diff options
author | Palmer Dabbelt | 2022-05-19 09:51:59 -0700 |
---|---|---|
committer | Palmer Dabbelt | 2022-05-19 09:51:59 -0700 |
commit | 7eb6369d7acfe87df73848b3757c648e8f352b86 (patch) | |
tree | 393d357d93b5f4ff37fc633b270e0fded795f721 /arch/riscv | |
parent | 93c0651617a62a69717299f1464dda798af8bebb (diff) | |
parent | 9be8459298eadb39b9fe9974b890239e9c123107 (diff) |
RISC-V: Add support for rv32 userspace via COMPAT
The RISC-V port supports the rv32i and rv64i base ISAs, but provides no
mechanism to run 32-bit userspace on 64-bit systems. This adds that
support, via the COMPAT framework. As the RISC-V ISAs (and uABIs) were
developed concurrently, the resulting compat support is mostly generic.
This includes a handful of cleanups to the generic compat infrastructure
to more cleanly support RISC-V, followed by the RISC-V implementation.
* palmer/riscv-compat:
riscv: compat: Add COMPAT Kbuild skeletal support
riscv: compat: ptrace: Add compat_arch_ptrace implement
riscv: compat: signal: Add rt_frame implementation
riscv: compat: vdso: Add setup additional pages implementation
riscv: compat: vdso: Add COMPAT_VDSO base code implementation
riscv: compat: Add hw capability check for elf
riscv: compat: Add elf.h implementation
riscv: compat: process: Add UXL_32 support in start_thread
riscv: compat: syscall: Add entry.S implementation
riscv: compat: syscall: Add compat_sys_call_table implementation
riscv: compat: Support TASK_SIZE for compat mode
riscv: compat: Add basic compat data type implementation
riscv: Fixup difference with defconfig
syscalls: compat: Fix the missing part for __SYSCALL_COMPAT
asm-generic: compat: Cleanup duplicate definitions
fs: stat: compat: Add __ARCH_WANT_COMPAT_STAT
arch: Add SYSVIPC_COMPAT for all architectures
compat: consolidate the compat_flock{,64} definition
uapi: always define F_GETLK64/F_SETLK64/F_SETLKW64 in fcntl.h
uapi: simplify __ARCH_FLOCK{,64}_PAD a little
Diffstat (limited to 'arch/riscv')
33 files changed, 863 insertions, 52 deletions
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d08584681216..cad2d42a77d9 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -76,6 +76,7 @@ config RISCV select HAVE_ARCH_KGDB if !XIP_KERNEL select HAVE_ARCH_KGDB_QXFER_PKT select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU @@ -127,12 +128,18 @@ config ARCH_MMAP_RND_BITS_MIN default 18 if 64BIT default 8 +config ARCH_MMAP_RND_COMPAT_BITS_MIN + default 8 + # max bits determined by the following formula: # VA_BITS - PAGE_SHIFT - 3 config ARCH_MMAP_RND_BITS_MAX default 24 if 64BIT # SV39 based default 17 +config ARCH_MMAP_RND_COMPAT_BITS_MAX + default 17 + # set if we run in machine mode, cleared if we run in supervisor mode config RISCV_M_MODE bool @@ -422,6 +429,18 @@ config CRASH_DUMP For more details see Documentation/admin-guide/kdump/kdump.rst +config COMPAT + bool "Kernel support for 32-bit U-mode" + default 64BIT + depends on 64BIT && MMU + help + This option enables support for a 32-bit U-mode running under a 64-bit + kernel at S-mode. riscv32-specific components such as system calls, + the user helper functions (vdso), signal rt_frame functions and the + ptrace interface are handled appropriately by the kernel. + + If you want to execute 32-bit userspace applications, say Y. + endmenu menu "Boot options" diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index a7ed47ce9311..c4228c5d155e 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -112,12 +112,17 @@ libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@ + $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ + $(build)=arch/riscv/kernel/compat_vdso $@) ifeq ($(KBUILD_EXTMOD),) ifeq ($(CONFIG_MMU),y) prepare: vdso_prepare vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso include/generated/vdso-offsets.h + $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ + $(build)=arch/riscv/kernel/compat_vdso include/generated/compat_vdso-offsets.h) + endif endif @@ -154,3 +159,7 @@ PHONY += rv64_randconfig rv64_randconfig: $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/64-bit.config \ -f $(srctree)/Makefile randconfig + +PHONY += rv32_defconfig +rv32_defconfig: + $(Q)$(MAKE) -f $(srctree)/Makefile defconfig 32-bit.config diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h new file mode 100644 index 000000000000..2ac955b51148 --- /dev/null +++ b/arch/riscv/include/asm/compat.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_COMPAT_H +#define __ASM_COMPAT_H + +#define COMPAT_UTS_MACHINE "riscv\0\0" + +/* + * Architecture specific compatibility types + */ +#include <linux/types.h> +#include <linux/sched.h> +#include <linux/sched/task_stack.h> +#include <asm-generic/compat.h> + +static inline int is_compat_task(void) +{ + return test_thread_flag(TIF_32BIT); +} + +struct compat_user_regs_struct { + compat_ulong_t pc; + compat_ulong_t ra; + compat_ulong_t sp; + compat_ulong_t gp; + compat_ulong_t tp; + compat_ulong_t t0; + compat_ulong_t t1; + compat_ulong_t t2; + compat_ulong_t s0; + compat_ulong_t s1; + compat_ulong_t a0; + compat_ulong_t a1; + compat_ulong_t a2; + compat_ulong_t a3; + compat_ulong_t a4; + compat_ulong_t a5; + compat_ulong_t a6; + compat_ulong_t a7; + compat_ulong_t s2; + compat_ulong_t s3; + compat_ulong_t s4; + compat_ulong_t s5; + compat_ulong_t s6; + compat_ulong_t s7; + compat_ulong_t s8; + compat_ulong_t s9; + compat_ulong_t s10; + compat_ulong_t s11; + compat_ulong_t t3; + compat_ulong_t t4; + compat_ulong_t t5; + compat_ulong_t t6; +}; + +static inline void regs_to_cregs(struct compat_user_regs_struct *cregs, + struct pt_regs *regs) +{ + cregs->pc = (compat_ulong_t) regs->epc; + cregs->ra = (compat_ulong_t) regs->ra; + cregs->sp = (compat_ulong_t) regs->sp; + cregs->gp = (compat_ulong_t) regs->gp; + cregs->tp = (compat_ulong_t) regs->tp; + cregs->t0 = (compat_ulong_t) regs->t0; + cregs->t1 = (compat_ulong_t) regs->t1; + cregs->t2 = (compat_ulong_t) regs->t2; + cregs->s0 = (compat_ulong_t) regs->s0; + cregs->s1 = (compat_ulong_t) regs->s1; + cregs->a0 = (compat_ulong_t) regs->a0; + cregs->a1 = (compat_ulong_t) regs->a1; + cregs->a2 = (compat_ulong_t) regs->a2; + cregs->a3 = (compat_ulong_t) regs->a3; + cregs->a4 = (compat_ulong_t) regs->a4; + cregs->a5 = (compat_ulong_t) regs->a5; + cregs->a6 = (compat_ulong_t) regs->a6; + cregs->a7 = (compat_ulong_t) regs->a7; + cregs->s2 = (compat_ulong_t) regs->s2; + cregs->s3 = (compat_ulong_t) regs->s3; + cregs->s4 = (compat_ulong_t) regs->s4; + cregs->s5 = (compat_ulong_t) regs->s5; + cregs->s6 = (compat_ulong_t) regs->s6; + cregs->s7 = (compat_ulong_t) regs->s7; + cregs->s8 = (compat_ulong_t) regs->s8; + cregs->s9 = (compat_ulong_t) regs->s9; + cregs->s10 = (compat_ulong_t) regs->s10; + cregs->s11 = (compat_ulong_t) regs->s11; + cregs->t3 = (compat_ulong_t) regs->t3; + cregs->t4 = (compat_ulong_t) regs->t4; + cregs->t5 = (compat_ulong_t) regs->t5; + cregs->t6 = (compat_ulong_t) regs->t6; +}; + +static inline void cregs_to_regs(struct compat_user_regs_struct *cregs, + struct pt_regs *regs) +{ + regs->epc = (unsigned long) cregs->pc; + regs->ra = (unsigned long) cregs->ra; + regs->sp = (unsigned long) cregs->sp; + regs->gp = (unsigned long) cregs->gp; + regs->tp = (unsigned long) cregs->tp; + regs->t0 = (unsigned long) cregs->t0; + regs->t1 = (unsigned long) cregs->t1; + regs->t2 = (unsigned long) cregs->t2; + regs->s0 = (unsigned long) cregs->s0; + regs->s1 = (unsigned long) cregs->s1; + regs->a0 = (unsigned long) cregs->a0; + regs->a1 = (unsigned long) cregs->a1; + regs->a2 = (unsigned long) cregs->a2; + regs->a3 = (unsigned long) cregs->a3; + regs->a4 = (unsigned long) cregs->a4; + regs->a5 = (unsigned long) cregs->a5; + regs->a6 = (unsigned long) cregs->a6; + regs->a7 = (unsigned long) cregs->a7; + regs->s2 = (unsigned long) cregs->s2; + regs->s3 = (unsigned long) cregs->s3; + regs->s4 = (unsigned long) cregs->s4; + regs->s5 = (unsigned long) cregs->s5; + regs->s6 = (unsigned long) cregs->s6; + regs->s7 = (unsigned long) cregs->s7; + regs->s8 = (unsigned long) cregs->s8; + regs->s9 = (unsigned long) cregs->s9; + regs->s10 = (unsigned long) cregs->s10; + regs->s11 = (unsigned long) cregs->s11; + regs->t3 = (unsigned long) cregs->t3; + regs->t4 = (unsigned long) cregs->t4; + regs->t5 = (unsigned long) cregs->t5; + regs->t6 = (unsigned long) cregs->t6; +}; + +#endif /* __ASM_COMPAT_H */ diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index e935f27b10fd..f5d1251fd6c7 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -36,6 +36,13 @@ #define SR_SD _AC(0x8000000000000000, UL) /* FS/XS dirty */ #endif +#ifdef CONFIG_64BIT +#define SR_UXL _AC(0x300000000, UL) /* XLEN mask for U-mode */ +#define SR_UXL_32 _AC(0x100000000, UL) /* XLEN = 32 for U-mode */ +#define SR_UXL_64 _AC(0x200000000, UL) /* XLEN = 64 for U-mode */ +#define SR_UXL_SHIFT 32 +#endif + /* SATP flags */ #ifndef CONFIG_64BIT #define SATP_PPN _AC(0x003FFFFF, UL) diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index f53c40026c7a..14fc7342490b 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -8,6 +8,8 @@ #ifndef _ASM_RISCV_ELF_H #define _ASM_RISCV_ELF_H +#include <uapi/linux/elf.h> +#include <linux/compat.h> #include <uapi/asm/elf.h> #include <asm/auxvec.h> #include <asm/byteorder.h> @@ -18,18 +20,24 @@ */ #define ELF_ARCH EM_RISCV +#ifndef ELF_CLASS #ifdef CONFIG_64BIT #define ELF_CLASS ELFCLASS64 #else #define ELF_CLASS ELFCLASS32 #endif +#endif #define ELF_DATA ELFDATA2LSB /* * This is used to ensure we don't load something for the wrong architecture. */ -#define elf_check_arch(x) ((x)->e_machine == EM_RISCV) +#define elf_check_arch(x) (((x)->e_machine == EM_RISCV) && \ + ((x)->e_ident[EI_CLASS] == ELF_CLASS)) + +extern bool compat_elf_check_arch(Elf32_Ehdr *hdr); +#define compat_elf_check_arch compat_elf_check_arch #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE (PAGE_SIZE) @@ -43,8 +51,14 @@ #define ELF_ET_DYN_BASE ((TASK_SIZE / 3) * 2) #ifdef CONFIG_64BIT +#ifdef CONFIG_COMPAT +#define STACK_RND_MASK (test_thread_flag(TIF_32BIT) ? \ + 0x7ff >> (PAGE_SHIFT - 12) : \ + 0x3ffff >> (PAGE_SHIFT - 12)) +#else #define STACK_RND_MASK (0x3ffff >> (PAGE_SHIFT - 12)) #endif +#endif /* * This yields a mask that user programs can use to figure out what * instruction set this CPU supports. This could be done in user space, @@ -60,11 +74,19 @@ extern unsigned long elf_hwcap; */ #define ELF_PLATFORM (NULL) +#define COMPAT_ELF_PLATFORM (NULL) + #ifdef CONFIG_MMU #define ARCH_DLINFO \ do { \ + /* \ + * Note that we add ulong after elf_addr_t because \ + * casting current->mm->context.vdso triggers a cast \ + * warning of cast from pointer to integer for \ + * COMPAT ELFCLASS32. \ + */ \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ - (elf_addr_t)current->mm->context.vdso); \ + (elf_addr_t)(ulong)current->mm->context.vdso); \ NEW_AUX_ENT(AT_L1I_CACHESIZE, \ get_cache_size(1, CACHE_TYPE_INST)); \ NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, \ @@ -90,4 +112,28 @@ do { \ *(struct user_regs_struct *)regs; \ } while (0); +#ifdef CONFIG_COMPAT + +#define SET_PERSONALITY(ex) \ +do { if ((ex).e_ident[EI_CLASS] == ELFCLASS32) \ + set_thread_flag(TIF_32BIT); \ + else \ + clear_thread_flag(TIF_32BIT); \ + if (personality(current->personality) != PER_LINUX32) \ + set_personality(PER_LINUX | \ + (current->personality & (~PER_MASK))); \ +} while (0) + +#define COMPAT_ELF_ET_DYN_BASE ((TASK_SIZE_32 / 3) * 2) + +/* rv32 registers */ +typedef compat_ulong_t compat_elf_greg_t; +typedef compat_elf_greg_t compat_elf_gregset_t[ELF_NGREG]; + +extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); +#define compat_arch_setup_additional_pages \ + compat_arch_setup_additional_pages + +#endif /* CONFIG_COMPAT */ #endif /* _ASM_RISCV_ELF_H */ diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index 0099dc116168..cedcf8ea3c76 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -16,6 +16,7 @@ typedef struct { atomic_long_t id; #endif void *vdso; + void *vdso_info; #ifdef CONFIG_SMP /* A local icache flush is needed before user execution can resume. */ cpumask_t icache_stale_mask; diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 6f0a260d3f2c..eefaab1d3535 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -740,8 +740,17 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, * 63–48 all equal to bit 47, or else a page-fault exception will occur." */ #ifdef CONFIG_64BIT -#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2) -#define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2) +#define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) +#define TASK_SIZE_MIN (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2) + +#ifdef CONFIG_COMPAT +#define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) +#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ + TASK_SIZE_32 : TASK_SIZE_64) +#else +#define TASK_SIZE TASK_SIZE_64 +#endif + #else #define TASK_SIZE FIXADDR_START #define TASK_SIZE_MIN TASK_SIZE diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 0749924d9e55..21c8072dce17 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -19,7 +19,11 @@ #define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3) #define STACK_TOP TASK_SIZE -#define STACK_TOP_MAX STACK_TOP +#ifdef CONFIG_64BIT +#define STACK_TOP_MAX TASK_SIZE_64 +#else +#define STACK_TOP_MAX TASK_SIZE +#endif #define STACK_ALIGN 16 #ifndef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/signal32.h b/arch/riscv/include/asm/signal32.h new file mode 100644 index 000000000000..96dc56932e76 --- /dev/null +++ b/arch/riscv/include/asm/signal32.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_SIGNAL32_H +#define __ASM_SIGNAL32_H + +#if IS_ENABLED(CONFIG_COMPAT) +int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs); +#else +static inline +int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) +{ + return -1; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 7ac6a0e275f2..384a63b86420 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -16,6 +16,7 @@ /* The array of function pointers for syscalls. */ extern void * const sys_call_table[]; +extern void * const compat_sys_call_table[]; /* * Only the low 32 bits of orig_r0 are meaningful, so we return int. diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 74d888c8d631..78933ac04995 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -97,6 +97,7 @@ struct thread_info { #define TIF_SECCOMP 8 /* syscall secure computing */ #define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */ #define TIF_UPROBE 10 /* uprobe breakpoint or singlestep */ +#define TIF_32BIT 11 /* compat-mode 32bit process */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h index 6c316093a1e5..5ddac412b578 100644 --- a/arch/riscv/include/asm/unistd.h +++ b/arch/riscv/include/asm/unistd.h @@ -11,6 +11,17 @@ #define __ARCH_WANT_SYS_CLONE #define __ARCH_WANT_MEMFD_SECRET +#ifdef CONFIG_COMPAT +#define __ARCH_WANT_COMPAT_TRUNCATE64 +#define __ARCH_WANT_COMPAT_FTRUNCATE64 +#define __ARCH_WANT_COMPAT_FALLOCATE +#define __ARCH_WANT_COMPAT_PREAD64 +#define __ARCH_WANT_COMPAT_PWRITE64 +#define __ARCH_WANT_COMPAT_SYNC_FILE_RANGE +#define __ARCH_WANT_COMPAT_READAHEAD +#define __ARCH_WANT_COMPAT_FADVISE64_64 +#endif + #include <uapi/asm/unistd.h> #define NR_syscalls (__NR_syscalls) diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index bc6f75f3a199..af981426fe0f 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -21,6 +21,15 @@ #define VDSO_SYMBOL(base, name) \ (void __user *)((unsigned long)(base) + __vdso_##name##_offset) + +#ifdef CONFIG_COMPAT +#include <generated/compat_vdso-offsets.h> + +#define COMPAT_VDSO_SYMBOL(base, name) \ + (void __user *)((unsigned long)(base) + compat__vdso_##name##_offset) + +#endif /* CONFIG_COMPAT */ + #endif /* !__ASSEMBLY__ */ #endif /* CONFIG_MMU */ diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h index 8062996c2dfd..c9e50eed14aa 100644 --- a/arch/riscv/include/uapi/asm/unistd.h +++ b/arch/riscv/include/uapi/asm/unistd.h @@ -15,7 +15,7 @@ * along with this program. If not, see <https://www.gnu.org/licenses/>. */ -#ifdef __LP64__ +#if defined(__LP64__) && !defined(__SYSCALL_COMPAT) #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT #endif /* __LP64__ */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index bf3876a77ed7..19e0518d6721 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -84,3 +84,6 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_EFI) += efi.o +obj-$(CONFIG_COMPAT) += compat_syscall_table.o +obj-$(CONFIG_COMPAT) += compat_signal.o +obj-$(CONFIG_COMPAT) += compat_vdso/ diff --git a/arch/riscv/kernel/compat_signal.c b/arch/riscv/kernel/compat_signal.c new file mode 100644 index 000000000000..6ec4e34255a9 --- /dev/null +++ b/arch/riscv/kernel/compat_signal.c @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/compat.h> +#include <linux/signal.h> +#include <linux/uaccess.h> +#include <linux/syscalls.h> +#include <linux/linkage.h> + +#include <asm/csr.h> +#include <asm/signal32.h> +#include <asm/switch_to.h> +#include <asm/ucontext.h> +#include <asm/vdso.h> + +#define COMPAT_DEBUG_SIG 0 + +struct compat_sigcontext { + struct compat_user_regs_struct sc_regs; + union __riscv_fp_state sc_fpregs; +}; + +struct compat_ucontext { + compat_ulong_t uc_flags; + struct compat_ucontext *uc_link; + compat_stack_t uc_stack; + sigset_t uc_sigmask; + /* There's some padding here to allow sigset_t to be expanded in the + * future. Though this is unlikely, other architectures put uc_sigmask + * at the end of this structure and explicitly state it can be + * expanded, so we didn't want to box ourselves in here. */ + __u8 __unused[1024 / 8 - sizeof(sigset_t)]; + /* We can't put uc_sigmask at the end of this structure because we need + * to be able to expand sigcontext in the future. For example, the + * vector ISA extension will almost certainly add ISA state. We want + * to ensure all user-visible ISA state can be saved and restored via a + * ucontext, so we're putting this at the end in order to allow for + * infinite extensibility. Since we know this will be extended and we + * assume sigset_t won't be extended an extreme amount, we're + * prioritizing this. */ + struct compat_sigcontext uc_mcontext; +}; + +struct compat_rt_sigframe { + struct compat_siginfo info; + struct compat_ucontext uc; +}; + +#ifdef CONFIG_FPU +static long compat_restore_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + size_t i; + + err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state)); + if (unlikely(err)) + return err; + + fstate_restore(current, regs); + + /* We support no other extension state at this time. */ + for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { + u32 value; + + err = __get_user(value, &sc_fpregs->q.reserved[i]); + if (unlikely(err)) + break; + if (value != 0) + return -EINVAL; + } + + return err; +} + +static long compat_save_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + size_t i; + + fstate_save(current, regs); + err = __copy_to_user(state, ¤t->thread.fstate, sizeof(*state)); + if (unlikely(err)) + return err; + + /* We support no other extension state at this time. */ + for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { + err = __put_user(0, &sc_fpregs->q.reserved[i]); + if (unlikely(err)) + break; + } + + return err; +} +#else +#define compat_save_fp_state(task, regs) (0) +#define compat_restore_fp_state(task, regs) (0) +#endif + +static long compat_restore_sigcontext(struct pt_regs *regs, + struct compat_sigcontext __user *sc) +{ + long err; + struct compat_user_regs_struct cregs; + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_from_user(&cregs, &sc->sc_regs, sizeof(sc->sc_regs)); + + cregs_to_regs(&cregs, regs); + + /* Restore the floating-point state. */ + if (has_fpu()) + err |= compat_restore_fp_state(regs, &sc->sc_fpregs); + return err; +} + +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct compat_rt_sigframe __user *frame; + struct task_struct *task; + sigset_t set; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + frame = (struct compat_rt_sigframe __user *)regs->sp; + + if (!access_ok(frame, sizeof(*frame))) + goto badframe; + + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + set_current_blocked(&set); + + if (compat_restore_sigcontext(regs, &frame->uc.uc_mcontext)) + goto badframe; + + if (compat_restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + return regs->a0; + +badframe: + task = current; + if (show_unhandled_signals) { + pr_info_ratelimited( + "%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n", + task->comm, task_pid_nr(task), __func__, + frame, (void *)regs->epc, (void *)regs->sp); + } + force_sig(SIGSEGV); + return 0; +} + +static long compat_setup_sigcontext(struct compat_rt_sigframe __user *frame, + struct pt_regs *regs) +{ + struct compat_sigcontext __user *sc = &frame->uc.uc_mcontext; + struct compat_user_regs_struct cregs; + long err; + + regs_to_cregs(&cregs, regs); + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_to_user(&sc->sc_regs, &cregs, sizeof(sc->sc_regs)); + /* Save the floating-point state. */ + if (has_fpu()) + err |= compat_save_fp_state(regs, &sc->sc_fpregs); + return err; +} + +static inline void __user *compat_get_sigframe(struct ksignal *ksig, + struct pt_regs *regs, size_t framesize) +{ + unsigned long sp; + /* Default to using normal stack */ + sp = regs->sp; + + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) + return (void __user __force *)(-1UL); + + /* This is the X/Open sanctioned signal stack switching. */ + sp = sigsp(sp, ksig) - framesize; + + /* Align the stack frame. */ + sp &= ~0xfUL; + + return (void __user *)sp; +} + +int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) +{ + struct compat_rt_sigframe __user *frame; + long err = 0; + + frame = compat_get_sigframe(ksig, regs, sizeof(*frame)); + if (!access_ok(frame, sizeof(*frame))) + return -EFAULT; + + err |= copy_siginfo_to_user32(&frame->info, &ksig->info); + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(NULL, &frame->uc.uc_link); + err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + err |= compat_setup_sigcontext(frame, regs); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + return -EFAULT; + + regs->ra = (unsigned long)COMPAT_VDSO_SYMBOL( + current->mm->context.vdso, rt_sigreturn); + + /* + * Set up registers for signal handler. + * Registers that we don't modify keep the value they had from + * user-space at the time we took the signal. + * We always pass siginfo and mcontext, regardless of SA_SIGINFO, + * since some things rely on this (e.g. glibc's debug/segfault.c). + */ + regs->epc = (unsigned long)ksig->ka.sa.sa_handler; + regs->sp = (unsigned long)frame; + regs->a0 = ksig->sig; /* a0: signal number */ + regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */ + regs->a2 = (unsigned long)(&frame->uc); /* a2: ucontext pointer */ + +#if COMPAT_DEBUG_SIG + pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n", + current->comm, task_pid_nr(current), ksig->sig, + (void *)regs->epc, (void *)regs->ra, frame); +#endif + + return 0; +} diff --git a/arch/riscv/kernel/compat_syscall_table.c b/arch/riscv/kernel/compat_syscall_table.c new file mode 100644 index 000000000000..651f2b009c28 --- /dev/null +++ b/arch/riscv/kernel/compat_syscall_table.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define __SYSCALL_COMPAT + +#include <linux/compat.h> +#include <linux/syscalls.h> +#include <asm-generic/mman-common.h> +#include <asm-generic/syscalls.h> +#include <asm/syscall.h> + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = (call), + +asmlinkage long compat_sys_rt_sigreturn(void); + +void * const compat_sys_call_table[__NR_syscalls] = { + [0 ... __NR_syscalls - 1] = sys_ni_syscall, +#include <asm/unistd.h> +}; diff --git a/arch/riscv/kernel/compat_vdso/.gitignore b/arch/riscv/kernel/compat_vdso/.gitignore new file mode 100644 index 000000000000..19d83d846c1e --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +compat_vdso.lds diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile new file mode 100644 index 000000000000..260daf3236d3 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -0,0 +1,78 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for compat_vdso +# + +# Symbols present in the compat_vdso +compat_vdso-syms = rt_sigreturn +compat_vdso-syms += getcpu +compat_vdso-syms += flush_icache + +COMPAT_CC := $(CC) +COMPAT_LD := $(LD) + +COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +COMPAT_LD_FLAGS := -melf32lriscv + +# Files to link into the compat_vdso +obj-compat_vdso = $(patsubst %, %.o, $(compat_vdso-syms)) note.o + +# Build rules +targets := $(obj-compat_vdso) compat_vdso.so compat_vdso.so.dbg compat_vdso.lds +obj-compat_vdso := $(addprefix $(obj)/, $(obj-compat_vdso)) + +obj-y += compat_vdso.o +CPPFLAGS_compat_vdso.lds += -P -C -U$(ARCH) + +# Disable profiling and instrumentation for VDSO code +GCOV_PROFILE := n +KCOV_INSTRUMENT := n +KASAN_SANITIZE := n +UBSAN_SANITIZE := n + +# Force dependency +$(obj)/compat_vdso.o: $(obj)/compat_vdso.so + +# link rule for the .so file, .lds has to be first +$(obj)/compat_vdso.so.dbg: $(obj)/compat_vdso.lds $(obj-compat_vdso) FORCE + $(call if_changed,compat_vdsold) +LDFLAGS_compat_vdso.so.dbg = -shared -S -soname=linux-compat_vdso.so.1 \ + --build-id=sha1 --hash-style=both --eh-frame-hdr + +$(obj-compat_vdso): %.o: %.S FORCE + $(call if_changed_dep,compat_vdsoas) + +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# Generate VDSO offsets using helper script +gen-compat_vdsosym := $(srctree)/$(src)/gen_compat_vdso_offsets.sh +quiet_cmd_compat_vdsosym = VDSOSYM $@ + cmd_compat_vdsosym = $(NM) $< | $(gen-compat_vdsosym) | LC_ALL=C sort > $@ + +include/generated/compat_vdso-offsets.h: $(obj)/compat_vdso.so.dbg FORCE + $(call if_changed,compat_vdsosym) + +# actual build commands +# The DSO images are built using a special linker script +# Make sure only to export the intended __compat_vdso_xxx symbol offsets. +quiet_cmd_compat_vdsold = VDSOLD $@ + cmd_compat_vdsold = $(COMPAT_LD) $(ld_flags) $(COMPAT_LD_FLAGS) -T $(filter-out FORCE,$^) -o $@.tmp && \ + $(OBJCOPY) $(patsubst %, -G __compat_vdso_%, $(compat_vdso-syms)) $@.tmp $@ && \ + rm $@.tmp + +# actual build commands +quiet_cmd_compat_vdsoas = VDSOAS $@ + cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $< + +# install commands for the unstripped file +quiet_cmd_compat_vdso_install = INSTALL $@ + cmd_compat_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/compat_vdso/$@ + +compat_vdso.so: $(obj)/compat_vdso.so.dbg + @mkdir -p $(MODLIB)/compat_vdso + $(call cmd,compat_vdso_install) + +compat_vdso_install: compat_vdso.so diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.S b/arch/riscv/kernel/compat_vdso/compat_vdso.S new file mode 100644 index 000000000000..ffd66237e091 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/compat_vdso.S @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#define vdso_start compat_vdso_start +#define vdso_end compat_vdso_end + +#define __VDSO_PATH "arch/riscv/kernel/compat_vdso/compat_vdso.so" + +#include "../vdso/vdso.S" diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S new file mode 100644 index 000000000000..c7c9355d311e --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/vdso.lds.S" diff --git a/arch/riscv/kernel/compat_vdso/flush_icache.S b/arch/riscv/kernel/compat_vdso/flush_icache.S new file mode 100644 index 000000000000..523dd8b96045 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/flush_icache.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/flush_icache.S" diff --git a/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh new file mode 100755 index 000000000000..8ac070c783b3 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +LC_ALL=C +sed -n -e 's/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define compat\2_offset\t0x\1/p' diff --git a/arch/riscv/kernel/compat_vdso/getcpu.S b/arch/riscv/kernel/compat_vdso/getcpu.S new file mode 100644 index 000000000000..10f463efe271 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/getcpu.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/getcpu.S" diff --git a/arch/riscv/kernel/compat_vdso/note.S b/arch/riscv/kernel/compat_vdso/note.S new file mode 100644 index 000000000000..b10312907542 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/note.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/note.S" diff --git a/arch/riscv/kernel/compat_vdso/rt_sigreturn.S b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S new file mode 100644 index 000000000000..884aada4facc --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/rt_sigreturn.S" diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index c8b9ce274b9a..2e5b88ca11ce 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -207,13 +207,27 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bgeu a7, t0, 1f + bgeu a7, t0, 3f +#ifdef CONFIG_COMPAT + REG_L s0, PT_STATUS(sp) + srli s0, s0, SR_UXL_SHIFT + andi s0, s0, (SR_UXL >> SR_UXL_SHIFT) + li t0, (SR_UXL_32 >> SR_UXL_SHIFT) + sub t0, s0, t0 + bnez t0, 1f + + /* Call compat_syscall */ + la s0, compat_sys_call_table + j 2f +1: +#endif /* Call syscall */ la s0, sys_call_table +2: slli t0, a7, RISCV_LGPTR add s0, s0, t0 REG_L s0, 0(s0) -1: +3: jalr s0 ret_from_syscall: diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 504b496787aa..1c7be865ab31 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -84,6 +84,34 @@ void show_regs(struct pt_regs *regs) dump_backtrace(regs, NULL, KERN_DEFAULT); } +#ifdef CONFIG_COMPAT +static bool compat_mode_supported __read_mostly; + +bool compat_elf_check_arch(Elf32_Ehdr *hdr) +{ + return compat_mode_supported && + hdr->e_machine == EM_RISCV && + hdr->e_ident[EI_CLASS] == ELFCLASS32; +} + +static int __init compat_mode_detect(void) +{ + unsigned long tmp = csr_read(CSR_STATUS); + + csr_write(CSR_STATUS, (tmp & ~SR_UXL) | SR_UXL_32); + compat_mode_supported = + (csr_read(CSR_STATUS) & SR_UXL) == SR_UXL_32; + + csr_write(CSR_STATUS, tmp); + + pr_info("riscv: ELF compat mode %s", + compat_mode_supported ? "supported" : "failed"); + + return 0; +} +early_initcall(compat_mode_detect); +#endif + void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { @@ -98,6 +126,15 @@ void start_thread(struct pt_regs *regs, unsigned long pc, } regs->epc = pc; regs->sp = sp; + +#ifdef CONFIG_64BIT + regs->status &= ~SR_UXL; + + if (is_compat_task()) + regs->status |= SR_UXL_32; + else + regs->status |= SR_UXL_64; +#endif } void flush_thread(void) diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 793c7da0554b..2ae8280ae475 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -12,6 +12,7 @@ #include <asm/thread_info.h> #include <asm/switch_to.h> #include <linux/audit.h> +#include <linux/compat.h> #include <linux/ptrace.h> #include <linux/elf.h> #include <linux/regset.h> @@ -110,11 +111,6 @@ static const struct user_regset_view riscv_user_native_view = { .n = ARRAY_SIZE(riscv_user_regset), }; -const struct user_regset_view *task_user_regset_view(struct task_struct *task) -{ - return &riscv_user_native_view; -} - struct pt_regs_offset { const char *name; int offset; @@ -272,3 +268,84 @@ __visible void do_syscall_trace_exit(struct pt_regs *regs) trace_sys_exit(regs, regs_return_value(regs)); #endif } + +#ifdef CONFIG_COMPAT +static int compat_riscv_gpr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct compat_user_regs_struct cregs; + + regs_to_cregs(&cregs, task_pt_regs(target)); + + return membuf_write(&to, &cregs, + sizeof(struct compat_user_regs_struct)); +} + +static int compat_riscv_gpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct compat_user_regs_struct cregs; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &cregs, 0, -1); + + cregs_to_regs(&cregs, task_pt_regs(target)); + + return ret; +} + +static const struct user_regset compat_riscv_user_regset[] = { + [REGSET_X] = { + .core_note_type = NT_PRSTATUS, + .n = ELF_NGREG, + .size = sizeof(compat_elf_greg_t), + .align = sizeof(compat_elf_greg_t), + .regset_get = compat_riscv_gpr_get, + .set = compat_riscv_gpr_set, + }, +#ifdef CONFIG_FPU + [REGSET_F] = { + .core_note_type = NT_PRFPREG, + .n = ELF_NFPREG, + .size = sizeof(elf_fpreg_t), + .align = sizeof(elf_fpreg_t), + .regset_get = riscv_fpr_get, + .set = riscv_fpr_set, + }, +#endif +}; + +static const struct user_regset_view compat_riscv_user_native_view = { + .name = "riscv", + .e_machine = EM_RISCV, + .regsets = compat_riscv_user_regset, + .n = ARRAY_SIZE(compat_riscv_user_regset), +}; + +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ + long ret = -EIO; + + switch (request) { + default: + ret = compat_ptrace_request(child, request, caddr, cdata); + break; + } + + return ret; +} +#endif /* CONFIG_COMPAT */ + +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ +#ifdef CONFIG_COMPAT + if (test_tsk_thread_flag(task, TIF_32BIT)) + return &compat_riscv_user_native_view; + else +#endif + return &riscv_user_native_view; +} diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 9f4e59f80551..38b05ca6fe66 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -6,6 +6,7 @@ * Copyright (C) 2012 Regents of the University of California */ +#include <linux/compat.h> #include <linux/signal.h> #include <linux/uaccess.h> #include <linux/syscalls.h> @@ -14,6 +15,7 @@ #include <asm/ucontext.h> #include <asm/vdso.h> +#include <asm/signal32.h> #include <asm/switch_to.h> #include <asm/csr.h> @@ -261,7 +263,10 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ - ret = setup_rt_frame(ksig, oldset, regs); + if (is_compat_task()) + ret = compat_setup_rt_frame(ksig, oldset, regs); + else + ret = setup_rt_frame(ksig, oldset, regs); signal_setup_done(ret, ksig, 0); } diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 12f8a7fce78b..9c0194f176fc 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -33,7 +33,9 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, { return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0); } -#else +#endif + +#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, off_t, offset) @@ -44,7 +46,7 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, */ return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12); } -#endif /* !CONFIG_64BIT */ +#endif /* * Allows the instruction cache to be flushed from userspace. Despite RISC-V diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index a9436a65161a..50fe4c877603 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -23,6 +23,9 @@ struct vdso_data { #endif extern char vdso_start[], vdso_end[]; +#ifdef CONFIG_COMPAT +extern char compat_vdso_start[], compat_vdso_end[]; +#endif enum vvar_pages { VVAR_DATA_PAGE_OFFSET, @@ -30,6 +33,11 @@ enum vvar_pages { VVAR_NR_PAGES, }; +enum rv_vdso_map { + RV_VDSO_MAP_VVAR, + RV_VDSO_MAP_VDSO, +}; + #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) /* @@ -52,12 +60,6 @@ struct __vdso_info { struct vm_special_mapping *cm; }; -static struct __vdso_info vdso_info __ro_after_init = { - .name = "vdso", - .vdso_code_start = vdso_start, - .vdso_code_end = vdso_end, -}; - static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { @@ -66,37 +68,33 @@ static int vdso_mremap(const struct vm_special_mapping *sm, return 0; } -static int __init __vdso_init(void) +static void __init __vdso_init(struct __vdso_info *vdso_info) { unsigned int i; struct page **vdso_pagelist; unsigned long pfn; - if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) { - pr_err("vDSO is not a valid ELF object!\n"); - return -EINVAL; - } + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) + panic("vDSO is not a valid ELF object!\n"); - vdso_info.vdso_pages = ( - vdso_info.vdso_code_end - - vdso_info.vdso_code_start) >> + vdso_info->vdso_pages = ( + vdso_info->vdso_code_end - + vdso_info->vdso_code_start) >> PAGE_SHIFT; - vdso_pagelist = kcalloc(vdso_info.vdso_pages, + vdso_pagelist = kcalloc(vdso_info->vdso_pages, sizeof(struct page *), GFP_KERNEL); if (vdso_pagelist == NULL) - return -ENOMEM; + panic("vDSO kcalloc failed!\n"); /* Grab the vDSO code pages. */ - pfn = sym_to_pfn(vdso_info.vdso_code_start); + pfn = sym_to_pfn(vdso_info->vdso_code_start); - for (i = 0; i < vdso_info.vdso_pages; i++) + for (i = 0; i < vdso_info->vdso_pages; i++) vdso_pagelist[i] = pfn_to_page(pfn + i); - vdso_info.cm->pages = vdso_pagelist; - - return 0; + vdso_info->cm->pages = vdso_pagelist; } #ifdef CONFIG_TIME_NS @@ -116,13 +114,14 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { struct mm_struct *mm = task->mm; struct vm_area_struct *vma; + struct __vdso_info *vdso_info = mm->context.vdso_info; mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, vdso_info.dm)) + if (vma_is_special_mapping(vma, vdso_info->dm)) zap_page_range(vma, vma->vm_start, size); } @@ -187,11 +186,6 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, return vmf_insert_pfn(vma, vmf->address, pfn); } -enum rv_vdso_map { - RV_VDSO_MAP_VVAR, - RV_VDSO_MAP_VDSO, -}; - static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { [RV_VDSO_MAP_VVAR] = { .name = "[vvar]", @@ -203,25 +197,46 @@ static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { }, }; +static struct __vdso_info vdso_info __ro_after_init = { + .name = "vdso", + .vdso_code_start = vdso_start, + .vdso_code_end = vdso_end, + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR], + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO], +}; + +#ifdef CONFIG_COMPAT +static struct __vdso_info compat_vdso_info __ro_after_init = { + .name = "compat_vdso", + .vdso_code_start = compat_vdso_start, + .vdso_code_end = compat_vdso_end, + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR], + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO], +}; +#endif + static int __init vdso_init(void) { - vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR]; - vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO]; + __vdso_init(&vdso_info); +#ifdef CONFIG_COMPAT + __vdso_init(&compat_vdso_info); +#endif - return __vdso_init(); + return 0; } arch_initcall(vdso_init); static int __setup_additional_pages(struct mm_struct *mm, struct linux_binprm *bprm, - int uses_interp) + int uses_interp, + struct __vdso_info *vdso_info) { unsigned long vdso_base, vdso_text_len, vdso_mapping_len; void *ret; BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); - vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT; + vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT; /* Be sure to map the data page */ vdso_mapping_len = vdso_text_len + VVAR_SIZE; @@ -232,16 +247,18 @@ static int __setup_additional_pages(struct mm_struct *mm, } ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, - (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm); + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm); if (IS_ERR(ret)) goto up_fail; vdso_base += VVAR_SIZE; mm->context.vdso = (void *)vdso_base; + mm->context.vdso_info = (void *)vdso_info; + ret = _install_special_mapping(mm, vdso_base, vdso_text_len, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), - vdso_info.cm); + vdso_info->cm); if (IS_ERR(ret)) goto up_fail; @@ -253,6 +270,24 @@ up_fail: return PTR_ERR(ret); } +#ifdef CONFIG_COMPAT +int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp) +{ + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp, + &compat_vdso_info); + mmap_write_unlock(mm); + + return ret; +} +#endif + int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; @@ -261,7 +296,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (mmap_write_lock_killable(mm)) return -EINTR; - ret = __setup_additional_pages(mm, bprm, uses_interp); + ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info); mmap_write_unlock(mm); return ret; diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S index df222245be05..83f1c899e8d8 100644 --- a/arch/riscv/kernel/vdso/vdso.S +++ b/arch/riscv/kernel/vdso/vdso.S @@ -7,12 +7,16 @@ #include <linux/linkage.h> #include <asm/page.h> +#ifndef __VDSO_PATH +#define __VDSO_PATH "arch/riscv/kernel/vdso/vdso.so" +#endif + __PAGE_ALIGNED_DATA .globl vdso_start, vdso_end .balign PAGE_SIZE vdso_start: - .incbin "arch/riscv/kernel/vdso/vdso.so" + .incbin __VDSO_PATH .balign PAGE_SIZE vdso_end: |