | PAGE_SIZE | - * +---------------------+--------------------------+ - * | generic vdso data | PAGE_SIZE | - * +---------------------+--------------------------+ - * low - */ -#define LOONGARCH_VDSO_DATA_SIZE PAGE_ALIGN(sizeof(struct loongarch_vdso_data)) -#define LOONGARCH_VDSO_DATA_PAGES (LOONGARCH_VDSO_DATA_SIZE >> PAGE_SHIFT) - -enum vvar_pages { - VVAR_GENERIC_PAGE_OFFSET, - VVAR_TIMENS_PAGE_OFFSET, - VVAR_LOONGARCH_PAGES_START, - VVAR_LOONGARCH_PAGES_END = VVAR_LOONGARCH_PAGES_START + LOONGARCH_VDSO_DATA_PAGES - 1, - VVAR_NR_PAGES, -}; - -#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) - -extern struct loongarch_vdso_data _loongarch_data __attribute__((visibility("hidden"))); +#define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT) #endif /* __ASSEMBLY__ */ diff --git a/arch/loongarch/include/asm/vdso/vsyscall.h b/arch/loongarch/include/asm/vdso/vsyscall.h index 8987e951d0a9..1140b54b4bc8 100644 --- a/arch/loongarch/include/asm/vdso/vsyscall.h +++ b/arch/loongarch/include/asm/vdso/vsyscall.h @@ -6,23 +6,6 @@ #include <vdso/datapage.h> -extern struct vdso_data *vdso_data; -extern struct vdso_rng_data *vdso_rng_data; - -static __always_inline -struct vdso_data *__loongarch_get_k_vdso_data(void) -{ - return vdso_data; -} -#define __arch_get_k_vdso_data __loongarch_get_k_vdso_data - -static __always_inline -struct vdso_rng_data *__loongarch_get_k_vdso_rng_data(void) -{ - return vdso_rng_data; -} -#define __arch_get_k_vdso_rng_data __loongarch_get_k_vdso_rng_data - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index 8be1c38ad8eb..6f1524bba957 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -315,6 +315,6 @@ static void __used output_vdso_defines(void) { COMMENT("LoongArch vDSO offsets."); - DEFINE(__VVAR_PAGES, VVAR_NR_PAGES); + DEFINE(__VDSO_PAGES, VDSO_NR_PAGES); BLANK(); } diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c index 05e5fbac102a..10cf1608c7b3 100644 --- a/arch/loongarch/kernel/vdso.c +++ b/arch/loongarch/kernel/vdso.c @@ -14,7 +14,7 @@ #include <linux/random.h> #include <linux/sched.h> #include <linux/slab.h> -#include <linux/time_namespace.h> +#include <linux/vdso_datastore.h> #include <asm/page.h> #include <asm/vdso.h> @@ -25,18 +25,6 @@ extern char vdso_start[], vdso_end[]; -/* Kernel-provided data used by the VDSO. */ -static union vdso_data_store generic_vdso_data __page_aligned_data; - -static union { - u8 page[LOONGARCH_VDSO_DATA_SIZE]; - struct loongarch_vdso_data vdata; -} loongarch_vdso_data __page_aligned_data; - -struct vdso_data *vdso_data = generic_vdso_data.data; -struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata; -struct vdso_rng_data *vdso_rng_data = &loongarch_vdso_data.vdata.rng_data; - 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); @@ -44,53 +32,12 @@ static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struc return 0; } -static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, - struct vm_area_struct *vma, struct vm_fault *vmf) -{ - unsigned long pfn; - struct page *timens_page = find_timens_vvar_page(vma); - - switch (vmf->pgoff) { - case VVAR_GENERIC_PAGE_OFFSET: - if (!timens_page) - pfn = sym_to_pfn(vdso_data); - else - pfn = page_to_pfn(timens_page); - 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_GENERIC_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; - else - pfn = sym_to_pfn(vdso_data); - break; -#endif /* CONFIG_TIME_NS */ - case VVAR_LOONGARCH_PAGES_START ... VVAR_LOONGARCH_PAGES_END: - pfn = sym_to_pfn(&loongarch_vdso_data) + vmf->pgoff - VVAR_LOONGARCH_PAGES_START; - break; - default: - return VM_FAULT_SIGBUS; - } - - return vmf_insert_pfn(vma, vmf->address, pfn); -} - struct loongarch_vdso_info vdso_info = { .vdso = vdso_start, .code_mapping = { .name = "[vdso]", .mremap = vdso_mremap, }, - .data_mapping = { - .name = "[vvar]", - .fault = vvar_fault, - }, .offset_sigreturn = vdso_offset_sigreturn, }; @@ -101,7 +48,7 @@ static int __init init_vdso(void) BUG_ON(!PAGE_ALIGNED(vdso_info.vdso)); for_each_possible_cpu(cpu) - vdso_pdata[cpu].node = cpu_to_node(cpu); + vdso_k_arch_data->pdata[cpu].node = cpu_to_node(cpu); vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start); vdso_info.code_mapping.pages = @@ -115,37 +62,6 @@ static int __init init_vdso(void) } subsys_initcall(init_vdso); -#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; - - VMA_ITERATOR(vmi, mm, 0); - - mmap_read_lock(mm); - for_each_vma(vmi, vma) { - if (vma_is_special_mapping(vma, &vdso_info.data_mapping)) - zap_vma_pages(vma); - } - mmap_read_unlock(mm); - - return 0; -} -#endif - static unsigned long vdso_base(void) { unsigned long base = STACK_TOP; @@ -181,9 +97,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) goto out; } - vma = _install_special_mapping(mm, data_addr, VVAR_SIZE, - VM_READ | VM_MAYREAD | VM_PFNMAP, - &info->data_mapping); + vma = vdso_install_vvar_mapping(mm, data_addr); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile index fdde1bcd4e26..1c26147aff70 100644 --- a/arch/loongarch/vdso/Makefile +++ b/arch/loongarch/vdso/Makefile @@ -2,7 +2,7 @@ # Objects to go into the VDSO. # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include obj-vdso-y := elf.o vgetcpu.o vgettimeofday.o vgetrandom.o \ vgetrandom-chacha.o sigreturn.o diff --git a/arch/loongarch/vdso/vdso.lds.S b/arch/loongarch/vdso/vdso.lds.S index 160cfaef2de4..8ff986499947 100644 --- a/arch/loongarch/vdso/vdso.lds.S +++ b/arch/loongarch/vdso/vdso.lds.S @@ -5,6 +5,7 @@ */ #include <asm/page.h> #include <generated/asm-offsets.h> +#include <vdso/datapage.h> OUTPUT_FORMAT("elf64-loongarch", "elf64-loongarch", "elf64-loongarch") @@ -12,11 +13,8 @@ OUTPUT_ARCH(loongarch) SECTIONS { - PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); -#ifdef CONFIG_TIME_NS - PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); -#endif - PROVIDE(_loongarch_data = _vdso_data + 2 * PAGE_SIZE); + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/loongarch/vdso/vgetcpu.c b/arch/loongarch/vdso/vgetcpu.c index 0db51258b2a7..5301cd9d0f83 100644 --- a/arch/loongarch/vdso/vgetcpu.c +++ b/arch/loongarch/vdso/vgetcpu.c @@ -19,27 +19,19 @@ static __always_inline int read_cpu_id(void) return cpu_id; } -static __always_inline const struct vdso_pcpu_data *get_pcpu_data(void) -{ - return _loongarch_data.pdata; -} - extern int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused); int __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused) { int cpu_id; - const struct vdso_pcpu_data *data; cpu_id = read_cpu_id(); if (cpu) *cpu = cpu_id; - if (node) { - data = get_pcpu_data(); - *node = data[cpu_id].node; - } + if (node) + *node = vdso_u_arch_data.pdata[cpu_id].node; return 0; } diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 1924f2d83932..b51168e319ea 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -51,6 +51,7 @@ config MIPS select GENERIC_SMP_IDLE_THREAD select GENERIC_IDLE_POLL_SETUP select GENERIC_TIME_VSYSCALL + select GENERIC_VDSO_DATA_STORE select GUP_GET_PXX_LOW_HIGH if CPU_MIPS32 && PHYS_ADDR_T_64BIT select HAS_IOPORT if !NO_IOPORT_MAP || ISA select HAVE_ARCH_COMPILER_H diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h index 44a45f3fa4b0..fd32baa30e17 100644 --- a/arch/mips/include/asm/vdso/gettimeofday.h +++ b/arch/mips/include/asm/vdso/gettimeofday.h @@ -167,7 +167,7 @@ static __always_inline u64 read_r4k_count(void) #ifdef CONFIG_CLKSRC_MIPS_GIC -static __always_inline u64 read_gic_count(const struct vdso_data *data) +static __always_inline u64 read_gic_count(const struct vdso_time_data *data) { void __iomem *gic = get_gic(data); u32 hi, hi2, lo; @@ -184,7 +184,7 @@ static __always_inline u64 read_gic_count(const struct vdso_data *data) #endif static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { #ifdef CONFIG_CSRC_R4K if (clock_mode == VDSO_CLOCKMODE_R4K) @@ -209,10 +209,11 @@ static inline bool mips_vdso_hres_capable(void) } #define __arch_vdso_hres_capable mips_vdso_hres_capable -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) +static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void) { - return get_vdso_data(); + return get_vdso_time_data(); } +#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data #endif /* !__ASSEMBLY__ */ diff --git a/arch/mips/include/asm/vdso/vdso.h b/arch/mips/include/asm/vdso/vdso.h index 6cd88191fefa..acd0efcd3d93 100644 --- a/arch/mips/include/asm/vdso/vdso.h +++ b/arch/mips/include/asm/vdso/vdso.h @@ -5,16 +5,18 @@ */ #include <asm/sgidefs.h> +#include <vdso/page.h> + +#define __VDSO_PAGES 4 #ifndef __ASSEMBLY__ #include <asm/asm.h> -#include <asm/page.h> #include <asm/vdso.h> -static inline unsigned long get_vdso_base(void) +static inline const struct vdso_time_data *get_vdso_time_data(void) { - unsigned long addr; + const struct vdso_time_data *addr; /* * We can't use cpu_has_mips_r6 since it needs the cpu_data[] @@ -27,7 +29,7 @@ static inline unsigned long get_vdso_base(void) * We can't use addiupc because there is no label-label * support for the addiupc reloc */ - __asm__("lapc %0, _start \n" + __asm__("lapc %0, vdso_u_time_data \n" : "=r" (addr) : :); #else /* @@ -46,7 +48,7 @@ static inline unsigned long get_vdso_base(void) " .set noreorder \n" " bal 1f \n" " nop \n" - " .word _start - . \n" + " .word vdso_u_time_data - . \n" "1: lw %0, 0($31) \n" " " STR(PTR_ADDU) " %0, $31, %0 \n" " .set pop \n" @@ -58,14 +60,9 @@ static inline unsigned long get_vdso_base(void) return addr; } -static inline const struct vdso_data *get_vdso_data(void) -{ - return (const struct vdso_data *)(get_vdso_base() - PAGE_SIZE); -} - #ifdef CONFIG_CLKSRC_MIPS_GIC -static inline void __iomem *get_gic(const struct vdso_data *data) +static inline void __iomem *get_gic(const struct vdso_time_data *data) { return (void __iomem *)((unsigned long)data & PAGE_MASK) - PAGE_SIZE; } diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h index a4582870aaea..2b1debb62dee 100644 --- a/arch/mips/include/asm/vdso/vsyscall.h +++ b/arch/mips/include/asm/vdso/vsyscall.h @@ -2,22 +2,12 @@ #ifndef __ASM_VDSO_VSYSCALL_H #define __ASM_VDSO_VSYSCALL_H +#include <asm/page.h> + #ifndef __ASSEMBLY__ #include <vdso/datapage.h> -extern struct vdso_data *vdso_data; - -/* - * Update the vDSO data page to keep in sync with kernel timekeeping. - */ -static __always_inline -struct vdso_data *__mips_get_k_vdso_data(void) -{ - return vdso_data; -} -#define __arch_get_k_vdso_data __mips_get_k_vdso_data - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 75c9d3618f58..de096777172f 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -15,6 +15,7 @@ #include <linux/random.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/vdso_datastore.h> #include <asm/abi.h> #include <asm/mips-cps.h> @@ -23,20 +24,7 @@ #include <vdso/helpers.h> #include <vdso/vsyscall.h> -/* Kernel-provided data used by the VDSO. */ -static union vdso_data_store mips_vdso_data __page_aligned_data; -struct vdso_data *vdso_data = mips_vdso_data.data; - -/* - * Mapping for the VDSO data/GIC pages. The real pages are mapped manually, as - * what we map and where within the area they are mapped is determined at - * runtime. - */ -static struct page *no_pages[] = { NULL }; -static struct vm_special_mapping vdso_vvar_mapping = { - .name = "[vvar]", - .pages = no_pages, -}; +static_assert(VDSO_NR_PAGES == __VDSO_PAGES); static void __init init_vdso_image(struct mips_vdso_image *image) { @@ -90,7 +78,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mips_vdso_image *image = current->thread.abi->vdso; struct mm_struct *mm = current->mm; - unsigned long gic_size, vvar_size, size, base, data_addr, vdso_addr, gic_pfn, gic_base; + unsigned long gic_size, size, base, data_addr, vdso_addr, gic_pfn, gic_base; struct vm_area_struct *vma; int ret; @@ -119,8 +107,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * the counter registers at the start. */ gic_size = mips_gic_present() ? PAGE_SIZE : 0; - vvar_size = gic_size + PAGE_SIZE; - size = vvar_size + image->size; + size = gic_size + VDSO_NR_PAGES * PAGE_SIZE + image->size; /* * Find a region that's large enough for us to perform the @@ -143,15 +130,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) */ if (cpu_has_dc_aliases) { base = __ALIGN_MASK(base, shm_align_mask); - base += ((unsigned long)vdso_data - gic_size) & shm_align_mask; + base += ((unsigned long)vdso_k_time_data - gic_size) & shm_align_mask; } data_addr = base + gic_size; - vdso_addr = data_addr + PAGE_SIZE; + vdso_addr = data_addr + VDSO_NR_PAGES * PAGE_SIZE; - vma = _install_special_mapping(mm, base, vvar_size, - VM_READ | VM_MAYREAD, - &vdso_vvar_mapping); + vma = vdso_install_vvar_mapping(mm, data_addr); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; @@ -161,6 +146,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (gic_size) { gic_base = (unsigned long)mips_gic_base + MIPS_GIC_USER_OFS; gic_pfn = PFN_DOWN(__pa(gic_base)); + static const struct vm_special_mapping gic_mapping = { + .name = "[gic]", + .pages = (struct page **) { NULL }, + }; + + vma = _install_special_mapping(mm, base, gic_size, VM_READ | VM_MAYREAD, + &gic_mapping); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; + } ret = io_remap_pfn_range(vma, base, gic_pfn, gic_size, pgprot_noncached(vma->vm_page_prot)); @@ -168,13 +164,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) goto out; } - /* Map data page. */ - ret = remap_pfn_range(vma, data_addr, - virt_to_phys(vdso_data) >> PAGE_SHIFT, - PAGE_SIZE, vma->vm_page_prot); - if (ret) - goto out; - /* Map VDSO image. */ vma = _install_special_mapping(mm, vdso_addr, image->size, VM_READ | VM_EXEC | diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index b289b2c1b294..fb4c493aaffa 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -2,7 +2,7 @@ # Objects to go into the VDSO. # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include obj-vdso-y := elf.o vgettimeofday.o sigreturn.o diff --git a/arch/mips/vdso/vdso.lds.S b/arch/mips/vdso/vdso.lds.S index 836465e3bcb8..c8bbe56d89cb 100644 --- a/arch/mips/vdso/vdso.lds.S +++ b/arch/mips/vdso/vdso.lds.S @@ -5,6 +5,8 @@ */ #include <asm/sgidefs.h> +#include <asm/vdso/vdso.h> +#include <vdso/datapage.h> #if _MIPS_SIM == _MIPS_SIM_ABI64 OUTPUT_FORMAT("elf64-tradlittlemips", "elf64-tradbigmips", "elf64-tradlittlemips") @@ -18,7 +20,8 @@ OUTPUT_ARCH(mips) SECTIONS { - PROVIDE(_start = .); + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; /* diff --git a/arch/parisc/include/asm/vdso.h b/arch/parisc/include/asm/vdso.h index 2a2dc11b5545..5f581c1d6460 100644 --- a/arch/parisc/include/asm/vdso.h +++ b/arch/parisc/include/asm/vdso.h @@ -12,8 +12,6 @@ #define VDSO64_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso64_offset_##name)) #define VDSO32_SYMBOL(tsk, name) ((tsk)->mm->context.vdso_base + (vdso32_offset_##name)) -extern struct vdso_data *vdso_data; - #endif /* __ASSEMBLY __ */ /* Default link addresses for the vDSOs */ diff --git a/arch/parisc/kernel/vdso32/Makefile b/arch/parisc/kernel/vdso32/Makefile index 288f8b85978f..4ee8d17da229 100644 --- a/arch/parisc/kernel/vdso32/Makefile +++ b/arch/parisc/kernel/vdso32/Makefile @@ -1,5 +1,5 @@ # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include KCOV_INSTRUMENT := n diff --git a/arch/parisc/kernel/vdso64/Makefile b/arch/parisc/kernel/vdso64/Makefile index bc5d9553f311..c63f4069170f 100644 --- a/arch/parisc/kernel/vdso64/Makefile +++ b/arch/parisc/kernel/vdso64/Makefile @@ -1,5 +1,5 @@ # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include KCOV_INSTRUMENT := n diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 424f188e62d9..8a2a6e403eb1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -159,6 +159,7 @@ config PPC select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE select ARCH_HAS_UBSAN + select ARCH_HAS_VDSO_ARCH_DATA select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_HAVE_EXTRA_ELF_NOTES if SPU_BASE select ARCH_KEEP_MEMBLOCK @@ -209,6 +210,7 @@ config PPC select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL + select GENERIC_VDSO_DATA_STORE select GENERIC_VDSO_TIME_NS select HAS_IOPORT if PCI select HAVE_ARCH_AUDITSYSCALL diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h index 8d972bc98b55..1ca23fbfe087 100644 --- a/arch/powerpc/include/asm/vdso.h +++ b/arch/powerpc/include/asm/vdso.h @@ -3,6 +3,7 @@ #define _ASM_POWERPC_VDSO_H #define VDSO_VERSION_STRING LINUX_2.6.15 +#define __VDSO_PAGES 4 #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/vdso/arch_data.h b/arch/powerpc/include/asm/vdso/arch_data.h new file mode 100644 index 000000000000..c240a6b87518 --- /dev/null +++ b/arch/powerpc/include/asm/vdso/arch_data.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2002 Peter Bergner <bergner@vnet.ibm.com>, IBM + * Copyright (C) 2005 Benjamin Herrenschmidy <benh@kernel.crashing.org>, + * IBM Corp. + */ +#ifndef _ASM_POWERPC_VDSO_ARCH_DATA_H +#define _ASM_POWERPC_VDSO_ARCH_DATA_H + +#include <linux/unistd.h> +#include <linux/types.h> + +#define SYSCALL_MAP_SIZE ((NR_syscalls + 31) / 32) + +#ifdef CONFIG_PPC64 + +struct vdso_arch_data { + __u64 tb_ticks_per_sec; /* Timebase tics / sec */ + __u32 dcache_block_size; /* L1 d-cache block size */ + __u32 icache_block_size; /* L1 i-cache block size */ + __u32 dcache_log_block_size; /* L1 d-cache log block size */ + __u32 icache_log_block_size; /* L1 i-cache log block size */ + __u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */ + __u32 compat_syscall_map[SYSCALL_MAP_SIZE]; /* Map of compat syscalls */ +}; + +#else /* CONFIG_PPC64 */ + +struct vdso_arch_data { + __u64 tb_ticks_per_sec; /* Timebase tics / sec */ + __u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */ + __u32 compat_syscall_map[0]; /* No compat syscalls on PPC32 */ +}; + +#endif /* CONFIG_PPC64 */ + +#endif /* _ASM_POWERPC_VDSO_ARCH_DATA_H */ diff --git a/arch/powerpc/include/asm/vdso/getrandom.h b/arch/powerpc/include/asm/vdso/getrandom.h index 80ce0709725e..067a5396aac6 100644 --- a/arch/powerpc/include/asm/vdso/getrandom.h +++ b/arch/powerpc/include/asm/vdso/getrandom.h @@ -43,20 +43,21 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig (unsigned long)len, (unsigned long)flags); } -static __always_inline struct vdso_rng_data *__arch_get_vdso_rng_data(void) +static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(void) { - struct vdso_arch_data *data; + struct vdso_rng_data *data; asm ( " bcl 20, 31, .+4 ;" "0: mflr %0 ;" - " addis %0, %0, (_vdso_datapage - 0b)@ha ;" - " addi %0, %0, (_vdso_datapage - 0b)@l ;" + " addis %0, %0, (vdso_u_rng_data - 0b)@ha ;" + " addi %0, %0, (vdso_u_rng_data - 0b)@l ;" : "=r" (data) : : "lr" ); - return &data->rng_data; + return data; } +#define __arch_get_vdso_u_rng_data __arch_get_vdso_u_rng_data ssize_t __c_kernel_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len); diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index c6390890a60c..99c9d6f43fde 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -94,22 +94,12 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) #endif static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return get_tb(); } -const struct vdso_data *__arch_get_vdso_data(void); - -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - return (void *)vd + (1U << CONFIG_PAGE_SHIFT); -} -#endif - -static inline bool vdso_clocksource_ok(const struct vdso_data *vd) +static inline bool vdso_clocksource_ok(const struct vdso_clock *vc) { return true; } @@ -135,21 +125,22 @@ static __always_inline u64 vdso_shift_ns(u64 ns, unsigned long shift) #ifdef __powerpc64__ int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, - const struct vdso_data *vd); + const struct vdso_time_data *vd); int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, - const struct vdso_data *vd); + const struct vdso_time_data *vd); #else int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts, - const struct vdso_data *vd); + const struct vdso_time_data *vd); int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts, - const struct vdso_data *vd); + const struct vdso_time_data *vd); int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, - const struct vdso_data *vd); + const struct vdso_time_data *vd); #endif int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, - const struct vdso_data *vd); + const struct vdso_time_data *vd); __kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, - const struct vdso_data *vd); + const struct vdso_time_data *vd); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/powerpc/include/asm/vdso/vsyscall.h b/arch/powerpc/include/asm/vdso/vsyscall.h index 48560a119559..c2c9ae1b22e7 100644 --- a/arch/powerpc/include/asm/vdso/vsyscall.h +++ b/arch/powerpc/include/asm/vdso/vsyscall.h @@ -6,19 +6,6 @@ #include <asm/vdso_datapage.h> -static __always_inline -struct vdso_data *__arch_get_k_vdso_data(void) -{ - return vdso_data->data; -} -#define __arch_get_k_vdso_data __arch_get_k_vdso_data - -static __always_inline -struct vdso_rng_data *__arch_get_k_vdso_rng_data(void) -{ - return &vdso_data->rng_data; -} - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index a202f5b63479..95d45a50355d 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -11,56 +11,18 @@ #ifndef __ASSEMBLY__ -#include <linux/unistd.h> -#include <linux/time.h> #include <vdso/datapage.h> -#define SYSCALL_MAP_SIZE ((NR_syscalls + 31) / 32) - -#ifdef CONFIG_PPC64 - -struct vdso_arch_data { - __u64 tb_ticks_per_sec; /* Timebase tics / sec */ - __u32 dcache_block_size; /* L1 d-cache block size */ - __u32 icache_block_size; /* L1 i-cache block size */ - __u32 dcache_log_block_size; /* L1 d-cache log block size */ - __u32 icache_log_block_size; /* L1 i-cache log block size */ - __u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */ - __u32 compat_syscall_map[SYSCALL_MAP_SIZE]; /* Map of compat syscalls */ - - struct vdso_rng_data rng_data; - - struct vdso_data data[CS_BASES] __aligned(1 << CONFIG_PAGE_SHIFT); -}; - -#else /* CONFIG_PPC64 */ - -struct vdso_arch_data { - __u64 tb_ticks_per_sec; /* Timebase tics / sec */ - __u32 syscall_map[SYSCALL_MAP_SIZE]; /* Map of syscalls */ - __u32 compat_syscall_map[0]; /* No compat syscalls on PPC32 */ - struct vdso_rng_data rng_data; - - struct vdso_data data[CS_BASES] __aligned(1 << CONFIG_PAGE_SHIFT); -}; - -#endif /* CONFIG_PPC64 */ - -extern struct vdso_arch_data *vdso_data; - #else /* __ASSEMBLY__ */ -.macro get_datapage ptr offset=0 +.macro get_datapage ptr symbol bcl 20, 31, .+4 999: mflr \ptr - addis \ptr, \ptr, (_vdso_datapage - 999b + \offset)@ha - addi \ptr, \ptr, (_vdso_datapage - 999b + \offset)@l + addis \ptr, \ptr, (\symbol - 999b)@ha + addi \ptr, \ptr, (\symbol - 999b)@l .endm -#include <asm/asm-offsets.h> -#include <asm/page.h> - #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 7a390bd4f4af..b3048f6d3822 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -334,7 +334,6 @@ int main(void) #endif /* ! CONFIG_PPC64 */ /* datapage offsets for use by vdso */ - OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data); OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec); #ifdef CONFIG_PPC64 OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 0727332ad86f..15784c5c95c7 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -950,7 +950,7 @@ void __init time_init(void) sys_tz.tz_dsttime = 0; } - vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; + vdso_k_arch_data->tb_ticks_per_sec = tb_ticks_per_sec; #ifdef CONFIG_PPC64_PROC_SYSTEMCFG systemcfg->tb_ticks_per_sec = tb_ticks_per_sec; #endif diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 43379365ce1b..219d67bcf747 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -17,7 +17,7 @@ #include <linux/elf.h> #include <linux/security.h> #include <linux/syscalls.h> -#include <linux/time_namespace.h> +#include <linux/vdso_datastore.h> #include <vdso/datapage.h> #include <asm/syscall.h> @@ -32,6 +32,8 @@ #include <asm/vdso_datapage.h> #include <asm/setup.h> +static_assert(__VDSO_PAGES == VDSO_NR_PAGES); + /* The alignment of the vDSO */ #define VDSO_ALIGNMENT (1 << 16) @@ -40,24 +42,6 @@ extern char vdso64_start, vdso64_end; long sys_ni_syscall(void); -/* - * The vdso data page (aka. systemcfg for old ppc64 fans) is here. - * Once the early boot kernel code no longer needs to muck around - * with it, it will become dynamically allocated - */ -static union { - struct vdso_arch_data data; - u8 page[2 * PAGE_SIZE]; -} vdso_data_store __page_aligned_data; -struct vdso_arch_data *vdso_data = &vdso_data_store.data; - -enum vvar_pages { - VVAR_BASE_PAGE_OFFSET, - VVAR_TIME_PAGE_OFFSET, - VVAR_TIMENS_PAGE_OFFSET, - VVAR_NR_PAGES, -}; - static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma, unsigned long text_size) { @@ -96,14 +80,6 @@ static void vdso_close(const struct vm_special_mapping *sm, struct vm_area_struc mm->context.vdso = NULL; } -static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, - struct vm_area_struct *vma, struct vm_fault *vmf); - -static struct vm_special_mapping vvar_spec __ro_after_init = { - .name = "[vvar]", - .fault = vvar_fault, -}; - static struct vm_special_mapping vdso32_spec __ro_after_init = { .name = "[vdso]", .mremap = vdso32_mremap, @@ -116,73 +92,6 @@ static struct vm_special_mapping vdso64_spec __ro_after_init = { .close = vdso_close, }; -#ifdef CONFIG_TIME_NS -struct vdso_data *arch_get_vdso_data(void *vvar_page) -{ - return 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; - VMA_ITERATOR(vmi, mm, 0); - struct vm_area_struct *vma; - - mmap_read_lock(mm); - for_each_vma(vmi, vma) { - if (vma_is_special_mapping(vma, &vvar_spec)) - zap_vma_pages(vma); - } - mmap_read_unlock(mm); - - return 0; -} -#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_BASE_PAGE_OFFSET: - pfn = virt_to_pfn(vdso_data); - break; - case VVAR_TIME_PAGE_OFFSET: - if (timens_page) - pfn = page_to_pfn(timens_page); - else - pfn = virt_to_pfn(vdso_data->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 = virt_to_pfn(vdso_data->data); - break; -#endif /* CONFIG_TIME_NS */ - default: - return VM_FAULT_SIGBUS; - } - - return vmf_insert_pfn(vma, vmf->address, pfn); -} - /* * This is called from binfmt_elf, we create the special vma for the * vDSO and insert it into the mm struct tree @@ -191,7 +100,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int { unsigned long vdso_size, vdso_base, mappings_size; struct vm_special_mapping *vdso_spec; - unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE; + unsigned long vvar_size = VDSO_NR_PAGES * PAGE_SIZE; struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -217,9 +126,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int /* Add required alignment. */ vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT); - vma = _install_special_mapping(mm, vdso_base, vvar_size, - VM_READ | VM_MAYREAD | VM_IO | - VM_DONTDUMP | VM_PFNMAP, &vvar_spec); + vma = vdso_install_vvar_mapping(mm, vdso_base); if (IS_ERR(vma)) return PTR_ERR(vma); @@ -299,10 +206,10 @@ static void __init vdso_setup_syscall_map(void) for (i = 0; i < NR_syscalls; i++) { if (sys_call_table[i] != (void *)&sys_ni_syscall) - vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); + vdso_k_arch_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); if (IS_ENABLED(CONFIG_COMPAT) && compat_sys_call_table[i] != (void *)&sys_ni_syscall) - vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); + vdso_k_arch_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f); } } @@ -352,10 +259,10 @@ static struct page ** __init vdso_setup_pages(void *start, void *end) static int __init vdso_init(void) { #ifdef CONFIG_PPC64 - vdso_data->dcache_block_size = ppc64_caches.l1d.block_size; - vdso_data->icache_block_size = ppc64_caches.l1i.block_size; - vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size; - vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size; + vdso_k_arch_data->dcache_block_size = ppc64_caches.l1d.block_size; + vdso_k_arch_data->icache_block_size = ppc64_caches.l1i.block_size; + vdso_k_arch_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size; + vdso_k_arch_data->icache_log_block_size = ppc64_caches.l1i.log_block_size; #endif /* CONFIG_PPC64 */ vdso_setup_syscall_map(); diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 0e3ed6fb199f..e8824f933326 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -3,7 +3,7 @@ # List of files in the vdso, has to be asm only for now # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index 0085ae464dac..488d3ade11e6 100644 --- a/arch/powerpc/kernel/vdso/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) #ifdef CONFIG_PPC64 mflr r12 .cfi_register lr,r12 - get_datapage r10 + get_datapage r10 vdso_u_arch_data mtlr r12 .cfi_restore lr #endif diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S index db8e167f0166..d23b2e8e2a34 100644 --- a/arch/powerpc/kernel/vdso/datapage.S +++ b/arch/powerpc/kernel/vdso/datapage.S @@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mflr r12 .cfi_register lr,r12 mr. r4,r3 - get_datapage r3 + get_datapage r3 vdso_u_arch_data mtlr r12 #ifdef __powerpc64__ addi r3,r3,CFG_SYSCALL_MAP64 @@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 .cfi_register lr,r12 - get_datapage r3 + get_datapage r3 vdso_u_arch_data #ifndef __powerpc64__ lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) #endif diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index 5333848322ca..79c967212444 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -33,9 +33,9 @@ .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT #endif .ifeq \call_time - get_datapage r5 VDSO_DATA_OFFSET + get_datapage r5 vdso_u_time_data .else - get_datapage r4 VDSO_DATA_OFFSET + get_datapage r4 vdso_u_time_data .endif bl CFUNC(DOTSYM(\funct)) PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index 1a1b0b6d681a..72a1012b8a20 100644 --- a/arch/powerpc/kernel/vdso/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S @@ -6,6 +6,7 @@ #include <asm/vdso.h> #include <asm/page.h> #include <asm-generic/vmlinux.lds.h> +#include <vdso/datapage.h> #ifdef __LITTLE_ENDIAN__ OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle") @@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common) SECTIONS { - PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE); + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index e21b5506cad6..32102a05eaa7 100644 --- a/arch/powerpc/kernel/vdso/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S @@ -6,6 +6,7 @@ #include <asm/vdso.h> #include <asm/page.h> #include <asm-generic/vmlinux.lds.h> +#include <vdso/datapage.h> #ifdef __LITTLE_ENDIAN__ OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle") @@ -16,7 +17,8 @@ OUTPUT_ARCH(powerpc:common64) SECTIONS { - PROVIDE(_vdso_datapage = . - 3 * PAGE_SIZE); + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/powerpc/kernel/vdso/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c index 55a287c9a736..6f5167d81af5 100644 --- a/arch/powerpc/kernel/vdso/vgettimeofday.c +++ b/arch/powerpc/kernel/vdso/vgettimeofday.c @@ -7,43 +7,43 @@ #ifdef __powerpc64__ int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_gettime_data(vd, clock, ts); } int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_getres_data(vd, clock_id, res); } #else int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_gettime32_data(vd, clock, ts); } int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_gettime_data(vd, clock, ts); } int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_clock_getres_time32_data(vd, clock_id, res); } #endif int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { return __cvdso_gettimeofday_data(vd, tv, tz); } -__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd) +__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_time_data *vd) { return __cvdso_time_data(vd, time); } diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a32f39748775..0409be768666 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -53,7 +53,7 @@ config RISCV select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN - select ARCH_HAS_VDSO_TIME_DATA + select ARCH_HAS_VDSO_ARCH_DATA if GENERIC_VDSO_DATA_STORE select ARCH_KEEP_MEMBLOCK if ACPI select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE if 64BIT && MMU select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX @@ -117,6 +117,7 @@ config RISCV select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT + select GENERIC_VDSO_DATA_STORE if MMU select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO select HARDIRQS_SW_RESEND select HAS_IOPORT if MMU diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index f891478829a5..c130d8100232 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -14,7 +14,7 @@ */ #ifdef CONFIG_MMU -#define __VVAR_PAGES 2 +#define __VDSO_PAGES 4 #ifndef __ASSEMBLY__ #include <generated/vdso-offsets.h> diff --git a/arch/riscv/include/asm/vdso/time_data.h b/arch/riscv/include/asm/vdso/arch_data.h index dfa65228999b..da57a3786f7a 100644 --- a/arch/riscv/include/asm/vdso/time_data.h +++ b/arch/riscv/include/asm/vdso/arch_data.h @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __RISCV_ASM_VDSO_TIME_DATA_H -#define __RISCV_ASM_VDSO_TIME_DATA_H +#ifndef __RISCV_ASM_VDSO_ARCH_DATA_H +#define __RISCV_ASM_VDSO_ARCH_DATA_H #include <linux/types.h> #include <vdso/datapage.h> #include <asm/hwprobe.h> -struct arch_vdso_time_data { +struct vdso_arch_data { /* Stash static answers to the hwprobe queries when all CPUs are selected. */ __u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1]; @@ -14,4 +14,4 @@ struct arch_vdso_time_data { __u8 homogeneous_cpus; }; -#endif /* __RISCV_ASM_VDSO_TIME_DATA_H */ +#endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */ diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h index ba3283cf7acc..29164f84f93c 100644 --- a/arch/riscv/include/asm/vdso/gettimeofday.h +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -69,7 +69,7 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) #endif /* CONFIG_GENERIC_TIME_VSYSCALL */ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { /* * The purpose of csr_read(CSR_TIME) is to trap the system into @@ -79,18 +79,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return csr_read(CSR_TIME); } -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) -{ - return _vdso_data; -} - -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - return _timens_data; -} -#endif #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h index e8a9c4b53c0c..1140b54b4bc8 100644 --- a/arch/riscv/include/asm/vdso/vsyscall.h +++ b/arch/riscv/include/asm/vdso/vsyscall.h @@ -6,15 +6,6 @@ #include <vdso/datapage.h> -extern struct vdso_data *vdso_data; - -static __always_inline struct vdso_data *__riscv_get_k_vdso_data(void) -{ - return vdso_data; -} - -#define __arch_get_k_vdso_data __riscv_get_k_vdso_data - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index bcd3b816306c..04a4e5495512 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -450,8 +450,7 @@ static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, static int __init init_hwprobe_vdso_data(void) { - struct vdso_data *vd = __arch_get_k_vdso_data(); - struct arch_vdso_time_data *avd = &vd->arch_data; + struct vdso_arch_data *avd = vdso_k_arch_data; u64 id_bitsmash = 0; struct riscv_hwprobe pair; int key; diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 3ca3ae4277e1..cc2895d1fbc2 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -13,20 +13,11 @@ #include <linux/err.h> #include <asm/page.h> #include <asm/vdso.h> -#include <linux/time_namespace.h> +#include <linux/vdso_datastore.h> #include <vdso/datapage.h> #include <vdso/vsyscall.h> -enum vvar_pages { - VVAR_DATA_PAGE_OFFSET, - VVAR_TIMENS_PAGE_OFFSET, - VVAR_NR_PAGES, -}; - -#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) - -static union vdso_data_store vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = vdso_data_store.data; +#define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT) struct __vdso_info { const char *name; @@ -79,78 +70,6 @@ static void __init __vdso_init(struct __vdso_info *vdso_info) vdso_info->cm->pages = vdso_pagelist; } -#ifdef CONFIG_TIME_NS -struct vdso_data *arch_get_vdso_data(void *vvar_page) -{ - return (struct vdso_data *)(vvar_page); -} - -static const struct vm_special_mapping rv_vvar_map; - -/* - * 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; - VMA_ITERATOR(vmi, mm, 0); - - mmap_read_lock(mm); - - for_each_vma(vmi, vma) { - if (vma_is_special_mapping(vma, &rv_vvar_map)) - zap_vma_pages(vma); - } - - mmap_read_unlock(mm); - return 0; -} -#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); -} - -static const struct vm_special_mapping rv_vvar_map = { - .name = "[vvar]", - .fault = vvar_fault, -}; - static struct vm_special_mapping rv_vdso_map __ro_after_init = { .name = "[vdso]", .mremap = vdso_mremap, @@ -196,7 +115,7 @@ static int __setup_additional_pages(struct mm_struct *mm, unsigned long vdso_base, vdso_text_len, vdso_mapping_len; void *ret; - BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); + BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES); vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT; /* Be sure to map the data page */ @@ -208,8 +127,7 @@ static int __setup_additional_pages(struct mm_struct *mm, goto up_fail; } - ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, - (VM_READ | VM_MAYREAD | VM_PFNMAP), &rv_vvar_map); + ret = vdso_install_vvar_mapping(mm, vdso_base); if (IS_ERR(ret)) goto up_fail; diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 9a1b555e8733..ad73607abc28 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -2,7 +2,7 @@ # Copied from arch/tile/kernel/vdso/Makefile # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include # Symbols present in the vdso vdso-syms = rt_sigreturn ifdef CONFIG_64BIT diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c index a158c029344f..2ddeba6c68dd 100644 --- a/arch/riscv/kernel/vdso/hwprobe.c +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -16,8 +16,7 @@ static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count, size_t cpusetsize, unsigned long *cpus, unsigned int flags) { - const struct vdso_data *vd = __arch_get_vdso_data(); - const struct arch_vdso_time_data *avd = &vd->arch_data; + const struct vdso_arch_data *avd = &vdso_u_arch_data; bool all_cpus = !cpusetsize && !cpus; struct riscv_hwprobe *p = pairs; struct riscv_hwprobe *end = pairs + pair_count; @@ -51,8 +50,7 @@ static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count, size_t cpusetsize, unsigned long *cpus, unsigned int flags) { - const struct vdso_data *vd = __arch_get_vdso_data(); - const struct arch_vdso_time_data *avd = &vd->arch_data; + const struct vdso_arch_data *avd = &vdso_u_arch_data; struct riscv_hwprobe *p = pairs; struct riscv_hwprobe *end = pairs + pair_count; unsigned char *c = (unsigned char *)cpus; diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index cbe2a179331d..8e86965a8aae 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -4,15 +4,14 @@ */ #include <asm/page.h> #include <asm/vdso.h> +#include <vdso/datapage.h> OUTPUT_ARCH(riscv) SECTIONS { - PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); -#ifdef CONFIG_TIME_NS - PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); -#endif + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9c9ec08d78c7..7ed6f229250c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -166,6 +166,7 @@ config S390 select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL + select GENERIC_VDSO_DATA_STORE select GENERIC_VDSO_TIME_NS select GENERIC_IOREMAP if PCI select HAVE_ALIGNED_STRUCT_PAGE diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index 92c73e4d97a9..420a073fdde5 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -6,13 +6,11 @@ #ifndef __ASSEMBLY__ -extern struct vdso_data *vdso_data; - int vdso_getcpu_init(void); #endif /* __ASSEMBLY__ */ -#define __VVAR_PAGES 2 +#define __VDSO_PAGES 4 #define VDSO_VERSION_STRING LINUX_2.6.29 diff --git a/arch/s390/include/asm/vdso/getrandom.h b/arch/s390/include/asm/vdso/getrandom.h index 36355af7160b..f8713ce39bb2 100644 --- a/arch/s390/include/asm/vdso/getrandom.h +++ b/arch/s390/include/asm/vdso/getrandom.h @@ -23,18 +23,6 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig return syscall3(__NR_getrandom, (long)buffer, (long)len, (long)flags); } -static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void) -{ - /* - * The RNG data is in the real VVAR data page, but if a task belongs to a time namespace - * then VVAR_DATA_PAGE_OFFSET points to the namespace-specific VVAR page and VVAR_TIMENS_ - * PAGE_OFFSET points to the real VVAR page. - */ - if (IS_ENABLED(CONFIG_TIME_NS) && _vdso_data->clock_mode == VDSO_CLOCKMODE_TIMENS) - return (void *)&_vdso_rng_data + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE; - return &_vdso_rng_data; -} - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/s390/include/asm/vdso/gettimeofday.h b/arch/s390/include/asm/vdso/gettimeofday.h index 7937765ccfa5..fb4564308e9d 100644 --- a/arch/s390/include/asm/vdso/gettimeofday.h +++ b/arch/s390/include/asm/vdso/gettimeofday.h @@ -14,12 +14,7 @@ #include <linux/compiler.h> -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) -{ - return _vdso_data; -} - -static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_data *vd) +static inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_time_data *vd) { u64 adj, now; @@ -49,12 +44,4 @@ long clock_getres_fallback(clockid_t clkid, struct __kernel_timespec *ts) return syscall2(__NR_clock_getres, (long)clkid, (long)ts); } -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - return _timens_data; -} -#endif - #endif diff --git a/arch/s390/include/asm/vdso/vsyscall.h b/arch/s390/include/asm/vdso/vsyscall.h index 3eb576ecd3bd..d346ebe51301 100644 --- a/arch/s390/include/asm/vdso/vsyscall.h +++ b/arch/s390/include/asm/vdso/vsyscall.h @@ -2,32 +2,12 @@ #ifndef __ASM_VDSO_VSYSCALL_H #define __ASM_VDSO_VSYSCALL_H -#define __VDSO_RND_DATA_OFFSET 768 - #ifndef __ASSEMBLY__ #include <linux/hrtimer.h> #include <vdso/datapage.h> #include <asm/vdso.h> -enum vvar_pages { - VVAR_DATA_PAGE_OFFSET, - VVAR_TIMENS_PAGE_OFFSET, - VVAR_NR_PAGES -}; - -static __always_inline struct vdso_data *__s390_get_k_vdso_data(void) -{ - return vdso_data; -} -#define __arch_get_k_vdso_data __s390_get_k_vdso_data - -static __always_inline struct vdso_rng_data *__s390_get_k_vdso_rnd_data(void) -{ - return (void *)vdso_data + __VDSO_RND_DATA_OFFSET; -} -#define __arch_get_k_vdso_rng_data __s390_get_k_vdso_rnd_data - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index e9f47c3a6197..699a18f1c54e 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -79,12 +79,10 @@ void __init time_early_init(void) { struct ptff_qto qto; struct ptff_qui qui; - int cs; /* Initialize TOD steering parameters */ tod_steering_end = tod_clock_base.tod; - for (cs = 0; cs < CS_BASES; cs++) - vdso_data[cs].arch_data.tod_steering_end = tod_steering_end; + vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end; if (!test_facility(28)) return; @@ -373,7 +371,6 @@ static void clock_sync_global(long delta) { unsigned long now, adj; struct ptff_qto qto; - int cs; /* Fixup the monotonic sched clock. */ tod_clock_base.eitod += delta; @@ -389,10 +386,8 @@ static void clock_sync_global(long delta) panic("TOD clock sync offset %li is too large to drift\n", tod_steering_delta); tod_steering_end = now + (abs(tod_steering_delta) << 15); - for (cs = 0; cs < CS_BASES; cs++) { - vdso_data[cs].arch_data.tod_steering_end = tod_steering_end; - vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta; - } + vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end; + vdso_k_time_data->arch_data.tod_steering_delta = tod_steering_delta; /* Update LPAR offset. */ if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0) diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 598b512cde01..70c8f9ad13cd 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -16,8 +16,8 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/smp.h> -#include <linux/time_namespace.h> #include <linux/random.h> +#include <linux/vdso_datastore.h> #include <vdso/datapage.h> #include <asm/vdso/vsyscall.h> #include <asm/alternative.h> @@ -26,85 +26,6 @@ extern char vdso64_start[], vdso64_end[]; extern char vdso32_start[], vdso32_end[]; -static struct vm_special_mapping vvar_mapping; - -static union vdso_data_store vdso_data_store __page_aligned_data; - -struct vdso_data *vdso_data = vdso_data_store.data; - -#ifdef CONFIG_TIME_NS -struct vdso_data *arch_get_vdso_data(void *vvar_page) -{ - return (struct vdso_data *)(vvar_page); -} - -/* - * The VVAR page layout depends on whether a task belongs to the root or - * non-root time namespace. Whenever a task changes its namespace, the VVAR - * page tables are cleared and then they will be re-faulted with a - * corresponding layout. - * See also the comment near timens_setup_vdso_data() for details. - */ -int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) -{ - struct mm_struct *mm = task->mm; - VMA_ITERATOR(vmi, mm, 0); - struct vm_area_struct *vma; - - mmap_read_lock(mm); - for_each_vma(vmi, vma) { - if (!vma_is_special_mapping(vma, &vvar_mapping)) - continue; - zap_vma_pages(vma); - break; - } - mmap_read_unlock(mm); - return 0; -} -#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 addr, pfn; - vm_fault_t err; - - switch (vmf->pgoff) { - case VVAR_DATA_PAGE_OFFSET: - pfn = virt_to_pfn(vdso_data); - if (timens_page) { - /* - * Fault in VVAR page too, since it will be accessed - * to get clock data anyway. - */ - addr = vmf->address + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE; - err = vmf_insert_pfn(vma, addr, pfn); - if (unlikely(err & VM_FAULT_ERROR)) - return err; - pfn = page_to_pfn(timens_page); - } - 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 = virt_to_pfn(vdso_data); - break; -#endif /* CONFIG_TIME_NS */ - default: - return VM_FAULT_SIGBUS; - } - return vmf_insert_pfn(vma, vmf->address, pfn); -} - static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *vma) { @@ -112,11 +33,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm, return 0; } -static struct vm_special_mapping vvar_mapping = { - .name = "[vvar]", - .fault = vvar_fault, -}; - static struct vm_special_mapping vdso64_mapping = { .name = "[vdso]", .mremap = vdso_mremap, @@ -142,7 +58,7 @@ static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len) struct vm_area_struct *vma; int rc; - BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); + BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES); if (mmap_write_lock_killable(mm)) return -EINTR; @@ -157,14 +73,11 @@ static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len) rc = vvar_start; if (IS_ERR_VALUE(vvar_start)) goto out; - vma = _install_special_mapping(mm, vvar_start, VVAR_NR_PAGES*PAGE_SIZE, - VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP| - VM_PFNMAP, - &vvar_mapping); + vma = vdso_install_vvar_mapping(mm, vvar_start); rc = PTR_ERR(vma); if (IS_ERR(vma)) goto out; - vdso_text_start = vvar_start + VVAR_NR_PAGES * PAGE_SIZE; + vdso_text_start = vvar_start + VDSO_NR_PAGES * PAGE_SIZE; /* VM_MAYWRITE for COW so gdb can set breakpoints */ vma = _install_special_mapping(mm, vdso_text_start, vdso_text_len, VM_READ|VM_EXEC| @@ -220,7 +133,7 @@ unsigned long vdso_text_size(void) unsigned long vdso_size(void) { - return vdso_text_size() + VVAR_NR_PAGES * PAGE_SIZE; + return vdso_text_size() + VDSO_NR_PAGES * PAGE_SIZE; } int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index 2c5afb88d298..1e4ddd1a683f 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -2,7 +2,7 @@ # List of files in the vdso # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include obj-vdso32 = vdso_user_wrapper-32.o note-32.o # Build rules diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S index c916c4f73f76..9630d58c2080 100644 --- a/arch/s390/kernel/vdso32/vdso32.lds.S +++ b/arch/s390/kernel/vdso32/vdso32.lds.S @@ -6,16 +6,15 @@ #include <asm/page.h> #include <asm/vdso.h> +#include <vdso/datapage.h> OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390") OUTPUT_ARCH(s390:31-bit) SECTIONS { - PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); -#ifdef CONFIG_TIME_NS - PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); -#endif + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index ad206f2068d8..d8f0df742809 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -2,7 +2,7 @@ # List of files in the vdso # Include the generic Makefile to check the built vdso. -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include obj-vdso64 = vdso_user_wrapper.o note.o vgetrandom-chacha.o obj-cvdso64 = vdso64_generic.o getcpu.o vgetrandom.o VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S index ec42b7d9cb53..e4f6551ae898 100644 --- a/arch/s390/kernel/vdso64/vdso64.lds.S +++ b/arch/s390/kernel/vdso64/vdso64.lds.S @@ -7,17 +7,15 @@ #include <asm/vdso/vsyscall.h> #include <asm/page.h> #include <asm/vdso.h> +#include <vdso/datapage.h> OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390") OUTPUT_ARCH(s390:64-bit) SECTIONS { - PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); - PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET); -#ifdef CONFIG_TIME_NS - PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); -#endif + VDSO_VVAR_SYMS + . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 50ec2978cda5..fdc4a8f5a49c 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -22,7 +22,7 @@ targets += $(foreach x, 32 64, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg) CPPFLAGS_vdso.lds += -P -C -VDSO_LDFLAGS_vdso.lds = -m elf64_sparc -soname linux-vdso.so.1 --no-undefined \ +VDSO_LDFLAGS_vdso.lds = -m elf64_sparc -soname linux-vdso.so.1 \ -z max-page-size=8192 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE @@ -101,7 +101,6 @@ $(obj)/vdso32.so.dbg: FORCE \ quiet_cmd_vdso = VDSO $@ cmd_vdso = $(LD) -nostdlib -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ - -T $(filter %.lds,$^) $(filter %.o,$^) && \ - sh $(src)/checkundef.sh '$(OBJDUMP)' '$@' + -T $(filter %.lds,$^) $(filter %.o,$^) -VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic +VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic --no-undefined diff --git a/arch/sparc/vdso/checkundef.sh b/arch/sparc/vdso/checkundef.sh deleted file mode 100644 index 2d85876ffc32..000000000000 --- a/arch/sparc/vdso/checkundef.sh +++ /dev/null @@ -1,10 +0,0 @@ -#!/bin/sh -objdump="$1" -file="$2" -$objdump -t "$file" | grep '*UUND*' | grep -v '#scratch' > /dev/null 2>&1 -if [ $? -eq 1 ]; then - exit 0 -else - echo "$file: undefined symbols found" >&2 - exit 1 -fi diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 98bd4935280c..1665ebaba251 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -179,6 +179,7 @@ config X86 select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY + select GENERIC_VDSO_DATA_STORE select GENERIC_VDSO_TIME_NS select GENERIC_VDSO_OVERFLOW_PROTECT select GUP_GET_PXX_LOW_HIGH if X86_PAE diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index bf9f4f63e1b4..54d3e9774d62 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -4,7 +4,7 @@ # # Include the generic Makefile to check the built vDSO: -include $(srctree)/lib/vdso/Makefile +include $(srctree)/lib/vdso/Makefile.include # Files to link into the vDSO: vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vgetrandom.o vgetrandom-chacha.o @@ -32,7 +32,7 @@ targets += $(foreach x, 64 x32 32, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg CPPFLAGS_vdso.lds += -P -C -VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \ +VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 \ -z max-page-size=4096 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE @@ -152,10 +152,9 @@ $(obj)/vdso32.so.dbg: $(obj)/vdso32/vdso32.lds $(vobjs32) FORCE quiet_cmd_vdso = VDSO $@ cmd_vdso = $(LD) -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ - -T $(filter %.lds,$^) $(filter %.o,$^) && \ - sh $(src)/checkundef.sh '$(NM)' '$@' + -T $(filter %.lds,$^) $(filter %.o,$^) -VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 \ +VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 --no-undefined \ $(call ld-option, --eh-frame-hdr) -Bsymbolic -z noexecstack quiet_cmd_vdso_and_check = VDSO $@ diff --git a/arch/x86/entry/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh deleted file mode 100755 index 7ee90a9b549d..000000000000 --- a/arch/x86/entry/vdso/checkundef.sh +++ /dev/null @@ -1,10 +0,0 @@ -#!/bin/sh -nm="$1" -file="$2" -$nm "$file" | grep '^ *U' > /dev/null 2>&1 -if [ $? -eq 1 ]; then - exit 0 -else - echo "$file: undefined symbols found" >&2 - exit 1 -fi diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index 872947c1004c..ec1ac191a057 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <asm/vdso.h> #include <asm/vdso/vsyscall.h> +#include <vdso/datapage.h> /* * Linker script for vDSO. This is an ELF shared object prelinked to @@ -17,14 +18,9 @@ SECTIONS * segment. */ - vvar_start = . - __VVAR_PAGES * PAGE_SIZE; - vvar_page = vvar_start; + VDSO_VVAR_SYMS - vdso_rng_data = vvar_page + __VDSO_RND_DATA_OFFSET; - - timens_page = vvar_start + PAGE_SIZE; - - vclock_pages = vvar_start + VDSO_NR_VCLOCK_PAGES * PAGE_SIZE; + vclock_pages = VDSO_VCLOCK_PAGES_START(vdso_u_data); pvclock_page = vclock_pages + VDSO_PAGE_PVCLOCK_OFFSET * PAGE_SIZE; hvclock_page = vclock_pages + VDSO_PAGE_HVCLOCK_OFFSET * PAGE_SIZE; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 90d15f2a7205..f84e8f8fa5fe 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -69,33 +69,12 @@ const char *outfilename; -/* Symbols that we need in vdso2c. */ -enum { - sym_vvar_start, - sym_vvar_page, - sym_pvclock_page, - sym_hvclock_page, - sym_timens_page, -}; - -const int special_pages[] = { - sym_vvar_page, - sym_pvclock_page, - sym_hvclock_page, - sym_timens_page, -}; - struct vdso_sym { const char *name; bool export; }; struct vdso_sym required_syms[] = { - [sym_vvar_start] = {"vvar_start", true}, - [sym_vvar_page] = {"vvar_page", true}, - [sym_pvclock_page] = {"pvclock_page", true}, - [sym_hvclock_page] = {"hvclock_page", true}, - [sym_timens_page] = {"timens_page", true}, {"VDSO32_NOTE_MASK", true}, {"__kernel_vsyscall", true}, {"__kernel_sigreturn", true}, diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index 67b3e37576a6..78ed1c1f28b9 100644 --- a/arch/x86/entry/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h @@ -150,26 +150,6 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, } } - /* Validate mapping addresses. */ - for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) { - INT_BITS symval = syms[special_pages[i]]; - - if (!symval) - continue; /* The mapping isn't used; ignore it. */ - - if (symval % 4096) - fail("%s must be a multiple of 4096\n", - required_syms[i].name); - if (symval + 4096 < syms[sym_vvar_start]) - fail("%s underruns vvar_start\n", - required_syms[i].name); - if (symval + 4096 > 0) - fail("%s is on the wrong side of the vdso text\n", - required_syms[i].name); - } - if (syms[sym_vvar_start] % 4096) - fail("vvar_begin must be a multiple of 4096\n"); - if (!image_name) { fwrite(stripped_addr, stripped_len, 1, outfile); return; diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index bfc7cabf4017..9518bf1ddf35 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -14,7 +14,7 @@ #include <linux/elf.h> #include <linux/cpu.h> #include <linux/ptrace.h> -#include <linux/time_namespace.h> +#include <linux/vdso_datastore.h> #include <asm/pvclock.h> #include <asm/vgtod.h> @@ -27,13 +27,7 @@ #include <asm/vdso/vsyscall.h> #include <clocksource/hyperv_timer.h> -struct vdso_data *arch_get_vdso_data(void *vvar_page) -{ - return (struct vdso_data *)vvar_page; -} - -static union vdso_data_store vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = vdso_data_store.data; +static_assert(VDSO_NR_PAGES + VDSO_NR_VCLOCK_PAGES == __VDSO_PAGES); unsigned int vclocks_used __read_mostly; @@ -53,7 +47,6 @@ int __init init_vdso_image(const struct vdso_image *image) return 0; } -static const struct vm_special_mapping vvar_mapping; struct linux_binprm; static vm_fault_t vdso_fault(const struct vm_special_mapping *sm, @@ -97,99 +90,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm, return 0; } -#ifdef CONFIG_TIME_NS -/* - * The vvar page layout depends on whether a task belongs to the root or - * non-root time namespace. Whenever a task changes its namespace, the VVAR - * page tables are cleared and then they will re-faulted with a - * corresponding layout. - * See also the comment near timens_setup_vdso_data() for details. - */ -int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) -{ - struct mm_struct *mm = task->mm; - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, mm, 0); - - mmap_read_lock(mm); - for_each_vma(vmi, vma) { - if (vma_is_special_mapping(vma, &vvar_mapping)) - zap_vma_pages(vma); - } - mmap_read_unlock(mm); - - return 0; -} -#endif - -static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, - struct vm_area_struct *vma, struct vm_fault *vmf) -{ - const struct vdso_image *image = vma->vm_mm->context.vdso_image; - unsigned long pfn; - long sym_offset; - - if (!image) - return VM_FAULT_SIGBUS; - - sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) + - image->sym_vvar_start; - - /* - * Sanity check: a symbol offset of zero means that the page - * does not exist for this vdso image, not that the page is at - * offset zero relative to the text mapping. This should be - * impossible here, because sym_offset should only be zero for - * the page past the end of the vvar mapping. - */ - if (sym_offset == 0) - return VM_FAULT_SIGBUS; - - if (sym_offset == image->sym_vvar_page) { - struct page *timens_page = find_timens_vvar_page(vma); - - pfn = __pa_symbol(vdso_data) >> PAGE_SHIFT; - - /* - * If a task belongs to a time namespace then a namespace - * specific VVAR is mapped with the sym_vvar_page offset and - * the real VVAR page is mapped with the sym_timens_page - * offset. - * See also the comment near timens_setup_vdso_data(). - */ - if (timens_page) { - unsigned long addr; - vm_fault_t err; - - /* - * Optimization: inside time namespace pre-fault - * VVAR page too. As on timens page there are only - * offsets for clocks on VVAR, it'll be faulted - * shortly by VDSO code. - */ - addr = vmf->address + (image->sym_timens_page - sym_offset); - err = vmf_insert_pfn(vma, addr, pfn); - if (unlikely(err & VM_FAULT_ERROR)) - return err; - - pfn = page_to_pfn(timens_page); - } - - return vmf_insert_pfn(vma, vmf->address, pfn); - - } else if (sym_offset == image->sym_timens_page) { - struct page *timens_page = find_timens_vvar_page(vma); - - if (!timens_page) - return VM_FAULT_SIGBUS; - - pfn = __pa_symbol(vdso_data) >> PAGE_SHIFT; - return vmf_insert_pfn(vma, vmf->address, pfn); - } - - return VM_FAULT_SIGBUS; -} - static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf) { @@ -211,7 +111,6 @@ static vm_fault_t vvar_vclock_fault(const struct vm_special_mapping *sm, case VDSO_PAGE_HVCLOCK_OFFSET: { unsigned long pfn = hv_get_tsc_pfn(); - if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK)) return vmf_insert_pfn(vma, vmf->address, pfn); break; @@ -227,10 +126,6 @@ static const struct vm_special_mapping vdso_mapping = { .fault = vdso_fault, .mremap = vdso_mremap, }; -static const struct vm_special_mapping vvar_mapping = { - .name = "[vvar]", - .fault = vvar_fault, -}; static const struct vm_special_mapping vvar_vclock_mapping = { .name = "[vvar_vclock]", .fault = vvar_vclock_fault, @@ -252,13 +147,13 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr) return -EINTR; addr = get_unmapped_area(NULL, addr, - image->size - image->sym_vvar_start, 0, 0); + image->size + __VDSO_PAGES * PAGE_SIZE, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; goto up_fail; } - text_start = addr - image->sym_vvar_start; + text_start = addr + __VDSO_PAGES * PAGE_SIZE; /* * MAYWRITE to allow gdb to COW and set breakpoints @@ -275,13 +170,7 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr) goto up_fail; } - vma = _install_special_mapping(mm, - addr, - (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE, - VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP| - VM_PFNMAP, - &vvar_mapping); - + vma = vdso_install_vvar_mapping(mm, addr); if (IS_ERR(vma)) { ret = PTR_ERR(vma); do_munmap(mm, text_start, image->size, NULL); @@ -289,7 +178,7 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr) } vma = _install_special_mapping(mm, - addr + (__VVAR_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE, + VDSO_VCLOCK_PAGES_START(addr), VDSO_NR_VCLOCK_PAGES * PAGE_SIZE, VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP| VM_PFNMAP, @@ -326,7 +215,7 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr) */ for_each_vma(vmi, vma) { if (vma_is_special_mapping(vma, &vdso_mapping) || - vma_is_special_mapping(vma, &vvar_mapping) || + vma_is_special_mapping(vma, &vdso_vvar_mapping) || vma_is_special_mapping(vma, &vvar_vclock_mapping)) { mmap_write_unlock(mm); return -EEXIST; diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index d7f6592b74a9..80be0da733df 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -18,12 +18,6 @@ struct vdso_image { unsigned long extable_base, extable_len; const void *extable; - long sym_vvar_start; /* Negative offset to the vvar area */ - - long sym_vvar_page; - long sym_pvclock_page; - long sym_hvclock_page; - long sym_timens_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/vdso/getrandom.h index 785f8edcb9c9..ff1c11b9fa27 100644 --- a/arch/x86/include/asm/vdso/getrandom.h +++ b/arch/x86/include/asm/vdso/getrandom.h @@ -27,16 +27,6 @@ static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsig return ret; } -extern struct vdso_rng_data vdso_rng_data - __attribute__((visibility("hidden"))); - -static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void) -{ - if (IS_ENABLED(CONFIG_TIME_NS) && __arch_get_vdso_data()->clock_mode == VDSO_CLOCKMODE_TIMENS) - return (void *)&vdso_rng_data + ((void *)&timens_page - (void *)__arch_get_vdso_data()); - return &vdso_rng_data; -} - #endif /* !__ASSEMBLER__ */ #endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index 428f3f4c2235..73b2e7ee8f0f 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -19,12 +19,6 @@ #include <asm/pvclock.h> #include <clocksource/hyperv_timer.h> -extern struct vdso_data vvar_page - __attribute__((visibility("hidden"))); - -extern struct vdso_data timens_page - __attribute__((visibility("hidden"))); - #define VDSO_HAS_TIME 1 #define VDSO_HAS_CLOCK_GETRES 1 @@ -59,14 +53,6 @@ extern struct ms_hyperv_tsc_page hvclock_page __attribute__((visibility("hidden"))); #endif -#ifdef CONFIG_TIME_NS -static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) -{ - return &timens_page; -} -#endif - #ifndef BUILD_VDSO32 static __always_inline @@ -250,7 +236,7 @@ static u64 vread_hvclock(void) #endif static inline u64 __arch_get_hw_counter(s32 clock_mode, - const struct vdso_data *vd) + const struct vdso_time_data *vd) { if (likely(clock_mode == VDSO_CLOCKMODE_TSC)) return (u64)rdtsc_ordered() & S64_MAX; @@ -275,12 +261,7 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode, return U64_MAX; } -static __always_inline const struct vdso_data *__arch_get_vdso_data(void) -{ - return &vvar_page; -} - -static inline bool arch_vdso_clocksource_ok(const struct vdso_data *vd) +static inline bool arch_vdso_clocksource_ok(const struct vdso_clock *vc) { return true; } @@ -319,34 +300,34 @@ static inline bool arch_vdso_cycles_ok(u64 cycles) * declares everything with the MSB/Sign-bit set as invalid. Therefore the * effective mask is S64_MAX. */ -static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base) +static __always_inline u64 vdso_calc_ns(const struct vdso_clock *vc, u64 cycles, u64 base) { - u64 delta = cycles - vd->cycle_last; + u64 delta = cycles - vc->cycle_last; /* * Negative motion and deltas which can cause multiplication * overflow require special treatment. This check covers both as - * negative motion is guaranteed to be greater than @vd::max_cycles + * negative motion is guaranteed to be greater than @vc::max_cycles * due to unsigned comparison. * * Due to the MSB/Sign-bit being used as invalid marker (see * arch_vdso_cycles_ok() above), the effective mask is S64_MAX, but that * case is also unlikely and will also take the unlikely path here. */ - if (unlikely(delta > vd->max_cycles)) { + if (unlikely(delta > vc->max_cycles)) { /* * Due to the above mentioned TSC wobbles, filter out * negative motion. Per the above masking, the effective * sign bit is now bit 62. */ if (delta & (1ULL << 62)) - return base >> vd->shift; + return base >> vc->shift; /* Handle multiplication overflow gracefully */ - return mul_u64_u32_add_u64_shr(delta & S64_MAX, vd->mult, base, vd->shift); + return mul_u64_u32_add_u64_shr(delta & S64_MAX, vc->mult, base, vc->shift); } - return ((delta * vd->mult) + base) >> vd->shift; + return ((delta * vc->mult) + base) >> vc->shift; } #define vdso_calc_ns vdso_calc_ns diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h index 72aedebb7648..4aa311a923f2 100644 --- a/arch/x86/include/asm/vdso/vsyscall.h +++ b/arch/x86/include/asm/vdso/vsyscall.h @@ -2,10 +2,10 @@ #ifndef __ASM_VDSO_VSYSCALL_H #define __ASM_VDSO_VSYSCALL_H -#define __VDSO_RND_DATA_OFFSET 640 -#define __VVAR_PAGES 4 +#define __VDSO_PAGES 6 #define VDSO_NR_VCLOCK_PAGES 2 +#define VDSO_VCLOCK_PAGES_START(_b) ((_b) + (__VDSO_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE) #define VDSO_PAGE_PVCLOCK_OFFSET 0 #define VDSO_PAGE_HVCLOCK_OFFSET 1 @@ -14,25 +14,6 @@ #include <vdso/datapage.h> #include <asm/vgtod.h> -extern struct vdso_data *vdso_data; - -/* - * Update the vDSO data page to keep in sync with kernel timekeeping. - */ -static __always_inline -struct vdso_data *__x86_get_k_vdso_data(void) -{ - return vdso_data; -} -#define __arch_get_k_vdso_data __x86_get_k_vdso_data - -static __always_inline -struct vdso_rng_data *__x86_get_k_vdso_rng_data(void) -{ - return (void *)vdso_data + __VDSO_RND_DATA_OFFSET; -} -#define __arch_get_k_vdso_rng_data __x86_get_k_vdso_rng_data - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/drivers/char/random.c b/drivers/char/random.c index 2581186fa61b..92cbd24a36d8 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -278,7 +278,7 @@ static void crng_reseed(struct work_struct *work) WRITE_ONCE(base_crng.generation, next_gen); #ifdef CONFIG_VDSO_GETRANDOM /* base_crng.generation's invalid value is ULONG_MAX, while - * _vdso_rng_data.generation's invalid value is 0, so add one to the + * vdso_k_rng_data->generation's invalid value is 0, so add one to the * former to arrive at the latter. Use smp_store_release so that this * is ordered with the write above to base_crng.generation. Pairs with * the smp_rmb() before the syscall in the vDSO code. @@ -290,7 +290,7 @@ static void crng_reseed(struct work_struct *work) * because the vDSO side only checks whether the value changed, without * actually using or interpreting the value. */ - smp_store_release((unsigned long *)&__arch_get_k_vdso_rng_data()->generation, next_gen + 1); + smp_store_release((unsigned long *)&vdso_k_rng_data->generation, next_gen + 1); #endif if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; @@ -743,7 +743,7 @@ static void __cold _credit_init_bits(size_t bits) queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); #ifdef CONFIG_VDSO_GETRANDOM - WRITE_ONCE(__arch_get_k_vdso_rng_data()->is_ready, true); + WRITE_ONCE(vdso_k_rng_data->is_ready, true); #endif wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h index 01dafd604188..b550afa15ecd 100644 --- a/include/asm-generic/vdso/vsyscall.h +++ b/include/asm-generic/vdso/vsyscall.h @@ -4,24 +4,35 @@ #ifndef __ASSEMBLY__ -#ifndef __arch_get_k_vdso_data -static __always_inline struct vdso_data *__arch_get_k_vdso_data(void) +#ifdef CONFIG_GENERIC_VDSO_DATA_STORE + +#ifndef __arch_get_vdso_u_time_data +static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void) { - return NULL; + return &vdso_u_time_data; } -#endif /* __arch_get_k_vdso_data */ +#endif + +#ifndef __arch_get_vdso_u_rng_data +static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(void) +{ + return &vdso_u_rng_data; +} +#endif + +#endif /* CONFIG_GENERIC_VDSO_DATA_STORE */ #ifndef __arch_update_vsyscall -static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata) +static __always_inline void __arch_update_vsyscall(struct vdso_time_data *vdata) { } #endif /* __arch_update_vsyscall */ -#ifndef __arch_sync_vdso_data -static __always_inline void __arch_sync_vdso_data(struct vdso_data *vdata) +#ifndef __arch_sync_vdso_time_data +static __always_inline void __arch_sync_vdso_time_data(struct vdso_time_data *vdata) { } -#endif /* __arch_sync_vdso_data */ +#endif /* __arch_sync_vdso_time_data */ #endif /* !__ASSEMBLY__ */ diff --git a/include/linux/align.h b/include/linux/align.h index 2b4acec7b95a..55debf105a5d 100644 --- a/include/linux/align.h +++ b/include/linux/align.h @@ -2,14 +2,6 @@ #ifndef _LINUX_ALIGN_H #define _LINUX_ALIGN_H -#include <linux/const.h> - -/* @a is a power of 2 value */ -#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) -#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) -#define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) -#define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) -#define PTR_ALIGN_DOWN(p, a) ((typeof(p))ALIGN_DOWN((unsigned long)(p), (a))) -#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) +#include <vdso/align.h> #endif /* _LINUX_ALIGN_H */ diff --git a/include/linux/cache.h b/include/linux/cache.h index ca2a05682a54..e69768f50d53 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -3,16 +3,13 @@ #define __LINUX_CACHE_H #include <uapi/linux/kernel.h> +#include <vdso/cache.h> #include <asm/cache.h> #ifndef L1_CACHE_ALIGN #define L1_CACHE_ALIGN(x) __ALIGN_KERNEL(x, L1_CACHE_BYTES) #endif -#ifndef SMP_CACHE_BYTES -#define SMP_CACHE_BYTES L1_CACHE_BYTES -#endif - /** * SMP_CACHE_ALIGN - align a value to the L2 cacheline size * @x: value to align @@ -63,10 +60,6 @@ #define __ro_after_init __section(".data..ro_after_init") #endif -#ifndef ____cacheline_aligned -#define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES))) -#endif - #ifndef ____cacheline_aligned_in_smp #ifdef CONFIG_SMP #define ____cacheline_aligned_in_smp ____cacheline_aligned diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 876e31b4461d..0b8b32bf0655 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -165,6 +165,4 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) } #endif -struct vdso_data *arch_get_vdso_data(void *vvar_page); - #endif /* _LINUX_TIMENS_H */ diff --git a/include/linux/vdso_datastore.h b/include/linux/vdso_datastore.h new file mode 100644 index 000000000000..a91fa24b06e0 --- /dev/null +++ b/include/linux/vdso_datastore.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VDSO_DATASTORE_H +#define _LINUX_VDSO_DATASTORE_H + +#include <linux/mm_types.h> + +extern const struct vm_special_mapping vdso_vvar_mapping; +struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr); + +#endif /* _LINUX_VDSO_DATASTORE_H */ diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 8cf4ea9c544c..819ded2d39de 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -11,6 +11,7 @@ typedef __u16 Elf32_Half; typedef __u32 Elf32_Off; typedef __s32 Elf32_Sword; typedef __u32 Elf32_Word; +typedef __u16 Elf32_Versym; /* 64-bit ELF base types. */ typedef __u64 Elf64_Addr; @@ -21,6 +22,7 @@ typedef __s32 Elf64_Sword; typedef __u32 Elf64_Word; typedef __u64 Elf64_Xword; typedef __s64 Elf64_Sxword; +typedef __u16 Elf64_Versym; /* These constants are for the segment types stored in the image headers */ #define PT_NULL 0 @@ -107,6 +109,7 @@ typedef __s64 Elf64_Sxword; #define DT_VALRNGLO 0x6ffffd00 #define DT_VALRNGHI 0x6ffffdff #define DT_ADDRRNGLO 0x6ffffe00 +#define DT_GNU_HASH 0x6ffffef5 #define DT_ADDRRNGHI 0x6ffffeff #define DT_VERSYM 0x6ffffff0 #define DT_RELACOUNT 0x6ffffff9 @@ -125,6 +128,8 @@ typedef __s64 Elf64_Sxword; #define STB_GLOBAL 1 #define STB_WEAK 2 +#define STN_UNDEF 0 + #define STT_NOTYPE 0 #define STT_OBJECT 1 #define STT_FUNC 2 @@ -133,6 +138,9 @@ typedef __s64 Elf64_Sxword; #define STT_COMMON 5 #define STT_TLS 6 +#define VER_FLG_BASE 0x1 +#define VER_FLG_WEAK 0x2 + #define ELF_ST_BIND(x) ((x) >> 4) #define ELF_ST_TYPE(x) ((x) & 0xf) #define ELF32_ST_BIND(x) ELF_ST_BIND(x) @@ -572,4 +580,34 @@ typedef struct elf64_note { /* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */ #define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0) +typedef struct { + Elf32_Half vd_version; + Elf32_Half vd_flags; + Elf32_Half vd_ndx; + Elf32_Half vd_cnt; + Elf32_Word vd_hash; + Elf32_Word vd_aux; + Elf32_Word vd_next; +} Elf32_Verdef; + +typedef struct { + Elf64_Half vd_version; + Elf64_Half vd_flags; + Elf64_Half vd_ndx; + Elf64_Half vd_cnt; + Elf64_Word vd_hash; + Elf64_Word vd_aux; + Elf64_Word vd_next; +} Elf64_Verdef; + +typedef struct { + Elf32_Word vda_name; + Elf32_Word vda_next; +} Elf32_Verdaux; + +typedef struct { + Elf64_Word vda_name; + Elf64_Word vda_next; +} Elf64_Verdaux; + #endif /* _UAPI_LINUX_ELF_H */ diff --git a/include/vdso/align.h b/include/vdso/align.h new file mode 100644 index 000000000000..02dd8626b5c5 --- /dev/null +++ b/include/vdso/align.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_ALIGN_H +#define __VDSO_ALIGN_H + +#include <vdso/const.h> + +/* @a is a power of 2 value */ +#define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) +#define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) +#define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) +#define PTR_ALIGN_DOWN(p, a) ((typeof(p))ALIGN_DOWN((unsigned long)(p), (a))) +#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) + +#endif /* __VDSO_ALIGN_H */ diff --git a/include/vdso/cache.h b/include/vdso/cache.h new file mode 100644 index 000000000000..f89d48304bf8 --- /dev/null +++ b/include/vdso/cache.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_CACHE_H +#define __VDSO_CACHE_H + +#include <asm/cache.h> + +#ifndef SMP_CACHE_BYTES +#define SMP_CACHE_BYTES L1_CACHE_BYTES +#endif + +#ifndef ____cacheline_aligned +#define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES))) +#endif + +#endif /* __VDSO_ALIGN_H */ diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index d967baa0cd0c..1864e76e8f69 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -9,11 +9,14 @@ #include <uapi/linux/types.h> #include <uapi/asm-generic/errno-base.h> +#include <vdso/align.h> #include <vdso/bits.h> +#include <vdso/cache.h> #include <vdso/clocksource.h> #include <vdso/ktime.h> #include <vdso/limits.h> #include <vdso/math64.h> +#include <vdso/page.h> #include <vdso/processor.h> #include <vdso/time.h> #include <vdso/time32.h> @@ -25,6 +28,15 @@ struct arch_vdso_time_data {}; #endif +#if defined(CONFIG_ARCH_HAS_VDSO_ARCH_DATA) +#include <asm/vdso/arch_data.h> +#elif defined(CONFIG_GENERIC_VDSO_DATA_STORE) +struct vdso_arch_data { + /* Needed for the generic code, never actually used at runtime */ + char __unused; +}; +#endif + #define VDSO_BASES (CLOCK_TAI + 1) #define VDSO_HRES (BIT(CLOCK_REALTIME) | \ BIT(CLOCK_MONOTONIC) | \ @@ -45,11 +57,11 @@ struct arch_vdso_time_data {}; * * There is one vdso_timestamp object in vvar for each vDSO-accelerated * clock_id. For high-resolution clocks, this encodes the time - * corresponding to vdso_data.cycle_last. For coarse clocks this encodes + * corresponding to vdso_time_data.cycle_last. For coarse clocks this encodes * the actual time. * * To be noticed that for highres clocks nsec is left-shifted by - * vdso_data.cs[x].shift. + * vdso_time_data[x].shift. */ struct vdso_timestamp { u64 sec; @@ -57,7 +69,7 @@ struct vdso_timestamp { }; /** - * struct vdso_data - vdso datapage representation + * struct vdso_clock - vdso per clocksource datapage representation * @seq: timebase sequence counter * @clock_mode: clock mode * @cycle_last: timebase at clocksource init @@ -67,19 +79,9 @@ struct vdso_timestamp { * @shift: clocksource shift * @basetime[clock_id]: basetime per clock_id * @offset[clock_id]: time namespace offset per clock_id - * @tz_minuteswest: minutes west of Greenwich - * @tz_dsttime: type of DST correction - * @hrtimer_res: hrtimer resolution - * @__unused: unused - * @arch_data: architecture specific data (optional, defaults - * to an empty struct) * - * vdso_data will be accessed by 64 bit and compat code at the same time - * so we should be careful before modifying this structure. - * - * The ordering of the struct members is optimized to have fast access to the - * often required struct members which are related to CLOCK_REALTIME and - * CLOCK_MONOTONIC. This information is stored in the first cache lines. + * See also struct vdso_time_data for basic access and ordering information as + * struct vdso_clock is used there. * * @basetime is used to store the base time for the system wide time getter * VVAR page. @@ -92,7 +94,7 @@ struct vdso_timestamp { * For clocks which are not affected by time namespace adjustment the * offset must be zero. */ -struct vdso_data { +struct vdso_clock { u32 seq; s32 clock_mode; @@ -108,14 +110,35 @@ struct vdso_data { struct vdso_timestamp basetime[VDSO_BASES]; struct timens_offset offset[VDSO_BASES]; }; +}; + +/** + * struct vdso_time_data - vdso datapage representation + * @arch_data: architecture specific data (optional, defaults + * to an empty struct) + * @clock_data: clocksource related data (array) + * @tz_minuteswest: minutes west of Greenwich + * @tz_dsttime: type of DST correction + * @hrtimer_res: hrtimer resolution + * @__unused: unused + * + * vdso_time_data will be accessed by 64 bit and compat code at the same time + * so we should be careful before modifying this structure. + * + * The ordering of the struct members is optimized to have fast acces to the + * often required struct members which are related to CLOCK_REALTIME and + * CLOCK_MONOTONIC. This information is stored in the first cache lines. + */ +struct vdso_time_data { + struct arch_vdso_time_data arch_data; - s32 tz_minuteswest; - s32 tz_dsttime; - u32 hrtimer_res; - u32 __unused; + struct vdso_clock clock_data[CS_BASES]; - struct arch_vdso_time_data arch_data; -}; + s32 tz_minuteswest; + s32 tz_dsttime; + u32 hrtimer_res; + u32 __unused; +} ____cacheline_aligned; /** * struct vdso_rng_data - vdso RNG state information @@ -136,22 +159,32 @@ struct vdso_rng_data { * With the hidden visibility, the compiler simply generates a PC-relative * relocation, and this is what we need. */ -extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden"))); -extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden"))); -extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden"))); - -/** - * union vdso_data_store - Generic vDSO data page - */ -union vdso_data_store { - struct vdso_data data[CS_BASES]; - u8 page[1U << CONFIG_PAGE_SHIFT]; +#ifdef CONFIG_GENERIC_VDSO_DATA_STORE +extern struct vdso_time_data vdso_u_time_data __attribute__((visibility("hidden"))); +extern struct vdso_rng_data vdso_u_rng_data __attribute__((visibility("hidden"))); +extern struct vdso_arch_data vdso_u_arch_data __attribute__((visibility("hidden"))); + +extern struct vdso_time_data *vdso_k_time_data; +extern struct vdso_rng_data *vdso_k_rng_data; +extern struct vdso_arch_data *vdso_k_arch_data; + +#define VDSO_ARCH_DATA_SIZE ALIGN(sizeof(struct vdso_arch_data), PAGE_SIZE) +#define VDSO_ARCH_DATA_PAGES (VDSO_ARCH_DATA_SIZE >> PAGE_SHIFT) + +enum vdso_pages { + VDSO_TIME_PAGE_OFFSET, + VDSO_TIMENS_PAGE_OFFSET, + VDSO_RNG_PAGE_OFFSET, + VDSO_ARCH_PAGES_START, + VDSO_ARCH_PAGES_END = VDSO_ARCH_PAGES_START + VDSO_ARCH_DATA_PAGES - 1, + VDSO_NR_PAGES }; +#endif /* CONFIG_GENERIC_VDSO_DATA_STORE */ + /* * The generic vDSO implementation requires that gettimeofday.h * provides: - * - __arch_get_vdso_data(): to get the vdso datapage. * - __arch_get_hw_counter(): to get the hw counter based on the * clock_mode. * - gettimeofday_fallback(): fallback for gettimeofday. @@ -164,6 +197,27 @@ union vdso_data_store { #include <asm/vdso/gettimeofday.h> #endif /* ENABLE_COMPAT_VDSO */ +#else /* !__ASSEMBLY__ */ + +#ifdef CONFIG_VDSO_GETRANDOM +#define __vdso_u_rng_data PROVIDE(vdso_u_rng_data = vdso_u_data + 2 * PAGE_SIZE); +#else +#define __vdso_u_rng_data +#endif + +#ifdef CONFIG_ARCH_HAS_VDSO_ARCH_DATA +#define __vdso_u_arch_data PROVIDE(vdso_u_arch_data = vdso_u_data + 3 * PAGE_SIZE); +#else +#define __vdso_u_arch_data +#endif + +#define VDSO_VVAR_SYMS \ + PROVIDE(vdso_u_data = . - __VDSO_PAGES * PAGE_SIZE); \ + PROVIDE(vdso_u_time_data = vdso_u_data); \ + __vdso_u_rng_data \ + __vdso_u_arch_data \ + + #endif /* !__ASSEMBLY__ */ #endif /* __VDSO_DATAPAGE_H */ diff --git a/include/vdso/helpers.h b/include/vdso/helpers.h index 3ddb03bb05cb..0a98fed550ba 100644 --- a/include/vdso/helpers.h +++ b/include/vdso/helpers.h @@ -7,49 +7,53 @@ #include <asm/barrier.h> #include <vdso/datapage.h> -static __always_inline u32 vdso_read_begin(const struct vdso_data *vd) +static __always_inline u32 vdso_read_begin(const struct vdso_clock *vc) { u32 seq; - while (unlikely((seq = READ_ONCE(vd->seq)) & 1)) + while (unlikely((seq = READ_ONCE(vc->seq)) & 1)) cpu_relax(); smp_rmb(); return seq; } -static __always_inline u32 vdso_read_retry(const struct vdso_data *vd, +static __always_inline u32 vdso_read_retry(const struct vdso_clock *vc, u32 start) { u32 seq; smp_rmb(); - seq = READ_ONCE(vd->seq); + seq = READ_ONCE(vc->seq); return seq != start; } -static __always_inline void vdso_write_begin(struct vdso_data *vd) +static __always_inline void vdso_write_begin(struct vdso_time_data *vd) { + struct vdso_clock *vc = vd->clock_data; + /* * WRITE_ONCE() is required otherwise the compiler can validly tear * updates to vd[x].seq and it is possible that the value seen by the * reader is inconsistent. */ - WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1); - WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1); + WRITE_ONCE(vc[CS_HRES_COARSE].seq, vc[CS_HRES_COARSE].seq + 1); + WRITE_ONCE(vc[CS_RAW].seq, vc[CS_RAW].seq + 1); smp_wmb(); } -static __always_inline void vdso_write_end(struct vdso_data *vd) +static __always_inline void vdso_write_end(struct vdso_time_data *vd) { + struct vdso_clock *vc = vd->clock_data; + smp_wmb(); /* * WRITE_ONCE() is required otherwise the compiler can validly tear * updates to vd[x].seq and it is possible that the value seen by the * reader is inconsistent. */ - WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1); - WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1); + WRITE_ONCE(vc[CS_HRES_COARSE].seq, vc[CS_HRES_COARSE].seq + 1); + WRITE_ONCE(vc[CS_RAW].seq, vc[CS_RAW].seq + 1); } #endif /* !__ASSEMBLY__ */ diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c index 0775b9ec952a..e3642278df43 100644 --- a/kernel/time/namespace.c +++ b/kernel/time/namespace.c @@ -165,26 +165,26 @@ static struct timens_offset offset_from_ts(struct timespec64 off) * HVCLOCK * VVAR * - * The check for vdso_data->clock_mode is in the unlikely path of + * The check for vdso_clock->clock_mode is in the unlikely path of * the seq begin magic. So for the non-timens case most of the time * 'seq' is even, so the branch is not taken. * * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check - * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the + * for vdso_clock->clock_mode is a non-issue. The task is spin waiting for the * update to finish and for 'seq' to become even anyway. * - * Timens page has vdso_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which + * Timens page has vdso_clock->clock_mode set to VDSO_CLOCKMODE_TIMENS which * enforces the time namespace handling path. */ -static void timens_setup_vdso_data(struct vdso_data *vdata, - struct time_namespace *ns) +static void timens_setup_vdso_clock_data(struct vdso_clock *vc, + struct time_namespace *ns) { - struct timens_offset *offset = vdata->offset; + struct timens_offset *offset = vc->offset; struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic); struct timens_offset boottime = offset_from_ts(ns->offsets.boottime); - vdata->seq = 1; - vdata->clock_mode = VDSO_CLOCKMODE_TIMENS; + vc->seq = 1; + vc->clock_mode = VDSO_CLOCKMODE_TIMENS; offset[CLOCK_MONOTONIC] = monotonic; offset[CLOCK_MONOTONIC_RAW] = monotonic; offset[CLOCK_MONOTONIC_COARSE] = monotonic; @@ -219,7 +219,8 @@ static DEFINE_MUTEX(offset_lock); static void timens_set_vvar_page(struct task_struct *task, struct time_namespace *ns) { - struct vdso_data *vdata; + struct vdso_time_data *vdata; + struct vdso_clock *vc; unsigned int i; if (ns == &init_time_ns) @@ -235,10 +236,11 @@ static void timens_set_vvar_page(struct task_struct *task, goto out; ns->frozen_offsets = true; - vdata = arch_get_vdso_data(page_address(ns->vvar_page)); + vdata = page_address(ns->vvar_page); + vc = vdata->clock_data; for (i = 0; i < CS_BASES; i++) - timens_setup_vdso_data(&vdata[i], ns); + timens_setup_vdso_clock_data(&vc[i], ns); out: mutex_unlock(&offset_lock); diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 05d383143165..01c2ab1e8971 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -15,29 +15,29 @@ #include "timekeeping_internal.h" -static inline void update_vdso_data(struct vdso_data *vdata, - struct timekeeper *tk) +static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct timekeeper *tk) { + struct vdso_clock *vc = vdata->clock_data; struct vdso_timestamp *vdso_ts; u64 nsec, sec; - vdata[CS_HRES_COARSE].cycle_last = tk->tkr_mono.cycle_last; + vc[CS_HRES_COARSE].cycle_last = tk->tkr_mono.cycle_last; #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT - vdata[CS_HRES_COARSE].max_cycles = tk->tkr_mono.clock->max_cycles; + vc[CS_HRES_COARSE].max_cycles = tk->tkr_mono.clock->max_cycles; #endif - vdata[CS_HRES_COARSE].mask = tk->tkr_mono.mask; - vdata[CS_HRES_COARSE].mult = tk->tkr_mono.mult; - vdata[CS_HRES_COARSE].shift = tk->tkr_mono.shift; - vdata[CS_RAW].cycle_last = tk->tkr_raw.cycle_last; + vc[CS_HRES_COARSE].mask = tk->tkr_mono.mask; + vc[CS_HRES_COARSE].mult = tk->tkr_mono.mult; + vc[CS_HRES_COARSE].shift = tk->tkr_mono.shift; + vc[CS_RAW].cycle_last = tk->tkr_raw.cycle_last; #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT - vdata[CS_RAW].max_cycles = tk->tkr_raw.clock->max_cycles; + vc[CS_RAW].max_cycles = tk->tkr_raw.clock->max_cycles; #endif - vdata[CS_RAW].mask = tk->tkr_raw.mask; - vdata[CS_RAW].mult = tk->tkr_raw.mult; - vdata[CS_RAW].shift = tk->tkr_raw.shift; + vc[CS_RAW].mask = tk->tkr_raw.mask; + vc[CS_RAW].mult = tk->tkr_raw.mult; + vc[CS_RAW].shift = tk->tkr_raw.shift; /* CLOCK_MONOTONIC */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC]; + vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; nsec = tk->tkr_mono.xtime_nsec; @@ -55,7 +55,7 @@ static inline void update_vdso_data(struct vdso_data *vdata, nsec += (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift; /* CLOCK_BOOTTIME */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME]; + vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME]; vdso_ts->sec = sec; while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { @@ -65,19 +65,20 @@ static inline void update_vdso_data(struct vdso_data *vdata, vdso_ts->nsec = nsec; /* CLOCK_MONOTONIC_RAW */ - vdso_ts = &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW]; + vdso_ts = &vc[CS_RAW].basetime[CLOCK_MONOTONIC_RAW]; vdso_ts->sec = tk->raw_sec; vdso_ts->nsec = tk->tkr_raw.xtime_nsec; /* CLOCK_TAI */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI]; + vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_TAI]; vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; } void update_vsyscall(struct timekeeper *tk) { - struct vdso_data *vdata = __arch_get_k_vdso_data(); + struct vdso_time_data *vdata = vdso_k_time_data; + struct vdso_clock *vc = vdata->clock_data; struct vdso_timestamp *vdso_ts; s32 clock_mode; u64 nsec; @@ -86,21 +87,21 @@ void update_vsyscall(struct timekeeper *tk) vdso_write_begin(vdata); clock_mode = tk->tkr_mono.clock->vdso_clock_mode; - vdata[CS_HRES_COARSE].clock_mode = clock_mode; - vdata[CS_RAW].clock_mode = clock_mode; + vc[CS_HRES_COARSE].clock_mode = clock_mode; + vc[CS_RAW].clock_mode = clock_mode; /* CLOCK_REALTIME also required for time() */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; + vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; vdso_ts->sec = tk->xtime_sec; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; /* CLOCK_REALTIME_COARSE */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; + vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; vdso_ts->sec = tk->xtime_sec; vdso_ts->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; /* CLOCK_MONOTONIC_COARSE */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE]; + vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; nsec = nsec + tk->wall_to_monotonic.tv_nsec; @@ -108,32 +109,31 @@ void update_vsyscall(struct timekeeper *tk) /* * Read without the seqlock held by clock_getres(). - * Note: No need to have a second copy. */ - WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution); + WRITE_ONCE(vdata->hrtimer_res, hrtimer_resolution); /* * If the current clocksource is not VDSO capable, then spare the * update of the high resolution parts. */ if (clock_mode != VDSO_CLOCKMODE_NONE) - update_vdso_data(vdata, tk); + update_vdso_time_data(vdata, tk); __arch_update_vsyscall(vdata); vdso_write_end(vdata); - __arch_sync_vdso_data(vdata); + __arch_sync_vdso_time_data(vdata); } void update_vsyscall_tz(void) { - struct vdso_data *vdata = __arch_get_k_vdso_data(); + struct vdso_time_data *vdata = vdso_k_time_data; - vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest; - vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime; + vdata->tz_minuteswest = sys_tz.tz_minuteswest; + vdata->tz_dsttime = sys_tz.tz_dsttime; - __arch_sync_vdso_data(vdata); + __arch_sync_vdso_time_data(vdata); } /** @@ -150,7 +150,7 @@ void update_vsyscall_tz(void) */ unsigned long vdso_update_begin(void) { - struct vdso_data *vdata = __arch_get_k_vdso_data(); + struct vdso_time_data *vdata = vdso_k_time_data; unsigned long flags = timekeeper_lock_irqsave(); vdso_write_begin(vdata); @@ -167,9 +167,9 @@ unsigned long vdso_update_begin(void) */ void vdso_update_end(unsigned long flags) { - struct vdso_data *vdata = __arch_get_k_vdso_data(); + struct vdso_time_data *vdata = vdso_k_time_data; vdso_write_end(vdata); - __arch_sync_vdso_data(vdata); + __arch_sync_vdso_time_data(vdata); timekeeper_unlock_irqrestore(flags); } diff --git a/lib/Makefile b/lib/Makefile index 6de467a02b03..b752fcbc83d2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -124,7 +124,7 @@ endif obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any) -obj-y += math/ crypto/ tests/ +obj-y += math/ crypto/ tests/ vdso/ obj-$(CONFIG_GENERIC_IOMAP) += iomap.o obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index 82fe827af542..45df764b49ad 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -43,3 +43,8 @@ config VDSO_GETRANDOM bool help Selected by architectures that support vDSO getrandom(). + +config GENERIC_VDSO_DATA_STORE + bool + help + Selected by architectures that use the generic vDSO data store. diff --git a/lib/vdso/Makefile b/lib/vdso/Makefile index cedbf15f8087..aedd40aaa950 100644 --- a/lib/vdso/Makefile +++ b/lib/vdso/Makefile @@ -1,18 +1,3 @@ -# SPDX-License-Identifier: GPL-2.0 +# SPDX-License-Identifier: GPL-2.0-only -GENERIC_VDSO_MK_PATH := $(abspath $(lastword $(MAKEFILE_LIST))) -GENERIC_VDSO_DIR := $(dir $(GENERIC_VDSO_MK_PATH)) - -c-gettimeofday-$(CONFIG_GENERIC_GETTIMEOFDAY) := $(addprefix $(GENERIC_VDSO_DIR), gettimeofday.c) -c-getrandom-$(CONFIG_VDSO_GETRANDOM) := $(addprefix $(GENERIC_VDSO_DIR), getrandom.c) - -# This cmd checks that the vdso library does not contain dynamic relocations. -# It has to be called after the linking of the vdso library and requires it -# as a parameter. -# -# As a workaround for some GNU ld ports which produce unneeded R_*_NONE -# dynamic relocations, ignore R_*_NONE. -quiet_cmd_vdso_check = VDSOCHK $@ - cmd_vdso_check = if $(READELF) -rW $@ | grep -v _NONE | grep -q " R_\w*_"; \ - then (echo >&2 "$@: dynamic relocations are not supported"; \ - rm -f $@; /bin/false); fi +obj-$(CONFIG_GENERIC_VDSO_DATA_STORE) += datastore.o diff --git a/lib/vdso/Makefile.include b/lib/vdso/Makefile.include new file mode 100644 index 000000000000..cedbf15f8087 --- /dev/null +++ b/lib/vdso/Makefile.include @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0 + +GENERIC_VDSO_MK_PATH := $(abspath $(lastword $(MAKEFILE_LIST))) +GENERIC_VDSO_DIR := $(dir $(GENERIC_VDSO_MK_PATH)) + +c-gettimeofday-$(CONFIG_GENERIC_GETTIMEOFDAY) := $(addprefix $(GENERIC_VDSO_DIR), gettimeofday.c) +c-getrandom-$(CONFIG_VDSO_GETRANDOM) := $(addprefix $(GENERIC_VDSO_DIR), getrandom.c) + +# This cmd checks that the vdso library does not contain dynamic relocations. +# It has to be called after the linking of the vdso library and requires it +# as a parameter. +# +# As a workaround for some GNU ld ports which produce unneeded R_*_NONE +# dynamic relocations, ignore R_*_NONE. +quiet_cmd_vdso_check = VDSOCHK $@ + cmd_vdso_check = if $(READELF) -rW $@ | grep -v _NONE | grep -q " R_\w*_"; \ + then (echo >&2 "$@: dynamic relocations are not supported"; \ + rm -f $@; /bin/false); fi diff --git a/lib/vdso/datastore.c b/lib/vdso/datastore.c new file mode 100644 index 000000000000..c715e217ec65 --- /dev/null +++ b/lib/vdso/datastore.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/linkage.h> +#include <linux/mmap_lock.h> +#include <linux/mm.h> +#include <linux/time_namespace.h> +#include <linux/types.h> +#include <linux/vdso_datastore.h> +#include <vdso/datapage.h> + +/* + * The vDSO data page. + */ +#ifdef CONFIG_HAVE_GENERIC_VDSO +static union { + struct vdso_time_data data; + u8 page[PAGE_SIZE]; +} vdso_time_data_store __page_aligned_data; +struct vdso_time_data *vdso_k_time_data = &vdso_time_data_store.data; +static_assert(sizeof(vdso_time_data_store) == PAGE_SIZE); +#endif /* CONFIG_HAVE_GENERIC_VDSO */ + +#ifdef CONFIG_VDSO_GETRANDOM +static union { + struct vdso_rng_data data; + u8 page[PAGE_SIZE]; +} vdso_rng_data_store __page_aligned_data; +struct vdso_rng_data *vdso_k_rng_data = &vdso_rng_data_store.data; +static_assert(sizeof(vdso_rng_data_store) == PAGE_SIZE); +#endif /* CONFIG_VDSO_GETRANDOM */ + +#ifdef CONFIG_ARCH_HAS_VDSO_ARCH_DATA +static union { + struct vdso_arch_data data; + u8 page[VDSO_ARCH_DATA_SIZE]; +} vdso_arch_data_store __page_aligned_data; +struct vdso_arch_data *vdso_k_arch_data = &vdso_arch_data_store.data; +#endif /* CONFIG_ARCH_HAS_VDSO_ARCH_DATA */ + +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 addr, pfn; + vm_fault_t err; + + switch (vmf->pgoff) { + case VDSO_TIME_PAGE_OFFSET: + if (!IS_ENABLED(CONFIG_HAVE_GENERIC_VDSO)) + return VM_FAULT_SIGBUS; + pfn = __phys_to_pfn(__pa_symbol(vdso_k_time_data)); + if (timens_page) { + /* + * Fault in VVAR page too, since it will be accessed + * to get clock data anyway. + */ + addr = vmf->address + VDSO_TIMENS_PAGE_OFFSET * PAGE_SIZE; + err = vmf_insert_pfn(vma, addr, pfn); + if (unlikely(err & VM_FAULT_ERROR)) + return err; + pfn = page_to_pfn(timens_page); + } + break; + case VDSO_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 (!IS_ENABLED(CONFIG_TIME_NS) || !timens_page) + return VM_FAULT_SIGBUS; + pfn = __phys_to_pfn(__pa_symbol(vdso_k_time_data)); + break; + case VDSO_RNG_PAGE_OFFSET: + if (!IS_ENABLED(CONFIG_VDSO_GETRANDOM)) + return VM_FAULT_SIGBUS; + pfn = __phys_to_pfn(__pa_symbol(vdso_k_rng_data)); + break; + case VDSO_ARCH_PAGES_START ... VDSO_ARCH_PAGES_END: + if (!IS_ENABLED(CONFIG_ARCH_HAS_VDSO_ARCH_DATA)) + return VM_FAULT_SIGBUS; + pfn = __phys_to_pfn(__pa_symbol(vdso_k_arch_data)) + + vmf->pgoff - VDSO_ARCH_PAGES_START; + break; + default: + return VM_FAULT_SIGBUS; + } + + return vmf_insert_pfn(vma, vmf->address, pfn); +} + +const struct vm_special_mapping vdso_vvar_mapping = { + .name = "[vvar]", + .fault = vvar_fault, +}; + +struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr) +{ + return _install_special_mapping(mm, addr, VDSO_NR_PAGES * PAGE_SIZE, + VM_READ | VM_MAYREAD | VM_IO | VM_DONTDUMP | VM_PFNMAP, + &vdso_vvar_mapping); +} + +#ifdef CONFIG_TIME_NS +/* + * The vvar page layout depends on whether a task belongs to the root or + * non-root time namespace. Whenever a task changes its namespace, the VVAR + * page tables are cleared and then they will be re-faulted with a + * corresponding layout. + * See also the comment near timens_setup_vdso_clock_data() for details. + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); + + mmap_read_lock(mm); + for_each_vma(vmi, vma) { + if (vma_is_special_mapping(vma, &vdso_vvar_mapping)) + zap_vma_pages(vma); + } + mmap_read_unlock(mm); + + return 0; +} +#endif diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c index 938ca539aaa6..440f8a6203a6 100644 --- a/lib/vdso/getrandom.c +++ b/lib/vdso/getrandom.c @@ -12,6 +12,9 @@ #include <uapi/linux/mman.h> #include <uapi/linux/random.h> +/* Bring in default accessors */ +#include <vdso/vsyscall.h> + #undef PAGE_SIZE #undef PAGE_MASK #define PAGE_SIZE (1UL << CONFIG_PAGE_SHIFT) @@ -152,7 +155,7 @@ retry_generation: /* * Prevent the syscall from being reordered wrt current_generation. Pairs with the - * smp_store_release(&_vdso_rng_data.generation) in random.c. + * smp_store_release(&vdso_k_rng_data->generation) in random.c. */ smp_rmb(); @@ -256,5 +259,6 @@ fallback_syscall: static __always_inline ssize_t __cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) { - return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len); + return __cvdso_getrandom_data(__arch_get_vdso_u_rng_data(), buffer, len, flags, + opaque_state, opaque_len); } diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index c01eaafd8041..93ef801a97ef 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -5,6 +5,9 @@ #include <vdso/datapage.h> #include <vdso/helpers.h> +/* Bring in default accessors */ +#include <vdso/vsyscall.h> + #ifndef vdso_calc_ns #ifdef VDSO_DELTA_NOMASK @@ -14,12 +17,12 @@ #endif #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT -static __always_inline bool vdso_delta_ok(const struct vdso_data *vd, u64 delta) +static __always_inline bool vdso_delta_ok(const struct vdso_clock *vc, u64 delta) { - return delta < vd->max_cycles; + return delta < vc->max_cycles; } #else -static __always_inline bool vdso_delta_ok(const struct vdso_data *vd, u64 delta) +static __always_inline bool vdso_delta_ok(const struct vdso_clock *vc, u64 delta) { return true; } @@ -36,14 +39,14 @@ static __always_inline u64 vdso_shift_ns(u64 ns, u32 shift) * Default implementation which works for all sane clocksources. That * obviously excludes x86/TSC. */ -static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base) +static __always_inline u64 vdso_calc_ns(const struct vdso_clock *vc, u64 cycles, u64 base) { - u64 delta = (cycles - vd->cycle_last) & VDSO_DELTA_MASK(vd); + u64 delta = (cycles - vc->cycle_last) & VDSO_DELTA_MASK(vc); - if (likely(vdso_delta_ok(vd, delta))) - return vdso_shift_ns((delta * vd->mult) + base, vd->shift); + if (likely(vdso_delta_ok(vc, delta))) + return vdso_shift_ns((delta * vc->mult) + base, vc->shift); - return mul_u64_u32_add_u64_shr(delta, vd->mult, base, vd->shift); + return mul_u64_u32_add_u64_shr(delta, vc->mult, base, vc->shift); } #endif /* vdso_calc_ns */ @@ -55,9 +58,9 @@ static inline bool __arch_vdso_hres_capable(void) #endif #ifndef vdso_clocksource_ok -static inline bool vdso_clocksource_ok(const struct vdso_data *vd) +static inline bool vdso_clocksource_ok(const struct vdso_clock *vc) { - return vd->clock_mode != VDSO_CLOCKMODE_NONE; + return vc->clock_mode != VDSO_CLOCKMODE_NONE; } #endif @@ -69,36 +72,45 @@ static inline bool vdso_cycles_ok(u64 cycles) #endif #ifdef CONFIG_TIME_NS -static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk, - struct __kernel_timespec *ts) + +#ifdef CONFIG_GENERIC_VDSO_DATA_STORE +static __always_inline +const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_time_data *vd) +{ + return (void *)vd + PAGE_SIZE; +} +#endif /* CONFIG_GENERIC_VDSO_DATA_STORE */ + +static __always_inline +int do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns, + clockid_t clk, struct __kernel_timespec *ts) { - const struct timens_offset *offs = &vdns->offset[clk]; + const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns); + const struct timens_offset *offs = &vcns->offset[clk]; + const struct vdso_clock *vc = vd->clock_data; const struct vdso_timestamp *vdso_ts; - const struct vdso_data *vd; u64 cycles, ns; u32 seq; s64 sec; - vd = vdns - (clk == CLOCK_MONOTONIC_RAW ? CS_RAW : CS_HRES_COARSE); - vd = __arch_get_timens_vdso_data(vd); if (clk != CLOCK_MONOTONIC_RAW) - vd = &vd[CS_HRES_COARSE]; + vc = &vc[CS_HRES_COARSE]; else - vd = &vd[CS_RAW]; - vdso_ts = &vd->basetime[clk]; + vc = &vc[CS_RAW]; + vdso_ts = &vc->basetime[clk]; do { - seq = vdso_read_begin(vd); + seq = vdso_read_begin(vc); - if (unlikely(!vdso_clocksource_ok(vd))) + if (unlikely(!vdso_clocksource_ok(vc))) return -1; - cycles = __arch_get_hw_counter(vd->clock_mode, vd); + cycles = __arch_get_hw_counter(vc->clock_mode, vd); if (unlikely(!vdso_cycles_ok(cycles))) return -1; - ns = vdso_calc_ns(vd, cycles, vdso_ts->nsec); + ns = vdso_calc_ns(vc, cycles, vdso_ts->nsec); sec = vdso_ts->sec; - } while (unlikely(vdso_read_retry(vd, seq))); + } while (unlikely(vdso_read_retry(vc, seq))); /* Add the namespace offset */ sec += offs->sec; @@ -115,22 +127,24 @@ static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_ } #else static __always_inline -const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) +const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_time_data *vd) { return NULL; } -static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline +int do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns, + clockid_t clk, struct __kernel_timespec *ts) { return -EINVAL; } #endif -static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline +int do_hres(const struct vdso_time_data *vd, const struct vdso_clock *vc, + clockid_t clk, struct __kernel_timespec *ts) { - const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; + const struct vdso_timestamp *vdso_ts = &vc->basetime[clk]; u64 cycles, sec, ns; u32 seq; @@ -142,31 +156,31 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, /* * Open coded function vdso_read_begin() to handle * VDSO_CLOCKMODE_TIMENS. Time namespace enabled tasks have a - * special VVAR page installed which has vd->seq set to 1 and - * vd->clock_mode set to VDSO_CLOCKMODE_TIMENS. For non time + * special VVAR page installed which has vc->seq set to 1 and + * vc->clock_mode set to VDSO_CLOCKMODE_TIMENS. For non time * namespace affected tasks this does not affect performance - * because if vd->seq is odd, i.e. a concurrent update is in - * progress the extra check for vd->clock_mode is just a few - * extra instructions while spin waiting for vd->seq to become + * because if vc->seq is odd, i.e. a concurrent update is in + * progress the extra check for vc->clock_mode is just a few + * extra instructions while spin waiting for vc->seq to become * even again. */ - while (unlikely((seq = READ_ONCE(vd->seq)) & 1)) { + while (unlikely((seq = READ_ONCE(vc->seq)) & 1)) { if (IS_ENABLED(CONFIG_TIME_NS) && - vd->clock_mode == VDSO_CLOCKMODE_TIMENS) - return do_hres_timens(vd, clk, ts); + vc->clock_mode == VDSO_CLOCKMODE_TIMENS) + return do_hres_timens(vd, vc, clk, ts); cpu_relax(); } smp_rmb(); - if (unlikely(!vdso_clocksource_ok(vd))) + if (unlikely(!vdso_clocksource_ok(vc))) return -1; - cycles = __arch_get_hw_counter(vd->clock_mode, vd); + cycles = __arch_get_hw_counter(vc->clock_mode, vd); if (unlikely(!vdso_cycles_ok(cycles))) return -1; - ns = vdso_calc_ns(vd, cycles, vdso_ts->nsec); + ns = vdso_calc_ns(vc, cycles, vdso_ts->nsec); sec = vdso_ts->sec; - } while (unlikely(vdso_read_retry(vd, seq))); + } while (unlikely(vdso_read_retry(vc, seq))); /* * Do this outside the loop: a race inside the loop could result @@ -179,21 +193,25 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, } #ifdef CONFIG_TIME_NS -static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline +int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns, + clockid_t clk, struct __kernel_timespec *ts) { - const struct vdso_data *vd = __arch_get_timens_vdso_data(vdns); - const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; - const struct timens_offset *offs = &vdns->offset[clk]; + const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns); + const struct timens_offset *offs = &vcns->offset[clk]; + const struct vdso_clock *vc = vd->clock_data; + const struct vdso_timestamp *vdso_ts; u64 nsec; s64 sec; s32 seq; + vdso_ts = &vc->basetime[clk]; + do { - seq = vdso_read_begin(vd); + seq = vdso_read_begin(vc); sec = vdso_ts->sec; nsec = vdso_ts->nsec; - } while (unlikely(vdso_read_retry(vd, seq))); + } while (unlikely(vdso_read_retry(vc, seq))); /* Add the namespace offset */ sec += offs->sec; @@ -208,17 +226,19 @@ static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clocki return 0; } #else -static __always_inline int do_coarse_timens(const struct vdso_data *vdns, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline +int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns, + clockid_t clk, struct __kernel_timespec *ts) { return -1; } #endif -static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk, - struct __kernel_timespec *ts) +static __always_inline +int do_coarse(const struct vdso_time_data *vd, const struct vdso_clock *vc, + clockid_t clk, struct __kernel_timespec *ts) { - const struct vdso_timestamp *vdso_ts = &vd->basetime[clk]; + const struct vdso_timestamp *vdso_ts = &vc->basetime[clk]; u32 seq; do { @@ -226,25 +246,26 @@ static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk, * Open coded function vdso_read_begin() to handle * VDSO_CLOCK_TIMENS. See comment in do_hres(). */ - while ((seq = READ_ONCE(vd->seq)) & 1) { + while ((seq = READ_ONCE(vc->seq)) & 1) { if (IS_ENABLED(CONFIG_TIME_NS) && - vd->clock_mode == VDSO_CLOCKMODE_TIMENS) - return do_coarse_timens(vd, clk, ts); + vc->clock_mode == VDSO_CLOCKMODE_TIMENS) + return do_coarse_timens(vd, vc, clk, ts); cpu_relax(); } smp_rmb(); ts->tv_sec = vdso_ts->sec; ts->tv_nsec = vdso_ts->nsec; - } while (unlikely(vdso_read_retry(vd, seq))); + } while (unlikely(vdso_read_retry(vc, seq))); return 0; } static __always_inline int -__cvdso_clock_gettime_common(const struct vdso_data *vd, clockid_t clock, +__cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock, struct __kernel_timespec *ts) { + const struct vdso_clock *vc = vd->clock_data; u32 msk; /* Check for negative values or invalid clocks */ @@ -257,19 +278,19 @@ __cvdso_clock_gettime_common(const struct vdso_data *vd, clockid_t clock, */ msk = 1U << clock; if (likely(msk & VDSO_HRES)) - vd = &vd[CS_HRES_COARSE]; + vc = &vc[CS_HRES_COARSE]; else if (msk & VDSO_COARSE) - return do_coarse(&vd[CS_HRES_COARSE], clock, ts); + return do_coarse(vd, &vc[CS_HRES_COARSE], clock, ts); else if (msk & VDSO_RAW) - vd = &vd[CS_RAW]; + vc = &vc[CS_RAW]; else return -1; - return do_hres(vd, clock, ts); + return do_hres(vd, vc, clock, ts); } static __maybe_unused int -__cvdso_clock_gettime_data(const struct vdso_data *vd, clockid_t clock, +__cvdso_clock_gettime_data(const struct vdso_time_data *vd, clockid_t clock, struct __kernel_timespec *ts) { int ret = __cvdso_clock_gettime_common(vd, clock, ts); @@ -282,12 +303,12 @@ __cvdso_clock_gettime_data(const struct vdso_data *vd, clockid_t clock, static __maybe_unused int __cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { - return __cvdso_clock_gettime_data(__arch_get_vdso_data(), clock, ts); + return __cvdso_clock_gettime_data(__arch_get_vdso_u_time_data(), clock, ts); } #ifdef BUILD_VDSO32 static __maybe_unused int -__cvdso_clock_gettime32_data(const struct vdso_data *vd, clockid_t clock, +__cvdso_clock_gettime32_data(const struct vdso_time_data *vd, clockid_t clock, struct old_timespec32 *res) { struct __kernel_timespec ts; @@ -308,19 +329,20 @@ __cvdso_clock_gettime32_data(const struct vdso_data *vd, clockid_t clock, static __maybe_unused int __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res) { - return __cvdso_clock_gettime32_data(__arch_get_vdso_data(), clock, res); + return __cvdso_clock_gettime32_data(__arch_get_vdso_u_time_data(), clock, res); } #endif /* BUILD_VDSO32 */ static __maybe_unused int -__cvdso_gettimeofday_data(const struct vdso_data *vd, +__cvdso_gettimeofday_data(const struct vdso_time_data *vd, struct __kernel_old_timeval *tv, struct timezone *tz) { + const struct vdso_clock *vc = vd->clock_data; if (likely(tv != NULL)) { struct __kernel_timespec ts; - if (do_hres(&vd[CS_HRES_COARSE], CLOCK_REALTIME, &ts)) + if (do_hres(vd, &vc[CS_HRES_COARSE], CLOCK_REALTIME, &ts)) return gettimeofday_fallback(tv, tz); tv->tv_sec = ts.tv_sec; @@ -329,8 +351,8 @@ __cvdso_gettimeofday_data(const struct vdso_data *vd, if (unlikely(tz != NULL)) { if (IS_ENABLED(CONFIG_TIME_NS) && - vd->clock_mode == VDSO_CLOCKMODE_TIMENS) - vd = __arch_get_timens_vdso_data(vd); + vc->clock_mode == VDSO_CLOCKMODE_TIMENS) + vd = __arch_get_vdso_u_timens_data(vd); tz->tz_minuteswest = vd[CS_HRES_COARSE].tz_minuteswest; tz->tz_dsttime = vd[CS_HRES_COARSE].tz_dsttime; @@ -342,20 +364,23 @@ __cvdso_gettimeofday_data(const struct vdso_data *vd, static __maybe_unused int __cvdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { - return __cvdso_gettimeofday_data(__arch_get_vdso_data(), tv, tz); + return __cvdso_gettimeofday_data(__arch_get_vdso_u_time_data(), tv, tz); } #ifdef VDSO_HAS_TIME static __maybe_unused __kernel_old_time_t -__cvdso_time_data(const struct vdso_data *vd, __kernel_old_time_t *time) +__cvdso_time_data(const struct vdso_time_data *vd, __kernel_old_time_t *time) { + const struct vdso_clock *vc = vd->clock_data; __kernel_old_time_t t; if (IS_ENABLED(CONFIG_TIME_NS) && - vd->clock_mode == VDSO_CLOCKMODE_TIMENS) - vd = __arch_get_timens_vdso_data(vd); + vc->clock_mode == VDSO_CLOCKMODE_TIMENS) { + vd = __arch_get_vdso_u_timens_data(vd); + vc = vd->clock_data; + } - t = READ_ONCE(vd[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec); + t = READ_ONCE(vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME].sec); if (time) *time = t; @@ -365,15 +390,16 @@ __cvdso_time_data(const struct vdso_data *vd, __kernel_old_time_t *time) static __maybe_unused __kernel_old_time_t __cvdso_time(__kernel_old_time_t *time) { - return __cvdso_time_data(__arch_get_vdso_data(), time); + return __cvdso_time_data(__arch_get_vdso_u_time_data(), time); } #endif /* VDSO_HAS_TIME */ #ifdef VDSO_HAS_CLOCK_GETRES static __maybe_unused -int __cvdso_clock_getres_common(const struct vdso_data *vd, clockid_t clock, +int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock, struct __kernel_timespec *res) { + const struct vdso_clock *vc = vd->clock_data; u32 msk; u64 ns; @@ -382,8 +408,8 @@ int __cvdso_clock_getres_common(const struct vdso_data *vd, clockid_t clock, return -1; if (IS_ENABLED(CONFIG_TIME_NS) && - vd->clock_mode == VDSO_CLOCKMODE_TIMENS) - vd = __arch_get_timens_vdso_data(vd); + vc->clock_mode == VDSO_CLOCKMODE_TIMENS) + vd = __arch_get_vdso_u_timens_data(vd); /* * Convert the clockid to a bitmask and use it to check which @@ -394,7 +420,7 @@ int __cvdso_clock_getres_common(const struct vdso_data *vd, clockid_t clock, /* * Preserves the behaviour of posix_get_hrtimer_res(). */ - ns = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res); + ns = READ_ONCE(vd->hrtimer_res); } else if (msk & VDSO_COARSE) { /* * Preserves the behaviour of posix_get_coarse_res(). @@ -412,7 +438,7 @@ int __cvdso_clock_getres_common(const struct vdso_data *vd, clockid_t clock, } static __maybe_unused -int __cvdso_clock_getres_data(const struct vdso_data *vd, clockid_t clock, +int __cvdso_clock_getres_data(const struct vdso_time_data *vd, clockid_t clock, struct __kernel_timespec *res) { int ret = __cvdso_clock_getres_common(vd, clock, res); @@ -425,12 +451,12 @@ int __cvdso_clock_getres_data(const struct vdso_data *vd, clockid_t clock, static __maybe_unused int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) { - return __cvdso_clock_getres_data(__arch_get_vdso_data(), clock, res); + return __cvdso_clock_getres_data(__arch_get_vdso_u_time_data(), clock, res); } #ifdef BUILD_VDSO32 static __maybe_unused int -__cvdso_clock_getres_time32_data(const struct vdso_data *vd, clockid_t clock, +__cvdso_clock_getres_time32_data(const struct vdso_time_data *vd, clockid_t clock, struct old_timespec32 *res) { struct __kernel_timespec ts; @@ -451,7 +477,7 @@ __cvdso_clock_getres_time32_data(const struct vdso_data *vd, clockid_t clock, static __maybe_unused int __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res) { - return __cvdso_clock_getres_time32_data(__arch_get_vdso_data(), + return __cvdso_clock_getres_time32_data(__arch_get_vdso_u_time_data(), clock, res); } #endif /* BUILD_VDSO32 */ diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile index dceec0e1a135..f9702877ac21 100644 --- a/tools/include/nolibc/Makefile +++ b/tools/include/nolibc/Makefile @@ -31,6 +31,7 @@ all_files := \ ctype.h \ dirent.h \ errno.h \ + limits.h \ nolibc.h \ signal.h \ stackprotector.h \ diff --git a/tools/include/nolibc/limits.h b/tools/include/nolibc/limits.h new file mode 100644 index 000000000000..306d4141f4d2 --- /dev/null +++ b/tools/include/nolibc/limits.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Shim limits.h header for NOLIBC. + * Copyright (C) 2025 Thomas Weißschuh <thomas.weissschuh@linutronix.de> + */ + +#include "nolibc.h" diff --git a/tools/include/uapi/linux/elf.h b/tools/include/uapi/linux/elf.h new file mode 100644 index 000000000000..5834b83d7f9a --- /dev/null +++ b/tools/include/uapi/linux/elf.h @@ -0,0 +1,524 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_ELF_H +#define _LINUX_ELF_H + +#include <linux/types.h> +#include <linux/elf-em.h> + +/* 32-bit ELF base types. */ +typedef __u32 Elf32_Addr; +typedef __u16 Elf32_Half; +typedef __u32 Elf32_Off; +typedef __s32 Elf32_Sword; +typedef __u32 Elf32_Word; +typedef __u16 Elf32_Versym; + +/* 64-bit ELF base types. */ +typedef __u64 Elf64_Addr; +typedef __u16 Elf64_Half; +typedef __s16 Elf64_SHalf; +typedef __u64 Elf64_Off; +typedef __s32 Elf64_Sword; +typedef __u32 Elf64_Word; +typedef __u64 Elf64_Xword; +typedef __s64 Elf64_Sxword; +typedef __u16 Elf64_Versym; + +/* These constants are for the segment types stored in the image headers */ +#define PT_NULL 0 +#define PT_LOAD 1 +#define PT_DYNAMIC 2 +#define PT_INTERP 3 +#define PT_NOTE 4 +#define PT_SHLIB 5 +#define PT_PHDR 6 +#define PT_TLS 7 /* Thread local storage segment */ +#define PT_LOOS 0x60000000 /* OS-specific */ +#define PT_HIOS 0x6fffffff /* OS-specific */ +#define PT_LOPROC 0x70000000 +#define PT_HIPROC 0x7fffffff +#define PT_GNU_EH_FRAME (PT_LOOS + 0x474e550) +#define PT_GNU_STACK (PT_LOOS + 0x474e551) +#define PT_GNU_RELRO (PT_LOOS + 0x474e552) +#define PT_GNU_PROPERTY (PT_LOOS + 0x474e553) + + +/* ARM MTE memory tag segment type */ +#define PT_AARCH64_MEMTAG_MTE (PT_LOPROC + 0x2) + +/* + * Extended Numbering + * + * If the real number of program header table entries is larger than + * or equal to PN_XNUM(0xffff), it is set to sh_info field of the + * section header at index 0, and PN_XNUM is set to e_phnum + * field. Otherwise, the section header at index 0 is zero + * initialized, if it exists. + * + * Specifications are available in: + * + * - Oracle: Linker and Libraries. + * Part No: 817–1984–19, August 2011. + * https://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf + * + * - System V ABI AMD64 Architecture Processor Supplement + * Draft Version 0.99.4, + * January 13, 2010. + * http://www.cs.washington.edu/education/courses/cse351/12wi/supp-docs/abi.pdf + */ +#define PN_XNUM 0xffff + +/* These constants define the different elf file types */ +#define ET_NONE 0 +#define ET_REL 1 +#define ET_EXEC 2 +#define ET_DYN 3 +#define ET_CORE 4 +#define ET_LOPROC 0xff00 +#define ET_HIPROC 0xffff + +/* This is the info that is needed to parse the dynamic section of the file */ +#define DT_NULL 0 +#define DT_NEEDED 1 +#define DT_PLTRELSZ 2 +#define DT_PLTGOT 3 +#define DT_HASH 4 +#define DT_STRTAB 5 +#define DT_SYMTAB 6 +#define DT_RELA 7 +#define DT_RELASZ 8 +#define DT_RELAENT 9 +#define DT_STRSZ 10 +#define DT_SYMENT 11 +#define DT_INIT 12 +#define DT_FINI 13 +#define DT_SONAME 14 +#define DT_RPATH 15 +#define DT_SYMBOLIC 16 +#define DT_REL 17 +#define DT_RELSZ 18 +#define DT_RELENT 19 +#define DT_PLTREL 20 +#define DT_DEBUG 21 +#define DT_TEXTREL 22 +#define DT_JMPREL 23 +#define DT_ENCODING 32 +#define OLD_DT_LOOS 0x60000000 +#define DT_LOOS 0x6000000d +#define DT_HIOS 0x6ffff000 +#define DT_VALRNGLO 0x6ffffd00 +#define DT_VALRNGHI 0x6ffffdff +#define DT_ADDRRNGLO 0x6ffffe00 +#define DT_GNU_HASH 0x6ffffef5 +#define DT_ADDRRNGHI 0x6ffffeff +#define DT_VERSYM 0x6ffffff0 +#define DT_RELACOUNT 0x6ffffff9 +#define DT_RELCOUNT 0x6ffffffa +#define DT_FLAGS_1 0x6ffffffb +#define DT_VERDEF 0x6ffffffc +#define DT_VERDEFNUM 0x6ffffffd +#define DT_VERNEED 0x6ffffffe +#define DT_VERNEEDNUM 0x6fffffff +#define OLD_DT_HIOS 0x6fffffff +#define DT_LOPROC 0x70000000 +#define DT_HIPROC 0x7fffffff + +/* This info is needed when parsing the symbol table */ +#define STB_LOCAL 0 +#define STB_GLOBAL 1 +#define STB_WEAK 2 + +#define STN_UNDEF 0 + +#define STT_NOTYPE 0 +#define STT_OBJECT 1 +#define STT_FUNC 2 +#define STT_SECTION 3 +#define STT_FILE 4 +#define STT_COMMON 5 +#define STT_TLS 6 + +#define VER_FLG_BASE 0x1 +#define VER_FLG_WEAK 0x2 + +#define ELF_ST_BIND(x) ((x) >> 4) +#define ELF_ST_TYPE(x) ((x) & 0xf) +#define ELF32_ST_BIND(x) ELF_ST_BIND(x) +#define ELF32_ST_TYPE(x) ELF_ST_TYPE(x) +#define ELF64_ST_BIND(x) ELF_ST_BIND(x) +#define ELF64_ST_TYPE(x) ELF_ST_TYPE(x) + +typedef struct { + Elf32_Sword d_tag; + union { + Elf32_Sword d_val; + Elf32_Addr d_ptr; + } d_un; +} Elf32_Dyn; + +typedef struct { + Elf64_Sxword d_tag; /* entry tag value */ + union { + Elf64_Xword d_val; + Elf64_Addr d_ptr; + } d_un; +} Elf64_Dyn; + +/* The following are used with relocations */ +#define ELF32_R_SYM(x) ((x) >> 8) +#define ELF32_R_TYPE(x) ((x) & 0xff) + +#define ELF64_R_SYM(i) ((i) >> 32) +#define ELF64_R_TYPE(i) ((i) & 0xffffffff) + +typedef struct elf32_rel { + Elf32_Addr r_offset; + Elf32_Word r_info; +} Elf32_Rel; + +typedef struct elf64_rel { + Elf64_Addr r_offset; /* Location at which to apply the action */ + Elf64_Xword r_info; /* index and type of relocation */ +} Elf64_Rel; + +typedef struct elf32_rela { + Elf32_Addr r_offset; + Elf32_Word r_info; + Elf32_Sword r_addend; +} Elf32_Rela; + +typedef struct elf64_rela { + Elf64_Addr r_offset; /* Location at which to apply the action */ + Elf64_Xword r_info; /* index and type of relocation */ + Elf64_Sxword r_addend; /* Constant addend used to compute value */ +} Elf64_Rela; + +typedef struct elf32_sym { + Elf32_Word st_name; + Elf32_Addr st_value; + Elf32_Word st_size; + unsigned char st_info; + unsigned char st_other; + Elf32_Half st_shndx; +} Elf32_Sym; + +typedef struct elf64_sym { + Elf64_Word st_name; /* Symbol name, index in string tbl */ + unsigned char st_info; /* Type and binding attributes */ + unsigned char st_other; /* No defined meaning, 0 */ + Elf64_Half st_shndx; /* Associated section index */ + Elf64_Addr st_value; /* Value of the symbol */ + Elf64_Xword st_size; /* Associated symbol size */ +} Elf64_Sym; + + +#define EI_NIDENT 16 + +typedef struct elf32_hdr { + unsigned char e_ident[EI_NIDENT]; + Elf32_Half e_type; + Elf32_Half e_machine; + Elf32_Word e_version; + Elf32_Addr e_entry; /* Entry point */ + Elf32_Off e_phoff; + Elf32_Off e_shoff; + Elf32_Word e_flags; + Elf32_Half e_ehsize; + Elf32_Half e_phentsize; + Elf32_Half e_phnum; + Elf32_Half e_shentsize; + Elf32_Half e_shnum; + Elf32_Half e_shstrndx; +} Elf32_Ehdr; + +typedef struct elf64_hdr { + unsigned char e_ident[EI_NIDENT]; /* ELF "magic number" */ + Elf64_Half e_type; + Elf64_Half e_machine; + Elf64_Word e_version; + Elf64_Addr e_entry; /* Entry point virtual address */ + Elf64_Off e_phoff; /* Program header table file offset */ + Elf64_Off e_shoff; /* Section header table file offset */ + Elf64_Word e_flags; + Elf64_Half e_ehsize; + Elf64_Half e_phentsize; + Elf64_Half e_phnum; + Elf64_Half e_shentsize; + Elf64_Half e_shnum; + Elf64_Half e_shstrndx; +} Elf64_Ehdr; + +/* These constants define the permissions on sections in the program + header, p_flags. */ +#define PF_R 0x4 +#define PF_W 0x2 +#define PF_X 0x1 + +typedef struct elf32_phdr { + Elf32_Word p_type; + Elf32_Off p_offset; + Elf32_Addr p_vaddr; + Elf32_Addr p_paddr; + Elf32_Word p_filesz; + Elf32_Word p_memsz; + Elf32_Word p_flags; + Elf32_Word p_align; +} Elf32_Phdr; + +typedef struct elf64_phdr { + Elf64_Word p_type; + Elf64_Word p_flags; + Elf64_Off p_offset; /* Segment file offset */ + Elf64_Addr p_vaddr; /* Segment virtual address */ + Elf64_Addr p_paddr; /* Segment physical address */ + Elf64_Xword p_filesz; /* Segment size in file */ + Elf64_Xword p_memsz; /* Segment size in memory */ + Elf64_Xword p_align; /* Segment alignment, file & memory */ +} Elf64_Phdr; + +/* sh_type */ +#define SHT_NULL 0 +#define SHT_PROGBITS 1 +#define SHT_SYMTAB 2 +#define SHT_STRTAB 3 +#define SHT_RELA 4 +#define SHT_HASH 5 +#define SHT_DYNAMIC 6 +#define SHT_NOTE 7 +#define SHT_NOBITS 8 +#define SHT_REL 9 +#define SHT_SHLIB 10 +#define SHT_DYNSYM 11 +#define SHT_NUM 12 +#define SHT_LOPROC 0x70000000 +#define SHT_HIPROC 0x7fffffff +#define SHT_LOUSER 0x80000000 +#define SHT_HIUSER 0xffffffff + +/* sh_flags */ +#define SHF_WRITE 0x1 +#define SHF_ALLOC 0x2 +#define SHF_EXECINSTR 0x4 +#define SHF_RELA_LIVEPATCH 0x00100000 +#define SHF_RO_AFTER_INIT 0x00200000 +#define SHF_MASKPROC 0xf0000000 + +/* special section indexes */ +#define SHN_UNDEF 0 +#define SHN_LORESERVE 0xff00 +#define SHN_LOPROC 0xff00 +#define SHN_HIPROC 0xff1f +#define SHN_LIVEPATCH 0xff20 +#define SHN_ABS 0xfff1 +#define SHN_COMMON 0xfff2 +#define SHN_HIRESERVE 0xffff + +typedef struct elf32_shdr { + Elf32_Word sh_name; + Elf32_Word sh_type; + Elf32_Word sh_flags; + Elf32_Addr sh_addr; + Elf32_Off sh_offset; + Elf32_Word sh_size; + Elf32_Word sh_link; + Elf32_Word sh_info; + Elf32_Word sh_addralign; + Elf32_Word sh_entsize; +} Elf32_Shdr; + +typedef struct elf64_shdr { + Elf64_Word sh_name; /* Section name, index in string tbl */ + Elf64_Word sh_type; /* Type of section */ + Elf64_Xword sh_flags; /* Miscellaneous section attributes */ + Elf64_Addr sh_addr; /* Section virtual addr at execution */ + Elf64_Off sh_offset; /* Section file offset */ + Elf64_Xword sh_size; /* Size of section in bytes */ + Elf64_Word sh_link; /* Index of another section */ + Elf64_Word sh_info; /* Additional section information */ + Elf64_Xword sh_addralign; /* Section alignment */ + Elf64_Xword sh_entsize; /* Entry size if section holds table */ +} Elf64_Shdr; + +#define EI_MAG0 0 /* e_ident[] indexes */ +#define EI_MAG1 1 +#define EI_MAG2 2 +#define EI_MAG3 3 +#define EI_CLASS 4 +#define EI_DATA 5 +#define EI_VERSION 6 +#define EI_OSABI 7 +#define EI_PAD 8 + +#define ELFMAG0 0x7f /* EI_MAG */ +#define ELFMAG1 'E' +#define ELFMAG2 'L' +#define ELFMAG3 'F' +#define ELFMAG "\177ELF" +#define SELFMAG 4 + +#define ELFCLASSNONE 0 /* EI_CLASS */ +#define ELFCLASS32 1 +#define ELFCLASS64 2 +#define ELFCLASSNUM 3 + +#define ELFDATANONE 0 /* e_ident[EI_DATA] */ +#define ELFDATA2LSB 1 +#define ELFDATA2MSB 2 + +#define EV_NONE 0 /* e_version, EI_VERSION */ +#define EV_CURRENT 1 +#define EV_NUM 2 + +#define ELFOSABI_NONE 0 +#define ELFOSABI_LINUX 3 + +#ifndef ELF_OSABI +#define ELF_OSABI ELFOSABI_NONE +#endif + +/* + * Notes used in ET_CORE. Architectures export some of the arch register sets + * using the corresponding note types via the PTRACE_GETREGSET and + * PTRACE_SETREGSET requests. + * The note name for these types is "LINUX", except NT_PRFPREG that is named + * "CORE". + */ +#define NT_PRSTATUS 1 +#define NT_PRFPREG 2 +#define NT_PRPSINFO 3 +#define NT_TASKSTRUCT 4 +#define NT_AUXV 6 +/* + * Note to userspace developers: size of NT_SIGINFO note may increase + * in the future to accomodate more fields, don't assume it is fixed! + */ +#define NT_SIGINFO 0x53494749 +#define NT_FILE 0x46494c45 +#define NT_PRXFPREG 0x46e62b7f /* copied from gdb5.1/include/elf/common.h */ +#define NT_PPC_VMX 0x100 /* PowerPC Altivec/VMX registers */ +#define NT_PPC_SPE 0x101 /* PowerPC SPE/EVR registers */ +#define NT_PPC_VSX 0x102 /* PowerPC VSX registers */ +#define NT_PPC_TAR 0x103 /* Target Address Register */ +#define NT_PPC_PPR 0x104 /* Program Priority Register */ +#define NT_PPC_DSCR 0x105 /* Data Stream Control Register */ +#define NT_PPC_EBB 0x106 /* Event Based Branch Registers */ +#define NT_PPC_PMU 0x107 /* Performance Monitor Registers */ +#define NT_PPC_TM_CGPR 0x108 /* TM checkpointed GPR Registers */ +#define NT_PPC_TM_CFPR 0x109 /* TM checkpointed FPR Registers */ +#define NT_PPC_TM_CVMX 0x10a /* TM checkpointed VMX Registers */ +#define NT_PPC_TM_CVSX 0x10b /* TM checkpointed VSX Registers */ +#define NT_PPC_TM_SPR 0x10c /* TM Special Purpose Registers */ +#define NT_PPC_TM_CTAR 0x10d /* TM checkpointed Target Address Register */ +#define NT_PPC_TM_CPPR 0x10e /* TM checkpointed Program Priority Register */ +#define NT_PPC_TM_CDSCR 0x10f /* TM checkpointed Data Stream Control Register */ +#define NT_PPC_PKEY 0x110 /* Memory Protection Keys registers */ +#define NT_PPC_DEXCR 0x111 /* PowerPC DEXCR registers */ +#define NT_PPC_HASHKEYR 0x112 /* PowerPC HASHKEYR register */ +#define NT_386_TLS 0x200 /* i386 TLS slots (struct user_desc) */ +#define NT_386_IOPERM 0x201 /* x86 io permission bitmap (1=deny) */ +#define NT_X86_XSTATE 0x202 /* x86 extended state using xsave */ +/* Old binutils treats 0x203 as a CET state */ +#define NT_X86_SHSTK 0x204 /* x86 SHSTK state */ +#define NT_X86_XSAVE_LAYOUT 0x205 /* XSAVE layout description */ +#define NT_S390_HIGH_GPRS 0x300 /* s390 upper register halves */ +#define NT_S390_TIMER 0x301 /* s390 timer register */ +#define NT_S390_TODCMP 0x302 /* s390 TOD clock comparator register */ +#define NT_S390_TODPREG 0x303 /* s390 TOD programmable register */ +#define NT_S390_CTRS 0x304 /* s390 control registers */ +#define NT_S390_PREFIX 0x305 /* s390 prefix register */ +#define NT_S390_LAST_BREAK 0x306 /* s390 breaking event address */ +#define NT_S390_SYSTEM_CALL 0x307 /* s390 system call restart data */ +#define NT_S390_TDB 0x308 /* s390 transaction diagnostic block */ +#define NT_S390_VXRS_LOW 0x309 /* s390 vector registers 0-15 upper half */ +#define NT_S390_VXRS_HIGH 0x30a /* s390 vector registers 16-31 */ +#define NT_S390_GS_CB 0x30b /* s390 guarded storage registers */ +#define NT_S390_GS_BC 0x30c /* s390 guarded storage broadcast control block */ +#define NT_S390_RI_CB 0x30d /* s390 runtime instrumentation */ +#define NT_S390_PV_CPU_DATA 0x30e /* s390 protvirt cpu dump data */ +#define NT_ARM_VFP 0x400 /* ARM VFP/NEON registers */ +#define NT_ARM_TLS 0x401 /* ARM TLS register */ +#define NT_ARM_HW_BREAK 0x402 /* ARM hardware breakpoint registers */ +#define NT_ARM_HW_WATCH 0x403 /* ARM hardware watchpoint registers */ +#define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ +#define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */ +#define NT_ARM_PAC_MASK 0x406 /* ARM pointer authentication code masks */ +#define NT_ARM_PACA_KEYS 0x407 /* ARM pointer authentication address keys */ +#define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ +#define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ +#define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ +#define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ +#define NT_ARM_FPMR 0x40e /* ARM floating point mode register */ +#define NT_ARM_POE 0x40f /* ARM POE registers */ +#define NT_ARM_GCS 0x410 /* ARM GCS state */ +#define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ +#define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ +#define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ +#define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ +#define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +#define NT_RISCV_CSR 0x900 /* RISC-V Control and Status Registers */ +#define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ +#define NT_RISCV_TAGGED_ADDR_CTRL 0x902 /* RISC-V tagged address control (prctl()) */ +#define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ +#define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ +#define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ +#define NT_LOONGARCH_LASX 0xa03 /* LoongArch Loongson Advanced SIMD Extension registers */ +#define NT_LOONGARCH_LBT 0xa04 /* LoongArch Loongson Binary Translation registers */ +#define NT_LOONGARCH_HW_BREAK 0xa05 /* LoongArch hardware breakpoint registers */ +#define NT_LOONGARCH_HW_WATCH 0xa06 /* LoongArch hardware watchpoint registers */ + +/* Note types with note name "GNU" */ +#define NT_GNU_PROPERTY_TYPE_0 5 + +/* Note header in a PT_NOTE section */ +typedef struct elf32_note { + Elf32_Word n_namesz; /* Name size */ + Elf32_Word n_descsz; /* Content size */ + Elf32_Word n_type; /* Content type */ +} Elf32_Nhdr; + +/* Note header in a PT_NOTE section */ +typedef struct elf64_note { + Elf64_Word n_namesz; /* Name size */ + Elf64_Word n_descsz; /* Content size */ + Elf64_Word n_type; /* Content type */ +} Elf64_Nhdr; + +/* .note.gnu.property types for EM_AARCH64: */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000 + +/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0) + +typedef struct { + Elf32_Half vd_version; + Elf32_Half vd_flags; + Elf32_Half vd_ndx; + Elf32_Half vd_cnt; + Elf32_Word vd_hash; + Elf32_Word vd_aux; + Elf32_Word vd_next; +} Elf32_Verdef; + +typedef struct { + Elf64_Half vd_version; + Elf64_Half vd_flags; + Elf64_Half vd_ndx; + Elf64_Half vd_cnt; + Elf64_Word vd_hash; + Elf64_Word vd_aux; + Elf64_Word vd_next; +} Elf64_Verdef; + +typedef struct { + Elf32_Word vda_name; + Elf32_Word vda_next; +} Elf32_Verdaux; + +typedef struct { + Elf64_Word vda_name; + Elf64_Word vda_next; +} Elf64_Verdaux; + +#endif /* _LINUX_ELF_H */ diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index d6edcfcb5be8..530390033929 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -228,4 +228,7 @@ $(OUTPUT)/%:%.S $(LINK.S) $^ $(LDLIBS) -o $@ endif -.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir +headers: + $(Q)$(MAKE) -C $(top_srcdir) headers + +.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir headers diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 1cf14a8da438..12a0614b9fd4 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -19,13 +19,20 @@ LDLIBS += -lgcc_s endif include ../lib.mk + +CFLAGS += $(TOOLS_INCLUDES) + +CFLAGS_NOLIBC := -nostdlib -nostdinc -ffreestanding -fno-asynchronous-unwind-tables \ + -fno-stack-protector -include $(top_srcdir)/tools/include/nolibc/nolibc.h \ + -I$(top_srcdir)/tools/include/nolibc/ $(KHDR_INCLUDES) + $(OUTPUT)/vdso_test_gettimeofday: parse_vdso.c vdso_test_gettimeofday.c $(OUTPUT)/vdso_test_getcpu: parse_vdso.c vdso_test_getcpu.c $(OUTPUT)/vdso_test_abi: parse_vdso.c vdso_test_abi.c $(OUTPUT)/vdso_test_clock_getres: vdso_test_clock_getres.c -$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c -$(OUTPUT)/vdso_standalone_test_x86: CFLAGS +=-nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector +$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c | headers +$(OUTPUT)/vdso_standalone_test_x86: CFLAGS:=$(CFLAGS_NOLIBC) $(CFLAGS) $(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c $(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index f89d052c730e..3ff00fb624a4 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -19,13 +19,14 @@ #include <stdint.h> #include <string.h> #include <limits.h> -#include <elf.h> +#include <linux/auxvec.h> +#include <linux/elf.h> #include "parse_vdso.h" /* And here's the code. */ #ifndef ELF_BITS -# if ULONG_MAX > 0xffffffffUL +# if __SIZEOF_LONG__ >= 8 # define ELF_BITS 64 # else # define ELF_BITS 32 @@ -297,17 +298,3 @@ void *vdso_sym(const char *version, const char *name) return 0; } - -void vdso_init_from_auxv(void *auxv) -{ - ELF(auxv_t) *elf_auxv = auxv; - for (int i = 0; elf_auxv[i].a_type != AT_NULL; i++) - { - if (elf_auxv[i].a_type == AT_SYSINFO_EHDR) { - vdso_init_from_sysinfo_ehdr(elf_auxv[i].a_un.a_val); - return; - } - } - - vdso_info.valid = false; -} diff --git a/tools/testing/selftests/vDSO/parse_vdso.h b/tools/testing/selftests/vDSO/parse_vdso.h index de0453067d7c..09d068ed11f9 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.h +++ b/tools/testing/selftests/vDSO/parse_vdso.h @@ -26,6 +26,5 @@ */ void *vdso_sym(const char *version, const char *name); void vdso_init_from_sysinfo_ehdr(uintptr_t base); -void vdso_init_from_auxv(void *auxv); #endif diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c index 644915862af8..9ce795b806f0 100644 --- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c +++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c @@ -1,142 +1,58 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * vdso_test.c: Sample code to test parse_vdso.c on x86 - * Copyright (c) 2011-2014 Andy Lutomirski + * vdso_test_gettimeofday.c: Sample code to test parse_vdso.c and + * vDSO gettimeofday() + * Copyright (c) 2014 Andy Lutomirski * - * You can amuse yourself by compiling with: - * gcc -std=gnu99 -nostdlib - * -Os -fno-asynchronous-unwind-tables -flto -lgcc_s - * vdso_standalone_test_x86.c parse_vdso.c - * to generate a small binary. On x86_64, you can omit -lgcc_s - * if you want the binary to be completely standalone. + * Compile with: + * gcc -std=gnu99 vdso_test_gettimeofday.c parse_vdso_gettimeofday.c + * + * Tested on x86, 32-bit and 64-bit. It may work on other architectures, too. */ -#include <sys/syscall.h> +#include <stdio.h> +#ifndef NOLIBC +#include <sys/auxv.h> #include <sys/time.h> -#include <unistd.h> -#include <stdint.h> - -#include "parse_vdso.h" - -/* We need some libc functions... */ -int strcmp(const char *a, const char *b) -{ - /* This implementation is buggy: it never returns -1. */ - while (*a || *b) { - if (*a != *b) - return 1; - if (*a == 0 || *b == 0) - return 1; - a++; - b++; - } - - return 0; -} - -/* - * The clang build needs this, although gcc does not. - * Stolen from lib/string.c. - */ -void *memcpy(void *dest, const void *src, size_t count) -{ - char *tmp = dest; - const char *s = src; - - while (count--) - *tmp++ = *s++; - return dest; -} - -/* ...and two syscalls. This is x86-specific. */ -static inline long x86_syscall3(long nr, long a0, long a1, long a2) -{ - long ret; -#ifdef __x86_64__ - asm volatile ("syscall" : "=a" (ret) : "a" (nr), - "D" (a0), "S" (a1), "d" (a2) : - "cc", "memory", "rcx", - "r8", "r9", "r10", "r11" ); -#else - asm volatile ("int $0x80" : "=a" (ret) : "a" (nr), - "b" (a0), "c" (a1), "d" (a2) : - "cc", "memory" ); #endif - return ret; -} -static inline long linux_write(int fd, const void *data, size_t len) -{ - return x86_syscall3(__NR_write, fd, (long)data, (long)len); -} +#include "../kselftest.h" +#include "parse_vdso.h" +#include "vdso_config.h" +#include "vdso_call.h" -static inline void linux_exit(int code) +int main(int argc, char **argv) { - x86_syscall3(__NR_exit, code, 0, 0); -} + const char *version = versions[VDSO_VERSION]; + const char **name = (const char **)&names[VDSO_NAMES]; -void to_base10(char *lastdig, time_t n) -{ - while (n) { - *lastdig = (n % 10) + '0'; - n /= 10; - lastdig--; + unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); + if (!sysinfo_ehdr) { + printf("AT_SYSINFO_EHDR is not present!\n"); + return KSFT_SKIP; } -} - -void c_main(void **stack) -{ - /* Parse the stack */ - long argc = (long)*stack; - stack += argc + 2; - - /* Now we're pointing at the environment. Skip it. */ - while(*stack) - stack++; - stack++; - /* Now we're pointing at auxv. Initialize the vDSO parser. */ - vdso_init_from_auxv((void *)stack); + vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR)); /* Find gettimeofday. */ typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz); - gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday"); + gtod_t gtod = (gtod_t)vdso_sym(version, name[0]); - if (!gtod) - linux_exit(1); + if (!gtod) { + printf("Could not find %s\n", name[0]); + return KSFT_SKIP; + } struct timeval tv; - long ret = gtod(&tv, 0); + long ret = VDSO_CALL(gtod, 2, &tv, 0); if (ret == 0) { - char buf[] = "The time is .000000\n"; - to_base10(buf + 31, tv.tv_sec); - to_base10(buf + 38, tv.tv_usec); - linux_write(1, buf, sizeof(buf) - 1); + printf("The time is %lld.%06lld\n", + (long long)tv.tv_sec, (long long)tv.tv_usec); } else { - linux_exit(ret); + printf("%s failed\n", name[0]); + return KSFT_FAIL; } - linux_exit(0); + return 0; } - -/* - * This is the real entry point. It passes the initial stack into - * the C entry point. - */ -asm ( - ".text\n" - ".global _start\n" - ".type _start,@function\n" - "_start:\n\t" -#ifdef __x86_64__ - "mov %rsp,%rdi\n\t" - "and $-16,%rsp\n\t" - "sub $8,%rsp\n\t" - "jmp c_main" -#else - "push %esp\n\t" - "call c_main\n\t" - "int $3" -#endif - ); diff --git a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c index e31b18ffae33..9ce795b806f0 100644 --- a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c +++ b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c @@ -10,11 +10,11 @@ * Tested on x86, 32-bit and 64-bit. It may work on other architectures, too. */ -#include <stdint.h> -#include <elf.h> #include <stdio.h> +#ifndef NOLIBC #include <sys/auxv.h> #include <sys/time.h> +#endif #include "../kselftest.h" #include "parse_vdso.h" |