diff options
Diffstat (limited to 'arch/x86/ia32')
| -rw-r--r-- | arch/x86/ia32/Makefile | 4 | ||||
| -rw-r--r-- | arch/x86/ia32/ia32_aout.c | 229 | ||||
| -rw-r--r-- | arch/x86/ia32/ia32_signal.c | 647 | ||||
| -rw-r--r-- | arch/x86/ia32/ia32entry.S | 668 | ||||
| -rw-r--r-- | arch/x86/ia32/ipc32.c | 53 | ||||
| -rw-r--r-- | arch/x86/ia32/nosyscall.c | 7 | ||||
| -rw-r--r-- | arch/x86/ia32/sys_ia32.c | 696 | ||||
| -rw-r--r-- | arch/x86/ia32/syscall_ia32.c | 25 |
8 files changed, 624 insertions, 1705 deletions
diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index 52d0ccfcf6e..e785b422b76 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -3,9 +3,7 @@ # obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o - -sysv-$(CONFIG_SYSVIPC) := ipc32.o -obj-$(CONFIG_IA32_EMULATION) += $(sysv-y) +obj-$(CONFIG_IA32_EMULATION) += nosyscall.o syscall_ia32.o obj-$(CONFIG_IA32_AOUT) += ia32_aout.o diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 58cccb6483b..d21ff89207c 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -21,13 +21,12 @@ #include <linux/fcntl.h> #include <linux/ptrace.h> #include <linux/user.h> -#include <linux/slab.h> #include <linux/binfmts.h> #include <linux/personality.h> #include <linux/init.h> #include <linux/jiffies.h> +#include <linux/perf_event.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> @@ -35,14 +34,18 @@ #include <asm/ia32.h> #undef WARN_OLD -#undef CORE_DUMP /* probably broken */ -static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs); +static int load_aout_binary(struct linux_binprm *); static int load_aout_library(struct file *); -#ifdef CORE_DUMP -static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, - unsigned long limit); +#ifdef CONFIG_COREDUMP +static int aout_core_dump(struct coredump_params *); + +static unsigned long get_dr(int n) +{ + struct perf_event *bp = current->thread.ptrace_bps[n]; + return bp ? bp->hw.info.address : 0; +} /* * fill in the user structure for a core dump.. @@ -50,6 +53,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, static void dump_thread32(struct pt_regs *regs, struct user32 *dump) { u32 fs, gs; + memset(dump, 0, sizeof(*dump)); /* changed the size calculations - should hopefully work better. lbt */ dump->magic = CMAGIC; @@ -59,15 +63,12 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump) dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT; dump->u_dsize -= dump->u_tsize; - dump->u_ssize = 0; - dump->u_debugreg[0] = current->thread.debugreg0; - dump->u_debugreg[1] = current->thread.debugreg1; - dump->u_debugreg[2] = current->thread.debugreg2; - dump->u_debugreg[3] = current->thread.debugreg3; - dump->u_debugreg[4] = 0; - dump->u_debugreg[5] = 0; + dump->u_debugreg[0] = get_dr(0); + dump->u_debugreg[1] = get_dr(1); + dump->u_debugreg[2] = get_dr(2); + dump->u_debugreg[3] = get_dr(3); dump->u_debugreg[6] = current->thread.debugreg6; - dump->u_debugreg[7] = current->thread.debugreg7; + dump->u_debugreg[7] = current->thread.ptrace_dr7; if (dump->start_stack < 0xc0000000) { unsigned long tmp; @@ -76,22 +77,24 @@ static void dump_thread32(struct pt_regs *regs, struct user32 *dump) dump->u_ssize = tmp >> PAGE_SHIFT; } - dump->regs.bx = regs->bx; - dump->regs.cx = regs->cx; - dump->regs.dx = regs->dx; - dump->regs.si = regs->si; - dump->regs.di = regs->di; - dump->regs.bp = regs->bp; - dump->regs.ax = regs->ax; + dump->regs.ebx = regs->bx; + dump->regs.ecx = regs->cx; + dump->regs.edx = regs->dx; + dump->regs.esi = regs->si; + dump->regs.edi = regs->di; + dump->regs.ebp = regs->bp; + dump->regs.eax = regs->ax; dump->regs.ds = current->thread.ds; dump->regs.es = current->thread.es; - asm("movl %%fs,%0" : "=r" (fs)); dump->regs.fs = fs; - asm("movl %%gs,%0" : "=r" (gs)); dump->regs.gs = gs; - dump->regs.orig_ax = regs->orig_ax; - dump->regs.ip = regs->ip; + savesegment(fs, fs); + dump->regs.fs = fs; + savesegment(gs, gs); + dump->regs.gs = gs; + dump->regs.orig_eax = regs->orig_ax; + dump->regs.eip = regs->ip; dump->regs.cs = regs->cs; - dump->regs.flags = regs->flags; - dump->regs.sp = regs->sp; + dump->regs.eflags = regs->flags; + dump->regs.esp = regs->sp; dump->regs.ss = regs->ss; #if 1 /* FIXME */ @@ -107,7 +110,7 @@ static struct linux_binfmt aout_format = { .module = THIS_MODULE, .load_binary = load_aout_binary, .load_shlib = load_aout_library, -#ifdef CORE_DUMP +#ifdef CONFIG_COREDUMP .core_dump = aout_core_dump, #endif .min_coredump = PAGE_SIZE @@ -119,34 +122,18 @@ static void set_brk(unsigned long start, unsigned long end) end = PAGE_ALIGN(end); if (end <= start) return; - down_write(¤t->mm->mmap_sem); - do_brk(start, end - start); - up_write(¤t->mm->mmap_sem); + vm_brk(start, end - start); } -#ifdef CORE_DUMP +#ifdef CONFIG_COREDUMP /* * These are the only things you should do on a core-file: use only these * macros to write out all the necessary info. */ -static int dump_write(struct file *file, const void *addr, int nr) -{ - return file->f_op->write(file, addr, nr, &file->f_pos) == nr; -} - -#define DUMP_WRITE(addr, nr) \ - if (!dump_write(file, (void *)(addr), (nr))) \ - goto end_coredump; - -#define DUMP_SEEK(offset) \ - if (file->f_op->llseek) { \ - if (file->f_op->llseek(file, (offset), 0) != (offset)) \ - goto end_coredump; \ - } else \ - file->f_pos = (offset) +#include <linux/coredump.h> -#define START_DATA() (u.u_tsize << PAGE_SHIFT) +#define START_DATA(u) (u.u_tsize << PAGE_SHIFT) #define START_STACK(u) (u.start_stack) /* @@ -159,8 +146,7 @@ static int dump_write(struct file *file, const void *addr, int nr) * dumping of the process results in another error.. */ -static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, - unsigned long limit) +static int aout_core_dump(struct coredump_params *cprm) { mm_segment_t fs; int has_dumped = 0; @@ -170,22 +156,21 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, fs = get_fs(); set_fs(KERNEL_DS); has_dumped = 1; - current->flags |= PF_DUMPCORE; strncpy(dump.u_comm, current->comm, sizeof(current->comm)); dump.u_ar0 = offsetof(struct user32, regs); - dump.signal = signr; - dump_thread32(regs, &dump); + dump.signal = cprm->siginfo->si_signo; + dump_thread32(cprm->regs, &dump); /* * If the size of the dump file exceeds the rlimit, then see * what would happen if we wrote the stack, but not the data * area. */ - if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > limit) + if ((dump.u_dsize + dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) dump.u_dsize = 0; /* Make sure we have enough room to write the stack and data areas. */ - if ((dump.u_ssize + 1) * PAGE_SIZE > limit) + if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) dump.u_ssize = 0; /* make sure we actually have a data and stack area to dump */ @@ -199,29 +184,27 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, set_fs(KERNEL_DS); /* struct user */ - DUMP_WRITE(&dump, sizeof(dump)); + if (!dump_emit(cprm, &dump, sizeof(dump))) + goto end_coredump; /* Now dump all of the user data. Include malloced stuff as well */ - DUMP_SEEK(PAGE_SIZE); + if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump))) + goto end_coredump; /* now we start writing out the user space info */ set_fs(USER_DS); /* Dump the data area */ if (dump.u_dsize != 0) { dump_start = START_DATA(dump); dump_size = dump.u_dsize << PAGE_SHIFT; - DUMP_WRITE(dump_start, dump_size); + if (!dump_emit(cprm, (void *)dump_start, dump_size)) + goto end_coredump; } /* Now prepare to dump the stack area */ if (dump.u_ssize != 0) { dump_start = START_STACK(dump); dump_size = dump.u_ssize << PAGE_SHIFT; - DUMP_WRITE(dump_start, dump_size); + if (!dump_emit(cprm, (void *)dump_start, dump_size)) + goto end_coredump; } - /* - * Finally dump the task struct. Not be used by gdb, but - * could be useful - */ - set_fs(KERNEL_DS); - DUMP_WRITE(current, sizeof(*current)); end_coredump: set_fs(fs); return has_dumped; @@ -274,9 +257,10 @@ static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm) * These are the functions used to load a.out style executables and shared * libraries. There is no binary dependent code anywhere else. */ -static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) +static int load_aout_binary(struct linux_binprm *bprm) { unsigned long error, fd_offset, rlim; + struct pt_regs *regs = current_pt_regs(); struct exec ex; int retval; @@ -284,7 +268,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC && N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) || N_TRSIZE(ex) || N_DRSIZE(ex) || - i_size_read(bprm->file->f_path.dentry->d_inode) < + i_size_read(file_inode(bprm->file)) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) { return -ENOEXEC; } @@ -295,7 +279,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) * size limits imposed on them by creating programs with large * arrays in the data or bss. */ - rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur; + rlim = rlimit(RLIMIT_DATA); if (rlim >= RLIM_INFINITY) rlim = ~0; if (ex.a_data + ex.a_bss > rlim) @@ -306,55 +290,51 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) if (retval) return retval; + /* OK, This is the point of no return */ + set_personality(PER_LINUX); + set_personality_ia32(false); + + setup_new_exec(bprm); + regs->cs = __USER32_CS; regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; - /* OK, This is the point of no return */ - set_personality(PER_LINUX); - set_thread_flag(TIF_IA32); - clear_thread_flag(TIF_ABI_PENDING); - current->mm->end_code = ex.a_text + (current->mm->start_code = N_TXTADDR(ex)); current->mm->end_data = ex.a_data + (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = TASK_UNMAPPED_BASE; - current->mm->cached_hole_size = 0; - current->mm->mmap = NULL; - compute_creds(bprm); - current->flags &= ~PF_FORKNOEXEC; + retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); + if (retval < 0) { + /* Someone check-me: is this error path enough? */ + send_sig(SIGKILL, current, 0); + return retval; + } + + install_exec_creds(bprm); if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; - loff_t pos; text_addr = N_TXTADDR(ex); - - pos = 32; map_size = ex.a_text+ex.a_data; - down_write(¤t->mm->mmap_sem); - error = do_brk(text_addr & PAGE_MASK, map_size); - up_write(¤t->mm->mmap_sem); + error = vm_brk(text_addr & PAGE_MASK, map_size); if (error != (text_addr & PAGE_MASK)) { send_sig(SIGKILL, current, 0); return error; } - error = bprm->file->f_op->read(bprm->file, - (char __user *)text_addr, - ex.a_text+ex.a_data, &pos); + error = read_code(bprm->file, text_addr, 32, + ex.a_text + ex.a_data); if ((signed long)error < 0) { send_sig(SIGKILL, current, 0); return error; } - - flush_icache_range(text_addr, text_addr+ex.a_text+ex.a_data); } else { #ifdef WARN_OLD static unsigned long error_time, error_time2; @@ -376,40 +356,28 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) #endif if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) { - loff_t pos = fd_offset; - - down_write(¤t->mm->mmap_sem); - do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); - up_write(¤t->mm->mmap_sem); - bprm->file->f_op->read(bprm->file, - (char __user *)N_TXTADDR(ex), - ex.a_text+ex.a_data, &pos); - flush_icache_range((unsigned long) N_TXTADDR(ex), - (unsigned long) N_TXTADDR(ex) + - ex.a_text+ex.a_data); + vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data); + read_code(bprm->file, N_TXTADDR(ex), fd_offset, + ex.a_text+ex.a_data); goto beyond_if; } - down_write(¤t->mm->mmap_sem); - error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, + error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE | MAP_32BIT, fd_offset); - up_write(¤t->mm->mmap_sem); if (error != N_TXTADDR(ex)) { send_sig(SIGKILL, current, 0); return error; } - down_write(¤t->mm->mmap_sem); - error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data, + error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE | MAP_32BIT, fd_offset + ex.a_text); - up_write(¤t->mm->mmap_sem); if (error != N_DATADDR(ex)) { send_sig(SIGKILL, current, 0); return error; @@ -420,18 +388,12 @@ beyond_if: set_brk(current->mm->start_brk, current->mm->brk); - retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); - if (retval < 0) { - /* Someone check-me: is this error path enough? */ - send_sig(SIGKILL, current, 0); - return retval; - } - current->mm->start_stack = (unsigned long)create_aout_tables((char __user *)bprm->p, bprm); /* start thread */ - asm volatile("movl %0,%%fs" :: "r" (0)); \ - asm volatile("movl %0,%%es; movl %0,%%ds": :"r" (__USER32_DS)); + loadsegment(fs, 0); + loadsegment(ds, __USER32_DS); + loadsegment(es, __USER32_DS); load_gs_index(0); (regs)->ip = ex.a_entry; (regs)->sp = current->mm->start_stack; @@ -441,23 +403,15 @@ beyond_if: regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; set_fs(USER_DS); - if (unlikely(current->ptrace & PT_PTRACED)) { - if (current->ptrace & PT_TRACE_EXEC) - ptrace_notify((PTRACE_EVENT_EXEC << 8) | SIGTRAP); - else - send_sig(SIGTRAP, current, 0); - } return 0; } static int load_aout_library(struct file *file) { - struct inode *inode; unsigned long bss, start_addr, len, error; int retval; struct exec ex; - inode = file->f_path.dentry->d_inode; retval = -ENOEXEC; error = kernel_read(file, 0, (char *) &ex, sizeof(ex)); @@ -467,7 +421,7 @@ static int load_aout_library(struct file *file) /* We come in here for the regular a.out style of shared libraries */ if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) || N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) || - i_size_read(inode) < + i_size_read(file_inode(file)) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) { goto out; } @@ -481,8 +435,6 @@ static int load_aout_library(struct file *file) start_addr = ex.a_entry & 0xfffff000; if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) { - loff_t pos = N_TXTOFF(ex); - #ifdef WARN_OLD static unsigned long error_time; if (time_after(jiffies, error_time + 5*HZ)) { @@ -493,26 +445,18 @@ static int load_aout_library(struct file *file) error_time = jiffies; } #endif - down_write(¤t->mm->mmap_sem); - do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); - up_write(¤t->mm->mmap_sem); - - file->f_op->read(file, (char __user *)start_addr, - ex.a_text + ex.a_data, &pos); - flush_icache_range((unsigned long) start_addr, - (unsigned long) start_addr + ex.a_text + - ex.a_data); + vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss); + read_code(file, start_addr, N_TXTOFF(ex), + ex.a_text + ex.a_data); retval = 0; goto out; } /* Now use mmap to map the library into memory. */ - down_write(¤t->mm->mmap_sem); - error = do_mmap(file, start_addr, ex.a_text + ex.a_data, + error = vm_mmap(file, start_addr, ex.a_text + ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT, N_TXTOFF(ex)); - up_write(¤t->mm->mmap_sem); retval = error; if (error != start_addr) goto out; @@ -520,9 +464,7 @@ static int load_aout_library(struct file *file) len = PAGE_ALIGN(ex.a_text + ex.a_data); bss = ex.a_text + ex.a_data + ex.a_bss; if (bss > len) { - down_write(¤t->mm->mmap_sem); - error = do_brk(start_addr + len, bss - len); - up_write(¤t->mm->mmap_sem); + error = vm_brk(start_addr + len, bss - len); retval = error; if (error != start_addr + len) goto out; @@ -534,7 +476,8 @@ out: static int __init init_aout_binfmt(void) { - return register_binfmt(&aout_format); + register_binfmt(&aout_format); + return 0; } static void __exit exit_aout_binfmt(void) diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 5e7771a3ba2..f9e181aaba9 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -12,10 +12,8 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> -#include <linux/signal.h> #include <linux/errno.h> #include <linux/wait.h> -#include <linux/ptrace.h> #include <linux/unistd.h> #include <linux/stddef.h> #include <linux/personality.h> @@ -24,261 +22,194 @@ #include <asm/ucontext.h> #include <asm/uaccess.h> #include <asm/i387.h> -#include <asm/ia32.h> +#include <asm/fpu-internal.h> #include <asm/ptrace.h> #include <asm/ia32_unistd.h> #include <asm/user32.h> #include <asm/sigcontext32.h> #include <asm/proto.h> #include <asm/vdso.h> +#include <asm/sigframe.h> +#include <asm/sighandling.h> +#include <asm/sys_ia32.h> +#include <asm/smap.h> -#define DEBUG_SIG 0 - -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - -asmlinkage int do_signal(struct pt_regs *regs, sigset_t *oldset); -void signal_fault(struct pt_regs *regs, void __user *frame, char *where); - -int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) { - int err; + int err = 0; + bool ia32 = test_thread_flag(TIF_IA32); if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) return -EFAULT; - /* If you change siginfo_t structure, please make sure that - this code is fixed accordingly. - It should never copy any pad contained in the structure - to avoid security leaks, but must copy the generic - 3 ints plus the relevant union member. */ - err = __put_user(from->si_signo, &to->si_signo); - err |= __put_user(from->si_errno, &to->si_errno); - err |= __put_user((short)from->si_code, &to->si_code); - - if (from->si_code < 0) { - err |= __put_user(from->si_pid, &to->si_pid); - err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user(ptr_to_compat(from->si_ptr), &to->si_ptr); - } else { - /* - * First 32bits of unions are always present: - * si_pid === si_band === si_tid === si_addr(LS half) - */ - err |= __put_user(from->_sifields._pad[0], - &to->_sifields._pad[0]); - switch (from->si_code >> 16) { - case __SI_FAULT >> 16: - break; - case __SI_CHLD >> 16: - err |= __put_user(from->si_utime, &to->si_utime); - err |= __put_user(from->si_stime, &to->si_stime); - err |= __put_user(from->si_status, &to->si_status); - /* FALL THROUGH */ - default: - case __SI_KILL >> 16: - err |= __put_user(from->si_uid, &to->si_uid); - break; - case __SI_POLL >> 16: - err |= __put_user(from->si_fd, &to->si_fd); - break; - case __SI_TIMER >> 16: - err |= __put_user(from->si_overrun, &to->si_overrun); - err |= __put_user(ptr_to_compat(from->si_ptr), - &to->si_ptr); - break; - /* This is not generated by the kernel as of now. */ - case __SI_RT >> 16: - case __SI_MESGQ >> 16: - err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user(from->si_int, &to->si_int); - break; + put_user_try { + /* If you change siginfo_t structure, please make sure that + this code is fixed accordingly. + It should never copy any pad contained in the structure + to avoid security leaks, but must copy the generic + 3 ints plus the relevant union member. */ + put_user_ex(from->si_signo, &to->si_signo); + put_user_ex(from->si_errno, &to->si_errno); + put_user_ex((short)from->si_code, &to->si_code); + + if (from->si_code < 0) { + put_user_ex(from->si_pid, &to->si_pid); + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); + } else { + /* + * First 32bits of unions are always present: + * si_pid === si_band === si_tid === si_addr(LS half) + */ + put_user_ex(from->_sifields._pad[0], + &to->_sifields._pad[0]); + switch (from->si_code >> 16) { + case __SI_FAULT >> 16: + break; + case __SI_SYS >> 16: + put_user_ex(from->si_syscall, &to->si_syscall); + put_user_ex(from->si_arch, &to->si_arch); + break; + case __SI_CHLD >> 16: + if (ia32) { + put_user_ex(from->si_utime, &to->si_utime); + put_user_ex(from->si_stime, &to->si_stime); + } else { + put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime); + put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime); + } + put_user_ex(from->si_status, &to->si_status); + /* FALL THROUGH */ + default: + case __SI_KILL >> 16: + put_user_ex(from->si_uid, &to->si_uid); + break; + case __SI_POLL >> 16: + put_user_ex(from->si_fd, &to->si_fd); + break; + case __SI_TIMER >> 16: + put_user_ex(from->si_overrun, &to->si_overrun); + put_user_ex(ptr_to_compat(from->si_ptr), + &to->si_ptr); + break; + /* This is not generated by the kernel as of now. */ + case __SI_RT >> 16: + case __SI_MESGQ >> 16: + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(from->si_int, &to->si_int); + break; + } } - } + } put_user_catch(err); + return err; } int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) { - int err; + int err = 0; u32 ptr32; if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) return -EFAULT; - err = __get_user(to->si_signo, &from->si_signo); - err |= __get_user(to->si_errno, &from->si_errno); - err |= __get_user(to->si_code, &from->si_code); + get_user_try { + get_user_ex(to->si_signo, &from->si_signo); + get_user_ex(to->si_errno, &from->si_errno); + get_user_ex(to->si_code, &from->si_code); - err |= __get_user(to->si_pid, &from->si_pid); - err |= __get_user(to->si_uid, &from->si_uid); - err |= __get_user(ptr32, &from->si_ptr); - to->si_ptr = compat_ptr(ptr32); + get_user_ex(to->si_pid, &from->si_pid); + get_user_ex(to->si_uid, &from->si_uid); + get_user_ex(ptr32, &from->si_ptr); + to->si_ptr = compat_ptr(ptr32); + } get_user_catch(err); return err; } -asmlinkage long sys32_sigsuspend(int history0, int history1, old_sigset_t mask) -{ - mask &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); - current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, mask); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - current->state = TASK_INTERRUPTIBLE; - schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); - return -ERESTARTNOHAND; -} - -asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr, - stack_ia32_t __user *uoss_ptr, - struct pt_regs *regs) -{ - stack_t uss, uoss; - int ret; - mm_segment_t seg; - - if (uss_ptr) { - u32 ptr; - - memset(&uss, 0, sizeof(stack_t)); - if (!access_ok(VERIFY_READ, uss_ptr, sizeof(stack_ia32_t)) || - __get_user(ptr, &uss_ptr->ss_sp) || - __get_user(uss.ss_flags, &uss_ptr->ss_flags) || - __get_user(uss.ss_size, &uss_ptr->ss_size)) - return -EFAULT; - uss.ss_sp = compat_ptr(ptr); - } - seg = get_fs(); - set_fs(KERNEL_DS); - ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp); - set_fs(seg); - if (ret >= 0 && uoss_ptr) { - if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)) || - __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) || - __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) || - __put_user(uoss.ss_size, &uoss_ptr->ss_size)) - ret = -EFAULT; - } - return ret; -} - /* * Do a signal return; undo the signal stack. */ +#define loadsegment_gs(v) load_gs_index(v) +#define loadsegment_fs(v) loadsegment(fs, v) +#define loadsegment_ds(v) loadsegment(ds, v) +#define loadsegment_es(v) loadsegment(es, v) -struct sigframe -{ - u32 pretcode; - int sig; - struct sigcontext_ia32 sc; - struct _fpstate_ia32 fpstate; - unsigned int extramask[_COMPAT_NSIG_WORDS-1]; - char retcode[8]; -}; - -struct rt_sigframe -{ - u32 pretcode; - int sig; - u32 pinfo; - u32 puc; - compat_siginfo_t info; - struct ucontext_ia32 uc; - struct _fpstate_ia32 fpstate; - char retcode[8]; -}; - -#define COPY(x) { \ - unsigned int reg; \ - err |= __get_user(reg, &sc->x); \ - regs->x = reg; \ +#define get_user_seg(seg) ({ unsigned int v; savesegment(seg, v); v; }) +#define set_user_seg(seg, v) loadsegment_##seg(v) + +#define COPY(x) { \ + get_user_ex(regs->x, &sc->x); \ } -#define RELOAD_SEG(seg,mask) \ - { unsigned int cur; \ - unsigned short pre; \ - err |= __get_user(pre, &sc->seg); \ - asm volatile("movl %%" #seg ",%0" : "=r" (cur)); \ - pre |= mask; \ - if (pre != cur) loadsegment(seg, pre); } +#define GET_SEG(seg) ({ \ + unsigned short tmp; \ + get_user_ex(tmp, &sc->seg); \ + tmp; \ +}) + +#define COPY_SEG_CPL3(seg) do { \ + regs->seg = GET_SEG(seg) | 3; \ +} while (0) + +#define RELOAD_SEG(seg) { \ + unsigned int pre = GET_SEG(seg); \ + unsigned int cur = get_user_seg(seg); \ + pre |= 3; \ + if (pre != cur) \ + set_user_seg(seg, pre); \ +} static int ia32_restore_sigcontext(struct pt_regs *regs, struct sigcontext_ia32 __user *sc, - unsigned int *peax) + unsigned int *pax) { - unsigned int tmpflags, gs, oldgs, err = 0; - struct _fpstate_ia32 __user *buf; + unsigned int tmpflags, err = 0; + void __user *buf; u32 tmp; /* Always make any pending restarted system calls return -EINTR */ current_thread_info()->restart_block.fn = do_no_restart_syscall; -#if DEBUG_SIG - printk(KERN_DEBUG "SIG restore_sigcontext: " - "sc=%p err(%x) eip(%x) cs(%x) flg(%x)\n", - sc, sc->err, sc->ip, sc->cs, sc->flags); -#endif - - /* - * Reload fs and gs if they have changed in the signal - * handler. This does not handle long fs/gs base changes in - * the handler, but does not clobber them at least in the - * normal case. - */ - err |= __get_user(gs, &sc->gs); - gs |= 3; - asm("movl %%gs,%0" : "=r" (oldgs)); - if (gs != oldgs) - load_gs_index(gs); - - RELOAD_SEG(fs, 3); - RELOAD_SEG(ds, 3); - RELOAD_SEG(es, 3); - - COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); - COPY(dx); COPY(cx); COPY(ip); - /* Don't touch extended registers */ - - err |= __get_user(regs->cs, &sc->cs); - regs->cs |= 3; - err |= __get_user(regs->ss, &sc->ss); - regs->ss |= 3; - - err |= __get_user(tmpflags, &sc->flags); - regs->flags = (regs->flags & ~0x40DD5) | (tmpflags & 0x40DD5); - /* disable syscall checks */ - regs->orig_ax = -1; - - err |= __get_user(tmp, &sc->fpstate); - buf = compat_ptr(tmp); - if (buf) { - if (!access_ok(VERIFY_READ, buf, sizeof(*buf))) - goto badframe; - err |= restore_i387_ia32(buf); - } else { - struct task_struct *me = current; + get_user_try { + /* + * Reload fs and gs if they have changed in the signal + * handler. This does not handle long fs/gs base changes in + * the handler, but does not clobber them at least in the + * normal case. + */ + RELOAD_SEG(gs); + RELOAD_SEG(fs); + RELOAD_SEG(ds); + RELOAD_SEG(es); - if (used_math()) { - clear_fpu(me); - clear_used_math(); - } - } + COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); + COPY(dx); COPY(cx); COPY(ip); + /* Don't touch extended registers */ - err |= __get_user(tmp, &sc->ax); - *peax = tmp; + COPY_SEG_CPL3(cs); + COPY_SEG_CPL3(ss); - return err; + get_user_ex(tmpflags, &sc->flags); + regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); + /* disable syscall checks */ + regs->orig_ax = -1; -badframe: - return 1; + get_user_ex(tmp, &sc->fpstate); + buf = compat_ptr(tmp); + + get_user_ex(*pax, &sc->ax); + } get_user_catch(err); + + err |= restore_xstate_sig(buf, 1); + + return err; } -asmlinkage long sys32_sigreturn(struct pt_regs *regs) +asmlinkage long sys32_sigreturn(void) { - struct sigframe __user *frame = (struct sigframe __user *)(regs->sp-8); + struct pt_regs *regs = current_pt_regs(); + struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8); sigset_t set; unsigned int ax; @@ -291,11 +222,7 @@ asmlinkage long sys32_sigreturn(struct pt_regs *regs) sizeof(frame->extramask)))) goto badframe; - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); if (ia32_restore_sigcontext(regs, &frame->sc, &ax)) goto badframe; @@ -306,31 +233,26 @@ badframe: return 0; } -asmlinkage long sys32_rt_sigreturn(struct pt_regs *regs) +asmlinkage long sys32_rt_sigreturn(void) { - struct rt_sigframe __user *frame; + struct pt_regs *regs = current_pt_regs(); + struct rt_sigframe_ia32 __user *frame; sigset_t set; unsigned int ax; - struct pt_regs tregs; - frame = (struct rt_sigframe __user *)(regs->sp - 4); + frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4); if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) goto badframe; - tregs = *regs; - if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT) + if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; return ax; @@ -345,50 +267,39 @@ badframe: */ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, - struct _fpstate_ia32 __user *fpstate, + void __user *fpstate, struct pt_regs *regs, unsigned int mask) { - int tmp, err = 0; - - tmp = 0; - __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp)); - err |= __put_user(tmp, (unsigned int __user *)&sc->gs); - __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp)); - err |= __put_user(tmp, (unsigned int __user *)&sc->fs); - __asm__("movl %%ds,%0" : "=r"(tmp): "0"(tmp)); - err |= __put_user(tmp, (unsigned int __user *)&sc->ds); - __asm__("movl %%es,%0" : "=r"(tmp): "0"(tmp)); - err |= __put_user(tmp, (unsigned int __user *)&sc->es); - - err |= __put_user((u32)regs->di, &sc->di); - err |= __put_user((u32)regs->si, &sc->si); - err |= __put_user((u32)regs->bp, &sc->bp); - err |= __put_user((u32)regs->sp, &sc->sp); - err |= __put_user((u32)regs->bx, &sc->bx); - err |= __put_user((u32)regs->dx, &sc->dx); - err |= __put_user((u32)regs->cx, &sc->cx); - err |= __put_user((u32)regs->ax, &sc->ax); - err |= __put_user((u32)regs->cs, &sc->cs); - err |= __put_user((u32)regs->ss, &sc->ss); - err |= __put_user(current->thread.trap_no, &sc->trapno); - err |= __put_user(current->thread.error_code, &sc->err); - err |= __put_user((u32)regs->ip, &sc->ip); - err |= __put_user((u32)regs->flags, &sc->flags); - err |= __put_user((u32)regs->sp, &sc->sp_at_signal); - - tmp = save_i387_ia32(fpstate); - if (tmp < 0) - err = -EFAULT; - else { - clear_used_math(); - stts(); - err |= __put_user(ptr_to_compat(tmp ? fpstate : NULL), - &sc->fpstate); - } + int err = 0; - /* non-iBCS2 extensions.. */ - err |= __put_user(mask, &sc->oldmask); - err |= __put_user(current->thread.cr2, &sc->cr2); + put_user_try { + put_user_ex(get_user_seg(gs), (unsigned int __user *)&sc->gs); + put_user_ex(get_user_seg(fs), (unsigned int __user *)&sc->fs); + put_user_ex(get_user_seg(ds), (unsigned int __user *)&sc->ds); + put_user_ex(get_user_seg(es), (unsigned int __user *)&sc->es); + + put_user_ex(regs->di, &sc->di); + put_user_ex(regs->si, &sc->si); + put_user_ex(regs->bp, &sc->bp); + put_user_ex(regs->sp, &sc->sp); + put_user_ex(regs->bx, &sc->bx); + put_user_ex(regs->dx, &sc->dx); + put_user_ex(regs->cx, &sc->cx); + put_user_ex(regs->ax, &sc->ax); + put_user_ex(current->thread.trap_nr, &sc->trapno); + put_user_ex(current->thread.error_code, &sc->err); + put_user_ex(regs->ip, &sc->ip); + put_user_ex(regs->cs, (unsigned int __user *)&sc->cs); + put_user_ex(regs->flags, &sc->flags); + put_user_ex(regs->sp, &sc->sp_at_signal); + put_user_ex(regs->ss, (unsigned int __user *)&sc->ss); + + put_user_ex(ptr_to_compat(fpstate), &sc->fpstate); + + /* non-iBCS2 extensions.. */ + put_user_ex(mask, &sc->oldmask); + put_user_ex(current->thread.cr2, &sc->cr2); + } put_user_catch(err); return err; } @@ -396,8 +307,9 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, /* * Determine which stack to use.. */ -static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, - size_t frame_size) +static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, + size_t frame_size, + void __user **fpstate) { unsigned long sp; @@ -405,16 +317,23 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, sp = regs->sp; /* This is the X/Open sanctioned signal stack switching. */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(sp) == 0) - sp = current->sas_ss_sp + current->sas_ss_size; - } - + if (ksig->ka.sa.sa_flags & SA_ONSTACK) + sp = sigsp(sp, ksig); /* This is the legacy signal stack switching. */ - else if ((regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) - sp = (unsigned long) ka->sa.sa_restorer; + else if ((regs->ss & 0xffff) != __USER32_DS && + !(ksig->ka.sa.sa_flags & SA_RESTORER) && + ksig->ka.sa.sa_restorer) + sp = (unsigned long) ksig->ka.sa.sa_restorer; + + if (used_math()) { + unsigned long fx_aligned, math_size; + + sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size); + *fpstate = (struct _fpstate_ia32 __user *) sp; + if (save_xstate_sig(*fpstate, (void __user *)fx_aligned, + math_size) < 0) + return (void __user *) -1L; + } sp -= frame_size; /* Align the stack pointer according to the i386 ABI, @@ -423,114 +342,98 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, return (void __user *) sp; } -int ia32_setup_frame(int sig, struct k_sigaction *ka, +int ia32_setup_frame(int sig, struct ksignal *ksig, compat_sigset_t *set, struct pt_regs *regs) { - struct sigframe __user *frame; + struct sigframe_ia32 __user *frame; void __user *restorer; int err = 0; + void __user *fpstate = NULL; /* copy_to_user optimizes that into a single 8 byte store */ static const struct { u16 poplmovl; u32 val; u16 int80; - u16 pad; } __attribute__((packed)) code = { 0xb858, /* popl %eax ; movl $...,%eax */ __NR_ia32_sigreturn, 0x80cd, /* int $0x80 */ - 0, }; - frame = get_sigframe(ka, regs, sizeof(*frame)); + frame = get_sigframe(ksig, regs, sizeof(*frame), &fpstate); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - goto give_sigsegv; + return -EFAULT; - err |= __put_user(sig, &frame->sig); - if (err) - goto give_sigsegv; + if (__put_user(sig, &frame->sig)) + return -EFAULT; - err |= ia32_setup_sigcontext(&frame->sc, &frame->fpstate, regs, - set->sig[0]); - if (err) - goto give_sigsegv; + if (ia32_setup_sigcontext(&frame->sc, fpstate, regs, set->sig[0])) + return -EFAULT; if (_COMPAT_NSIG_WORDS > 1) { - err |= __copy_to_user(frame->extramask, &set->sig[1], - sizeof(frame->extramask)); - if (err) - goto give_sigsegv; + if (__copy_to_user(frame->extramask, &set->sig[1], + sizeof(frame->extramask))) + return -EFAULT; } - if (ka->sa.sa_flags & SA_RESTORER) { - restorer = ka->sa.sa_restorer; + if (ksig->ka.sa.sa_flags & SA_RESTORER) { + restorer = ksig->ka.sa.sa_restorer; } else { /* Return stub is in 32bit vsyscall page */ - if (current->binfmt->hasvdso) - restorer = VDSO32_SYMBOL(current->mm->context.vdso, - sigreturn); + if (current->mm->context.vdso) + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_sigreturn; else restorer = &frame->retcode; } - err |= __put_user(ptr_to_compat(restorer), &frame->pretcode); - /* - * These are actually not used anymore, but left because some - * gdb versions depend on them as a marker. - */ - err |= __copy_to_user(frame->retcode, &code, 8); + put_user_try { + put_user_ex(ptr_to_compat(restorer), &frame->pretcode); + + /* + * These are actually not used anymore, but left because some + * gdb versions depend on them as a marker. + */ + put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); + } put_user_catch(err); + if (err) - goto give_sigsegv; + return -EFAULT; /* Set up registers for signal handler */ regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ka->sa.sa_handler; + regs->ip = (unsigned long) ksig->ka.sa.sa_handler; /* Make -mregparm=3 work */ regs->ax = sig; regs->dx = 0; regs->cx = 0; - asm volatile("movl %0,%%ds" :: "r" (__USER32_DS)); - asm volatile("movl %0,%%es" :: "r" (__USER32_DS)); + loadsegment(ds, __USER32_DS); + loadsegment(es, __USER32_DS); regs->cs = __USER32_CS; regs->ss = __USER32_DS; - set_fs(USER_DS); - regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); - -#if DEBUG_SIG - printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n", - current->comm, current->pid, frame, regs->ip, frame->pretcode); -#endif - return 0; - -give_sigsegv: - force_sigsegv(sig, current); - return -EFAULT; } -int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, +int ia32_setup_rt_frame(int sig, struct ksignal *ksig, compat_sigset_t *set, struct pt_regs *regs) { - struct rt_sigframe __user *frame; - struct exec_domain *ed = current_thread_info()->exec_domain; + struct rt_sigframe_ia32 __user *frame; void __user *restorer; int err = 0; + void __user *fpstate = NULL; /* __copy_to_user optimizes that into a single 8 byte store */ static const struct { u8 movl; u32 val; u16 int80; - u16 pad; - u8 pad2; + u8 pad; } __attribute__((packed)) code = { 0xb8, __NR_ia32_rt_sigreturn, @@ -538,80 +441,60 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, 0, }; - frame = get_sigframe(ka, regs, sizeof(*frame)); + frame = get_sigframe(ksig, regs, sizeof(*frame), &fpstate); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - goto give_sigsegv; + return -EFAULT; - err |= __put_user((ed && ed->signal_invmap && sig < 32 - ? ed->signal_invmap[sig] : sig), &frame->sig); - err |= __put_user(ptr_to_compat(&frame->info), &frame->pinfo); - err |= __put_user(ptr_to_compat(&frame->uc), &frame->puc); - err |= copy_siginfo_to_user32(&frame->info, info); - if (err) - goto give_sigsegv; - - /* Create the ucontext. */ - err |= __put_user(0, &frame->uc.uc_flags); - err |= __put_user(0, &frame->uc.uc_link); - err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(regs->sp), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate, + put_user_try { + put_user_ex(sig, &frame->sig); + put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo); + put_user_ex(ptr_to_compat(&frame->uc), &frame->puc); + + /* Create the ucontext. */ + if (cpu_has_xsave) + put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags); + else + put_user_ex(0, &frame->uc.uc_flags); + put_user_ex(0, &frame->uc.uc_link); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); + + if (ksig->ka.sa.sa_flags & SA_RESTORER) + restorer = ksig->ka.sa.sa_restorer; + else + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_rt_sigreturn; + put_user_ex(ptr_to_compat(restorer), &frame->pretcode); + + /* + * Not actually used anymore, but left because some gdb + * versions need it. + */ + put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode); + } put_user_catch(err); + + err |= copy_siginfo_to_user32(&frame->info, &ksig->info); + err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate, regs, set->sig[0]); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) - goto give_sigsegv; - - if (ka->sa.sa_flags & SA_RESTORER) - restorer = ka->sa.sa_restorer; - else - restorer = VDSO32_SYMBOL(current->mm->context.vdso, - rt_sigreturn); - err |= __put_user(ptr_to_compat(restorer), &frame->pretcode); - - /* - * Not actually used anymore, but left because some gdb - * versions need it. - */ - err |= __copy_to_user(frame->retcode, &code, 8); - if (err) - goto give_sigsegv; + return -EFAULT; /* Set up registers for signal handler */ regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ka->sa.sa_handler; + regs->ip = (unsigned long) ksig->ka.sa.sa_handler; /* Make -mregparm=3 work */ regs->ax = sig; regs->dx = (unsigned long) &frame->info; regs->cx = (unsigned long) &frame->uc; - /* Make -mregparm=3 work */ - regs->ax = sig; - regs->dx = (unsigned long) &frame->info; - regs->cx = (unsigned long) &frame->uc; - - asm volatile("movl %0,%%ds" :: "r" (__USER32_DS)); - asm volatile("movl %0,%%es" :: "r" (__USER32_DS)); + loadsegment(ds, __USER32_DS); + loadsegment(es, __USER32_DS); regs->cs = __USER32_CS; regs->ss = __USER32_DS; - set_fs(USER_DS); - regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF); - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); - -#if DEBUG_SIG - printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n", - current->comm, current->pid, frame, regs->ip, frame->pretcode); -#endif - return 0; - -give_sigsegv: - force_sigsegv(sig, current); - return -EFAULT; } diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 8022d3c695c..4299eb05023 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -13,9 +13,22 @@ #include <asm/thread_info.h> #include <asm/segment.h> #include <asm/irqflags.h> +#include <asm/asm.h> +#include <asm/smap.h> #include <linux/linkage.h> +#include <linux/err.h> -#define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) +/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ +#include <linux/elf-em.h> +#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_LE 0x40000000 + +#ifndef CONFIG_AUDITSYSCALL +#define sysexit_audit ia32_ret_from_sys_call +#define sysretl_audit ia32_ret_from_sys_call +#endif + + .section .entry.text, "ax" .macro IA32_ARG_FIXUP noebp=0 movl %edi,%r8d @@ -29,24 +42,33 @@ .endm /* clobbers %eax */ - .macro CLEAR_RREGS + .macro CLEAR_RREGS offset=0, _r9=rax xorl %eax,%eax - movq %rax,R11(%rsp) - movq %rax,R10(%rsp) - movq %rax,R9(%rsp) - movq %rax,R8(%rsp) + movq %rax,\offset+R11(%rsp) + movq %rax,\offset+R10(%rsp) + movq %\_r9,\offset+R9(%rsp) + movq %rax,\offset+R8(%rsp) .endm - .macro LOAD_ARGS32 offset - movl \offset(%rsp),%r11d - movl \offset+8(%rsp),%r10d + /* + * Reload arg registers from stack in case ptrace changed them. + * We don't reload %eax because syscall_trace_enter() returned + * the %rax value we should see. Instead, we just truncate that + * value to 32 bits again as we did on entry from user mode. + * If it's a new value set by user_regset during entry tracing, + * this matches the normal truncation of the user-mode value. + * If it's -1 to make us punt the syscall, then (u32)-1 is still + * an appropriately invalid value. + */ + .macro LOAD_ARGS32 offset, _r9=0 + .if \_r9 movl \offset+16(%rsp),%r9d - movl \offset+24(%rsp),%r8d + .endif movl \offset+40(%rsp),%ecx movl \offset+48(%rsp),%edx movl \offset+56(%rsp),%esi movl \offset+64(%rsp),%edi - movl \offset+72(%rsp),%eax + movl %eax,%eax /* zero extension */ .endm .macro CFI_STARTPROC32 simple @@ -61,6 +83,19 @@ CFI_UNDEFINED r15 .endm +#ifdef CONFIG_PARAVIRT +ENTRY(native_usergs_sysret32) + swapgs + sysretl +ENDPROC(native_usergs_sysret32) + +ENTRY(native_irq_enable_sysexit) + swapgs + sti + sysexit +ENDPROC(native_irq_enable_sysexit) +#endif + /* * 32bit SYSENTER instruction entry. * @@ -85,89 +120,135 @@ ENTRY(ia32_sysenter_target) CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,0 CFI_REGISTER rsp,rbp - swapgs - movq %gs:pda_kernelstack, %rsp - addq $(PDA_STACKOFFSET),%rsp + SWAPGS_UNSAFE_STACK + movq PER_CPU_VAR(kernel_stack), %rsp + addq $(KERNEL_STACK_OFFSET),%rsp /* * No need to follow this irqs on/off section: the syscall * disabled irqs, here we enable it straight after entry: */ - sti + ENABLE_INTERRUPTS(CLBR_NONE) movl %ebp,%ebp /* zero extension */ - pushq $__USER32_DS - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $__USER32_DS /*CFI_REL_OFFSET ss,0*/ - pushq %rbp - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rbp CFI_REL_OFFSET rsp,0 - pushfq - CFI_ADJUST_CFA_OFFSET 8 + pushfq_cfi /*CFI_REL_OFFSET rflags,0*/ - movl 8*3-THREAD_SIZE+threadinfo_sysenter_return(%rsp), %r10d + movl TI_sysenter_return+THREAD_INFO(%rsp,3*8-KERNEL_STACK_OFFSET),%r10d CFI_REGISTER rip,r10 - pushq $__USER32_CS - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $__USER32_CS /*CFI_REL_OFFSET cs,0*/ movl %eax, %eax - pushq %r10 - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %r10 CFI_REL_OFFSET rip,0 - pushq %rax - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rax cld - SAVE_ARGS 0,0,1 + SAVE_ARGS 0,1,0 /* no need to do an access_ok check here because rbp has been 32bit zero extended */ -1: movl (%rbp),%r9d - .section __ex_table,"a" - .quad 1b,ia32_badarg - .previous - GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + ASM_STAC +1: movl (%rbp),%ebp + _ASM_EXTABLE(1b,ia32_badarg) + ASM_CLAC + orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE jnz sysenter_tracesys -sysenter_do_call: - cmpl $(IA32_NR_syscalls-1),%eax + cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys - IA32_ARG_FIXUP 1 +sysenter_do_call: + IA32_ARG_FIXUP +sysenter_dispatch: call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) - GET_THREAD_INFO(%r10) - cli + DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) - jnz int_ret_from_sys_call - andl $~TS_COMPAT,threadinfo_status(%r10) + testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + jnz sysexit_audit +sysexit_from_sys_call: + andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) /* clear IF, that popfq doesn't enable interrupts early */ andl $~0x200,EFLAGS-R11(%rsp) movl RIP-R11(%rsp),%edx /* User %eip */ CFI_REGISTER rip,rdx - RESTORE_ARGS 1,24,1,1,1,1 - popfq - CFI_ADJUST_CFA_OFFSET -8 + RESTORE_ARGS 0,24,0,0,0,0 + xorq %r8,%r8 + xorq %r9,%r9 + xorq %r10,%r10 + xorq %r11,%r11 + popfq_cfi /*CFI_RESTORE rflags*/ - popq %rcx /* User %esp */ - CFI_ADJUST_CFA_OFFSET -8 + popq_cfi %rcx /* User %esp */ CFI_REGISTER rsp,rcx TRACE_IRQS_ON - swapgs - sti /* sti only takes effect after the next instruction */ - /* sysexit */ - .byte 0xf, 0x35 + ENABLE_INTERRUPTS_SYSEXIT32 -sysenter_tracesys: +#ifdef CONFIG_AUDITSYSCALL + .macro auditsys_entry_common + movl %esi,%r9d /* 6th arg: 4th syscall arg */ + movl %edx,%r8d /* 5th arg: 3rd syscall arg */ + /* (already in %ecx) 4th arg: 2nd syscall arg */ + movl %ebx,%edx /* 3rd arg: 1st syscall arg */ + movl %eax,%esi /* 2nd arg: syscall number */ + movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */ + call __audit_syscall_entry + movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */ + cmpq $(IA32_NR_syscalls-1),%rax + ja ia32_badsys + movl %ebx,%edi /* reload 1st syscall arg */ + movl RCX-ARGOFFSET(%rsp),%esi /* reload 2nd syscall arg */ + movl RDX-ARGOFFSET(%rsp),%edx /* reload 3rd syscall arg */ + movl RSI-ARGOFFSET(%rsp),%ecx /* reload 4th syscall arg */ + movl RDI-ARGOFFSET(%rsp),%r8d /* reload 5th syscall arg */ + .endm + + .macro auditsys_exit exit + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + jnz ia32_ret_from_sys_call + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + movl %eax,%esi /* second arg, syscall return value */ + cmpl $-MAX_ERRNO,%eax /* is it an error ? */ + jbe 1f + movslq %eax, %rsi /* if error sign extend to 64 bits */ +1: setbe %al /* 1 if error, 0 if not */ + movzbl %al,%edi /* zero-extend that into %edi */ + call __audit_syscall_exit + movq RAX-ARGOFFSET(%rsp),%rax /* reload syscall return value */ + movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + testl %edi,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + jz \exit + CLEAR_RREGS -ARGOFFSET + jmp int_with_check + .endm + +sysenter_auditsys: CFI_RESTORE_STATE - xchgl %r9d,%ebp + auditsys_entry_common + movl %ebp,%r9d /* reload 6th syscall arg */ + jmp sysenter_dispatch + +sysexit_audit: + auditsys_exit sysexit_from_sys_call +#endif + +sysenter_tracesys: +#ifdef CONFIG_AUDITSYSCALL + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + jz sysenter_auditsys +#endif SAVE_REST CLEAR_RREGS - movq %r9,R9(%rsp) - movq $-ENOSYS,RAX(%rsp) /* really needed? */ + movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST - xchgl %ebp,%r9d + cmpq $(IA32_NR_syscalls-1),%rax + ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */ jmp sysenter_do_call CFI_ENDPROC ENDPROC(ia32_sysenter_target) @@ -195,19 +276,19 @@ ENDPROC(ia32_sysenter_target) ENTRY(ia32_cstar_target) CFI_STARTPROC32 simple CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,PDA_STACKOFFSET + CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET CFI_REGISTER rip,rcx /*CFI_REGISTER rflags,r11*/ - swapgs + SWAPGS_UNSAFE_STACK movl %esp,%r8d CFI_REGISTER rsp,r8 - movq %gs:pda_kernelstack,%rsp + movq PER_CPU_VAR(kernel_stack),%rsp /* * No need to follow this irqs on/off section: the syscall * disabled irqs and here we enable it straight after entry: */ - sti - SAVE_ARGS 8,1,1 + ENABLE_INTERRUPTS(CLBR_NONE) + SAVE_ARGS 8,0,0 movl %eax,%eax /* zero extension */ movq %rax,ORIG_RAX-ARGOFFSET(%rsp) movq %rcx,RIP-ARGOFFSET(%rsp) @@ -223,55 +304,73 @@ ENTRY(ia32_cstar_target) /* no need to do an access_ok check here because r8 has been 32bit zero extended */ /* hardware stack frame is complete now */ + ASM_STAC 1: movl (%r8),%r9d - .section __ex_table,"a" - .quad 1b,ia32_badarg - .previous - GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + _ASM_EXTABLE(1b,ia32_badarg) + ASM_CLAC + orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE jnz cstar_tracesys -cstar_do_call: - cmpl $IA32_NR_syscalls-1,%eax + cmpq $IA32_NR_syscalls-1,%rax ja ia32_badsys +cstar_do_call: IA32_ARG_FIXUP 1 +cstar_dispatch: call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) - GET_THREAD_INFO(%r10) - cli + DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) - jnz int_ret_from_sys_call - andl $~TS_COMPAT,threadinfo_status(%r10) - RESTORE_ARGS 1,-ARG_SKIP,1,1,1 + testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + jnz sysretl_audit +sysretl_from_sys_call: + andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) + RESTORE_ARGS 0,-ARG_SKIP,0,0,0 movl RIP-ARGOFFSET(%rsp),%ecx CFI_REGISTER rip,rcx movl EFLAGS-ARGOFFSET(%rsp),%r11d /*CFI_REGISTER rflags,r11*/ + xorq %r10,%r10 + xorq %r9,%r9 + xorq %r8,%r8 TRACE_IRQS_ON movl RSP-ARGOFFSET(%rsp),%esp CFI_RESTORE rsp - swapgs - sysretl + USERGS_SYSRET32 -cstar_tracesys: +#ifdef CONFIG_AUDITSYSCALL +cstar_auditsys: CFI_RESTORE_STATE + movl %r9d,R9-ARGOFFSET(%rsp) /* register to be clobbered by call */ + auditsys_entry_common + movl R9-ARGOFFSET(%rsp),%r9d /* reload 6th syscall arg */ + jmp cstar_dispatch + +sysretl_audit: + auditsys_exit sysretl_from_sys_call +#endif + +cstar_tracesys: +#ifdef CONFIG_AUDITSYSCALL + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + jz cstar_auditsys +#endif xchgl %r9d,%ebp SAVE_REST - CLEAR_RREGS - movq %r9,R9(%rsp) - movq $-ENOSYS,RAX(%rsp) /* really needed? */ + CLEAR_RREGS 0, r9 + movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter - LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ + LOAD_ARGS32 ARGOFFSET, 1 /* reload args from stack in case ptrace changed it */ RESTORE_REST xchgl %ebp,%r9d - movl RSP-ARGOFFSET(%rsp), %r8d + cmpq $(IA32_NR_syscalls-1),%rax + ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */ jmp cstar_do_call END(ia32_cstar_target) ia32_badarg: + ASM_CLAC movq $-EFAULT,%rax jmp ia32_sysret CFI_ENDPROC @@ -306,75 +405,76 @@ ENTRY(ia32_syscall) /*CFI_REL_OFFSET rflags,EFLAGS-RIP*/ /*CFI_REL_OFFSET cs,CS-RIP*/ CFI_REL_OFFSET rip,RIP-RIP - swapgs + PARAVIRT_ADJUST_EXCEPTION_FRAME + SWAPGS /* * No need to follow this irqs on/off section: the syscall * disabled irqs and here we enable it straight after entry: */ - sti + ENABLE_INTERRUPTS(CLBR_NONE) movl %eax,%eax - pushq %rax - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rax cld /* note the registers are not zero extended to the sf. this could be a problem. */ - SAVE_ARGS 0,0,1 - GET_THREAD_INFO(%r10) - orl $TS_COMPAT,threadinfo_status(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + SAVE_ARGS 0,1,0 + orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) jnz ia32_tracesys -ia32_do_syscall: - cmpl $(IA32_NR_syscalls-1),%eax - ja ia32_badsys + cmpq $(IA32_NR_syscalls-1),%rax + ja ia32_badsys +ia32_do_call: IA32_ARG_FIXUP call *ia32_sys_call_table(,%rax,8) # xxx: rip relative ia32_sysret: movq %rax,RAX-ARGOFFSET(%rsp) +ia32_ret_from_sys_call: + CLEAR_RREGS -ARGOFFSET jmp int_ret_from_sys_call ia32_tracesys: SAVE_REST CLEAR_RREGS - movq $-ENOSYS,RAX(%rsp) /* really needed? */ + movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST - jmp ia32_do_syscall + cmpq $(IA32_NR_syscalls-1),%rax + ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */ + jmp ia32_do_call END(ia32_syscall) ia32_badsys: movq $0,ORIG_RAX-ARGOFFSET(%rsp) - movq $-ENOSYS,RAX-ARGOFFSET(%rsp) - jmp int_ret_from_sys_call - -quiet_ni_syscall: movq $-ENOSYS,%rax - ret + jmp ia32_sysret + CFI_ENDPROC - .macro PTREGSCALL label, func, arg - .globl \label -\label: + .macro PTREGSCALL label, func + ALIGN +GLOBAL(\label) leaq \func(%rip),%rax - leaq -ARGOFFSET+8(%rsp),\arg /* 8 for return address */ jmp ia32_ptregs_common .endm CFI_STARTPROC32 - PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi - PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi - PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx - PTREGSCALL stub32_sigsuspend, sys32_sigsuspend, %rcx - PTREGSCALL stub32_execve, sys32_execve, %rcx - PTREGSCALL stub32_fork, sys_fork, %rdi - PTREGSCALL stub32_clone, sys32_clone, %rdx - PTREGSCALL stub32_vfork, sys_vfork, %rdi - PTREGSCALL stub32_iopl, sys_iopl, %rsi - PTREGSCALL stub32_rt_sigsuspend, sys_rt_sigsuspend, %rdx + PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn + PTREGSCALL stub32_sigreturn, sys32_sigreturn + PTREGSCALL stub32_execve, compat_sys_execve + PTREGSCALL stub32_fork, sys_fork + PTREGSCALL stub32_vfork, sys_vfork -ENTRY(ia32_ptregs_common) + ALIGN +GLOBAL(stub32_clone) + leaq sys_clone(%rip),%rax + mov %r8, %rcx + jmp ia32_ptregs_common + + ALIGN +ia32_ptregs_common: popq %r11 CFI_ENDPROC CFI_STARTPROC32 simple @@ -396,335 +496,3 @@ ENTRY(ia32_ptregs_common) jmp ia32_sysret /* misbalances the return cache */ CFI_ENDPROC END(ia32_ptregs_common) - - .section .rodata,"a" - .align 8 -ia32_sys_call_table: - .quad sys_restart_syscall - .quad sys_exit - .quad stub32_fork - .quad sys_read - .quad sys_write - .quad compat_sys_open /* 5 */ - .quad sys_close - .quad sys32_waitpid - .quad sys_creat - .quad sys_link - .quad sys_unlink /* 10 */ - .quad stub32_execve - .quad sys_chdir - .quad compat_sys_time - .quad sys_mknod - .quad sys_chmod /* 15 */ - .quad sys_lchown16 - .quad quiet_ni_syscall /* old break syscall holder */ - .quad sys_stat - .quad sys32_lseek - .quad sys_getpid /* 20 */ - .quad compat_sys_mount /* mount */ - .quad sys_oldumount /* old_umount */ - .quad sys_setuid16 - .quad sys_getuid16 - .quad compat_sys_stime /* stime */ /* 25 */ - .quad sys32_ptrace /* ptrace */ - .quad sys_alarm - .quad sys_fstat /* (old)fstat */ - .quad sys_pause - .quad compat_sys_utime /* 30 */ - .quad quiet_ni_syscall /* old stty syscall holder */ - .quad quiet_ni_syscall /* old gtty syscall holder */ - .quad sys_access - .quad sys_nice - .quad quiet_ni_syscall /* 35 */ /* old ftime syscall holder */ - .quad sys_sync - .quad sys32_kill - .quad sys_rename - .quad sys_mkdir - .quad sys_rmdir /* 40 */ - .quad sys_dup - .quad sys32_pipe - .quad compat_sys_times - .quad quiet_ni_syscall /* old prof syscall holder */ - .quad sys_brk /* 45 */ - .quad sys_setgid16 - .quad sys_getgid16 - .quad sys_signal - .quad sys_geteuid16 - .quad sys_getegid16 /* 50 */ - .quad sys_acct - .quad sys_umount /* new_umount */ - .quad quiet_ni_syscall /* old lock syscall holder */ - .quad compat_sys_ioctl - .quad compat_sys_fcntl64 /* 55 */ - .quad quiet_ni_syscall /* old mpx syscall holder */ - .quad sys_setpgid - .quad quiet_ni_syscall /* old ulimit syscall holder */ - .quad sys32_olduname - .quad sys_umask /* 60 */ - .quad sys_chroot - .quad sys32_ustat - .quad sys_dup2 - .quad sys_getppid - .quad sys_getpgrp /* 65 */ - .quad sys_setsid - .quad sys32_sigaction - .quad sys_sgetmask - .quad sys_ssetmask - .quad sys_setreuid16 /* 70 */ - .quad sys_setregid16 - .quad stub32_sigsuspend - .quad compat_sys_sigpending - .quad sys_sethostname - .quad compat_sys_setrlimit /* 75 */ - .quad compat_sys_old_getrlimit /* old_getrlimit */ - .quad compat_sys_getrusage - .quad sys32_gettimeofday - .quad sys32_settimeofday - .quad sys_getgroups16 /* 80 */ - .quad sys_setgroups16 - .quad sys32_old_select - .quad sys_symlink - .quad sys_lstat - .quad sys_readlink /* 85 */ - .quad sys_uselib - .quad sys_swapon - .quad sys_reboot - .quad compat_sys_old_readdir - .quad sys32_mmap /* 90 */ - .quad sys_munmap - .quad sys_truncate - .quad sys_ftruncate - .quad sys_fchmod - .quad sys_fchown16 /* 95 */ - .quad sys_getpriority - .quad sys_setpriority - .quad quiet_ni_syscall /* old profil syscall holder */ - .quad compat_sys_statfs - .quad compat_sys_fstatfs /* 100 */ - .quad sys_ioperm - .quad compat_sys_socketcall - .quad sys_syslog - .quad compat_sys_setitimer - .quad compat_sys_getitimer /* 105 */ - .quad compat_sys_newstat - .quad compat_sys_newlstat - .quad compat_sys_newfstat - .quad sys32_uname - .quad stub32_iopl /* 110 */ - .quad sys_vhangup - .quad quiet_ni_syscall /* old "idle" system call */ - .quad sys32_vm86_warning /* vm86old */ - .quad compat_sys_wait4 - .quad sys_swapoff /* 115 */ - .quad compat_sys_sysinfo - .quad sys32_ipc - .quad sys_fsync - .quad stub32_sigreturn - .quad stub32_clone /* 120 */ - .quad sys_setdomainname - .quad sys_uname - .quad sys_modify_ldt - .quad compat_sys_adjtimex - .quad sys32_mprotect /* 125 */ - .quad compat_sys_sigprocmask - .quad quiet_ni_syscall /* create_module */ - .quad sys_init_module - .quad sys_delete_module - .quad quiet_ni_syscall /* 130 get_kernel_syms */ - .quad sys32_quotactl - .quad sys_getpgid - .quad sys_fchdir - .quad quiet_ni_syscall /* bdflush */ - .quad sys_sysfs /* 135 */ - .quad sys_personality - .quad quiet_ni_syscall /* for afs_syscall */ - .quad sys_setfsuid16 - .quad sys_setfsgid16 - .quad sys_llseek /* 140 */ - .quad compat_sys_getdents - .quad compat_sys_select - .quad sys_flock - .quad sys_msync - .quad compat_sys_readv /* 145 */ - .quad compat_sys_writev - .quad sys_getsid - .quad sys_fdatasync - .quad sys32_sysctl /* sysctl */ - .quad sys_mlock /* 150 */ - .quad sys_munlock - .quad sys_mlockall - .quad sys_munlockall - .quad sys_sched_setparam - .quad sys_sched_getparam /* 155 */ - .quad sys_sched_setscheduler - .quad sys_sched_getscheduler - .quad sys_sched_yield - .quad sys_sched_get_priority_max - .quad sys_sched_get_priority_min /* 160 */ - .quad sys32_sched_rr_get_interval - .quad compat_sys_nanosleep - .quad sys_mremap - .quad sys_setresuid16 - .quad sys_getresuid16 /* 165 */ - .quad sys32_vm86_warning /* vm86 */ - .quad quiet_ni_syscall /* query_module */ - .quad sys_poll - .quad compat_sys_nfsservctl - .quad sys_setresgid16 /* 170 */ - .quad sys_getresgid16 - .quad sys_prctl - .quad stub32_rt_sigreturn - .quad sys32_rt_sigaction - .quad sys32_rt_sigprocmask /* 175 */ - .quad sys32_rt_sigpending - .quad compat_sys_rt_sigtimedwait - .quad sys32_rt_sigqueueinfo - .quad stub32_rt_sigsuspend - .quad sys32_pread /* 180 */ - .quad sys32_pwrite - .quad sys_chown16 - .quad sys_getcwd - .quad sys_capget - .quad sys_capset - .quad stub32_sigaltstack - .quad sys32_sendfile - .quad quiet_ni_syscall /* streams1 */ - .quad quiet_ni_syscall /* streams2 */ - .quad stub32_vfork /* 190 */ - .quad compat_sys_getrlimit - .quad sys32_mmap2 - .quad sys32_truncate64 - .quad sys32_ftruncate64 - .quad sys32_stat64 /* 195 */ - .quad sys32_lstat64 - .quad sys32_fstat64 - .quad sys_lchown - .quad sys_getuid - .quad sys_getgid /* 200 */ - .quad sys_geteuid - .quad sys_getegid - .quad sys_setreuid - .quad sys_setregid - .quad sys_getgroups /* 205 */ - .quad sys_setgroups - .quad sys_fchown - .quad sys_setresuid - .quad sys_getresuid - .quad sys_setresgid /* 210 */ - .quad sys_getresgid - .quad sys_chown - .quad sys_setuid - .quad sys_setgid - .quad sys_setfsuid /* 215 */ - .quad sys_setfsgid - .quad sys_pivot_root - .quad sys_mincore - .quad sys_madvise - .quad compat_sys_getdents64 /* 220 getdents64 */ - .quad compat_sys_fcntl64 - .quad quiet_ni_syscall /* tux */ - .quad quiet_ni_syscall /* security */ - .quad sys_gettid - .quad sys32_readahead /* 225 */ - .quad sys_setxattr - .quad sys_lsetxattr - .quad sys_fsetxattr - .quad sys_getxattr - .quad sys_lgetxattr /* 230 */ - .quad sys_fgetxattr - .quad sys_listxattr - .quad sys_llistxattr - .quad sys_flistxattr - .quad sys_removexattr /* 235 */ - .quad sys_lremovexattr - .quad sys_fremovexattr - .quad sys_tkill - .quad sys_sendfile64 - .quad compat_sys_futex /* 240 */ - .quad compat_sys_sched_setaffinity - .quad compat_sys_sched_getaffinity - .quad sys_set_thread_area - .quad sys_get_thread_area - .quad compat_sys_io_setup /* 245 */ - .quad sys_io_destroy - .quad compat_sys_io_getevents - .quad compat_sys_io_submit - .quad sys_io_cancel - .quad sys32_fadvise64 /* 250 */ - .quad quiet_ni_syscall /* free_huge_pages */ - .quad sys_exit_group - .quad sys32_lookup_dcookie - .quad sys_epoll_create - .quad sys_epoll_ctl /* 255 */ - .quad sys_epoll_wait - .quad sys_remap_file_pages - .quad sys_set_tid_address - .quad compat_sys_timer_create - .quad compat_sys_timer_settime /* 260 */ - .quad compat_sys_timer_gettime - .quad sys_timer_getoverrun - .quad sys_timer_delete - .quad compat_sys_clock_settime - .quad compat_sys_clock_gettime /* 265 */ - .quad compat_sys_clock_getres - .quad compat_sys_clock_nanosleep - .quad compat_sys_statfs64 - .quad compat_sys_fstatfs64 - .quad sys_tgkill /* 270 */ - .quad compat_sys_utimes - .quad sys32_fadvise64_64 - .quad quiet_ni_syscall /* sys_vserver */ - .quad sys_mbind - .quad compat_sys_get_mempolicy /* 275 */ - .quad sys_set_mempolicy - .quad compat_sys_mq_open - .quad sys_mq_unlink - .quad compat_sys_mq_timedsend - .quad compat_sys_mq_timedreceive /* 280 */ - .quad compat_sys_mq_notify - .quad compat_sys_mq_getsetattr - .quad compat_sys_kexec_load /* reserved for kexec */ - .quad compat_sys_waitid - .quad quiet_ni_syscall /* 285: sys_altroot */ - .quad sys_add_key - .quad sys_request_key - .quad sys_keyctl - .quad sys_ioprio_set - .quad sys_ioprio_get /* 290 */ - .quad sys_inotify_init - .quad sys_inotify_add_watch - .quad sys_inotify_rm_watch - .quad sys_migrate_pages - .quad compat_sys_openat /* 295 */ - .quad sys_mkdirat - .quad sys_mknodat - .quad sys_fchownat - .quad compat_sys_futimesat - .quad sys32_fstatat /* 300 */ - .quad sys_unlinkat - .quad sys_renameat - .quad sys_linkat - .quad sys_symlinkat - .quad sys_readlinkat /* 305 */ - .quad sys_fchmodat - .quad sys_faccessat - .quad compat_sys_pselect6 - .quad compat_sys_ppoll - .quad sys_unshare /* 310 */ - .quad compat_sys_set_robust_list - .quad compat_sys_get_robust_list - .quad sys_splice - .quad sys32_sync_file_range - .quad sys_tee /* 315 */ - .quad compat_sys_vmsplice - .quad compat_sys_move_pages - .quad sys_getcpu - .quad sys_epoll_pwait - .quad compat_sys_utimensat /* 320 */ - .quad compat_sys_signalfd - .quad sys_timerfd_create - .quad sys_eventfd - .quad sys32_fallocate - .quad compat_sys_timerfd_settime /* 325 */ - .quad compat_sys_timerfd_gettime -ia32_syscall_end: diff --git a/arch/x86/ia32/ipc32.c b/arch/x86/ia32/ipc32.c deleted file mode 100644 index d21991ce606..00000000000 --- a/arch/x86/ia32/ipc32.c +++ /dev/null @@ -1,53 +0,0 @@ -#include <linux/kernel.h> -#include <linux/spinlock.h> -#include <linux/list.h> -#include <linux/syscalls.h> -#include <linux/time.h> -#include <linux/sem.h> -#include <linux/msg.h> -#include <linux/shm.h> -#include <linux/ipc.h> -#include <linux/compat.h> - -asmlinkage long sys32_ipc(u32 call, int first, int second, int third, - compat_uptr_t ptr, u32 fifth) -{ - int version; - - version = call >> 16; /* hack for backward compatibility */ - call &= 0xffff; - - switch (call) { - case SEMOP: - /* struct sembuf is the same on 32 and 64bit :)) */ - return sys_semtimedop(first, compat_ptr(ptr), second, NULL); - case SEMTIMEDOP: - return compat_sys_semtimedop(first, compat_ptr(ptr), second, - compat_ptr(fifth)); - case SEMGET: - return sys_semget(first, second, third); - case SEMCTL: - return compat_sys_semctl(first, second, third, compat_ptr(ptr)); - - case MSGSND: - return compat_sys_msgsnd(first, second, third, compat_ptr(ptr)); - case MSGRCV: - return compat_sys_msgrcv(first, second, fifth, third, - version, compat_ptr(ptr)); - case MSGGET: - return sys_msgget((key_t) first, second); - case MSGCTL: - return compat_sys_msgctl(first, second, compat_ptr(ptr)); - - case SHMAT: - return compat_sys_shmat(first, second, third, version, - compat_ptr(ptr)); - case SHMDT: - return sys_shmdt(compat_ptr(ptr)); - case SHMGET: - return sys_shmget(first, (unsigned)second, third); - case SHMCTL: - return compat_sys_shmctl(first, second, compat_ptr(ptr)); - } - return -ENOSYS; -} diff --git a/arch/x86/ia32/nosyscall.c b/arch/x86/ia32/nosyscall.c new file mode 100644 index 00000000000..51ecd5b4e78 --- /dev/null +++ b/arch/x86/ia32/nosyscall.c @@ -0,0 +1,7 @@ +#include <linux/kernel.h> +#include <linux/errno.h> + +long compat_ni_syscall(void) +{ + return -ENOSYS; +} diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index abf71d26fc2..8e0ceecdc95 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -26,91 +26,31 @@ #include <linux/file.h> #include <linux/signal.h> #include <linux/syscalls.h> -#include <linux/resource.h> #include <linux/times.h> #include <linux/utsname.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/sem.h> -#include <linux/msg.h> #include <linux/mm.h> -#include <linux/shm.h> -#include <linux/slab.h> #include <linux/uio.h> -#include <linux/nfs_fs.h> -#include <linux/quota.h> -#include <linux/module.h> -#include <linux/sunrpc/svc.h> -#include <linux/nfsd/nfsd.h> -#include <linux/nfsd/cache.h> -#include <linux/nfsd/xdr.h> -#include <linux/nfsd/syscall.h> #include <linux/poll.h> #include <linux/personality.h> #include <linux/stat.h> -#include <linux/ipc.h> #include <linux/rwsem.h> -#include <linux/binfmts.h> -#include <linux/init.h> -#include <linux/aio_abi.h> -#include <linux/aio.h> #include <linux/compat.h> #include <linux/vfs.h> #include <linux/ptrace.h> #include <linux/highuid.h> -#include <linux/vmalloc.h> -#include <linux/fsnotify.h> #include <linux/sysctl.h> +#include <linux/slab.h> #include <asm/mman.h> #include <asm/types.h> #include <asm/uaccess.h> -#include <asm/semaphore.h> -#include <asm/atomic.h> -#include <asm/ldt.h> - -#include <net/scm.h> -#include <net/sock.h> -#include <asm/ia32.h> +#include <linux/atomic.h> +#include <asm/vgtod.h> +#include <asm/sys_ia32.h> #define AA(__x) ((unsigned long)(__x)) -int cp_compat_stat(struct kstat *kbuf, struct compat_stat __user *ubuf) -{ - compat_ino_t ino; - typeof(ubuf->st_uid) uid = 0; - typeof(ubuf->st_gid) gid = 0; - SET_UID(uid, kbuf->uid); - SET_GID(gid, kbuf->gid); - if (!old_valid_dev(kbuf->dev) || !old_valid_dev(kbuf->rdev)) - return -EOVERFLOW; - if (kbuf->size >= 0x7fffffff) - return -EOVERFLOW; - ino = kbuf->ino; - if (sizeof(ino) < sizeof(kbuf->ino) && ino != kbuf->ino) - return -EOVERFLOW; - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct compat_stat)) || - __put_user(old_encode_dev(kbuf->dev), &ubuf->st_dev) || - __put_user(ino, &ubuf->st_ino) || - __put_user(kbuf->mode, &ubuf->st_mode) || - __put_user(kbuf->nlink, &ubuf->st_nlink) || - __put_user(uid, &ubuf->st_uid) || - __put_user(gid, &ubuf->st_gid) || - __put_user(old_encode_dev(kbuf->rdev), &ubuf->st_rdev) || - __put_user(kbuf->size, &ubuf->st_size) || - __put_user(kbuf->atime.tv_sec, &ubuf->st_atime) || - __put_user(kbuf->atime.tv_nsec, &ubuf->st_atime_nsec) || - __put_user(kbuf->mtime.tv_sec, &ubuf->st_mtime) || - __put_user(kbuf->mtime.tv_nsec, &ubuf->st_mtime_nsec) || - __put_user(kbuf->ctime.tv_sec, &ubuf->st_ctime) || - __put_user(kbuf->ctime.tv_nsec, &ubuf->st_ctime_nsec) || - __put_user(kbuf->blksize, &ubuf->st_blksize) || - __put_user(kbuf->blocks, &ubuf->st_blocks)) - return -EFAULT; - return 0; -} - -asmlinkage long sys32_truncate64(char __user *filename, +asmlinkage long sys32_truncate64(const char __user *filename, unsigned long offset_low, unsigned long offset_high) { @@ -131,8 +71,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) { typeof(ubuf->st_uid) uid = 0; typeof(ubuf->st_gid) gid = 0; - SET_UID(uid, stat->uid); - SET_GID(gid, stat->gid); + SET_UID(uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(gid, from_kgid_munged(current_user_ns(), stat->gid)); if (!access_ok(VERIFY_WRITE, ubuf, sizeof(struct stat64)) || __put_user(huge_encode_dev(stat->dev), &ubuf->st_dev) || __put_user(stat->ino, &ubuf->__st_ino) || @@ -155,7 +95,7 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) return 0; } -asmlinkage long sys32_stat64(char __user *filename, +asmlinkage long sys32_stat64(const char __user *filename, struct stat64 __user *statbuf) { struct kstat stat; @@ -166,7 +106,7 @@ asmlinkage long sys32_stat64(char __user *filename, return ret; } -asmlinkage long sys32_lstat64(char __user *filename, +asmlinkage long sys32_lstat64(const char __user *filename, struct stat64 __user *statbuf) { struct kstat stat; @@ -185,25 +125,16 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) return ret; } -asmlinkage long sys32_fstatat(unsigned int dfd, char __user *filename, +asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename, struct stat64 __user *statbuf, int flag) { struct kstat stat; - int error = -EINVAL; - - if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0) - goto out; + int error; - if (flag & AT_SYMLINK_NOFOLLOW) - error = vfs_lstat_fd(dfd, filename, &stat); - else - error = vfs_stat_fd(dfd, filename, &stat); - - if (!error) - error = cp_stat64(statbuf, &stat); - -out: - return error; + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_stat64(statbuf, &stat); } /* @@ -212,7 +143,7 @@ out: * block for parameter passing.. */ -struct mmap_arg_struct { +struct mmap_arg_struct32 { unsigned int addr; unsigned int len; unsigned int prot; @@ -221,12 +152,9 @@ struct mmap_arg_struct { unsigned int offset; }; -asmlinkage long sys32_mmap(struct mmap_arg_struct __user *arg) +asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) { - struct mmap_arg_struct a; - struct file *file = NULL; - unsigned long retval; - struct mm_struct *mm ; + struct mmap_arg_struct32 a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; @@ -234,418 +162,16 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct __user *arg) if (a.offset & ~PAGE_MASK) return -EINVAL; - if (!(a.flags & MAP_ANONYMOUS)) { - file = fget(a.fd); - if (!file) - return -EBADF; - } - - mm = current->mm; - down_write(&mm->mmap_sem); - retval = do_mmap_pgoff(file, a.addr, a.len, a.prot, a.flags, + return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset>>PAGE_SHIFT); - if (file) - fput(file); - - up_write(&mm->mmap_sem); - - return retval; -} - -asmlinkage long sys32_mprotect(unsigned long start, size_t len, - unsigned long prot) -{ - return sys_mprotect(start, len, prot); -} - -asmlinkage long sys32_pipe(int __user *fd) -{ - int retval; - int fds[2]; - - retval = do_pipe(fds); - if (retval) - goto out; - if (copy_to_user(fd, fds, sizeof(fds))) - retval = -EFAULT; -out: - return retval; -} - -asmlinkage long sys32_rt_sigaction(int sig, struct sigaction32 __user *act, - struct sigaction32 __user *oact, - unsigned int sigsetsize) -{ - struct k_sigaction new_ka, old_ka; - int ret; - compat_sigset_t set32; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(compat_sigset_t)) - return -EINVAL; - - if (act) { - compat_uptr_t handler, restorer; - - if (!access_ok(VERIFY_READ, act, sizeof(*act)) || - __get_user(handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_flags, &act->sa_flags) || - __get_user(restorer, &act->sa_restorer) || - __copy_from_user(&set32, &act->sa_mask, - sizeof(compat_sigset_t))) - return -EFAULT; - new_ka.sa.sa_handler = compat_ptr(handler); - new_ka.sa.sa_restorer = compat_ptr(restorer); - - /* - * FIXME: here we rely on _COMPAT_NSIG_WORS to be >= - * than _NSIG_WORDS << 1 - */ - switch (_NSIG_WORDS) { - case 4: new_ka.sa.sa_mask.sig[3] = set32.sig[6] - | (((long)set32.sig[7]) << 32); - case 3: new_ka.sa.sa_mask.sig[2] = set32.sig[4] - | (((long)set32.sig[5]) << 32); - case 2: new_ka.sa.sa_mask.sig[1] = set32.sig[2] - | (((long)set32.sig[3]) << 32); - case 1: new_ka.sa.sa_mask.sig[0] = set32.sig[0] - | (((long)set32.sig[1]) << 32); - } - } - - ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); - - if (!ret && oact) { - /* - * FIXME: here we rely on _COMPAT_NSIG_WORS to be >= - * than _NSIG_WORDS << 1 - */ - switch (_NSIG_WORDS) { - case 4: - set32.sig[7] = (old_ka.sa.sa_mask.sig[3] >> 32); - set32.sig[6] = old_ka.sa.sa_mask.sig[3]; - case 3: - set32.sig[5] = (old_ka.sa.sa_mask.sig[2] >> 32); - set32.sig[4] = old_ka.sa.sa_mask.sig[2]; - case 2: - set32.sig[3] = (old_ka.sa.sa_mask.sig[1] >> 32); - set32.sig[2] = old_ka.sa.sa_mask.sig[1]; - case 1: - set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32); - set32.sig[0] = old_ka.sa.sa_mask.sig[0]; - } - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || - __put_user(ptr_to_compat(old_ka.sa.sa_handler), - &oact->sa_handler) || - __put_user(ptr_to_compat(old_ka.sa.sa_restorer), - &oact->sa_restorer) || - __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || - __copy_to_user(&oact->sa_mask, &set32, - sizeof(compat_sigset_t))) - return -EFAULT; - } - - return ret; } -asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act, - struct old_sigaction32 __user *oact) -{ - struct k_sigaction new_ka, old_ka; - int ret; - - if (act) { - compat_old_sigset_t mask; - compat_uptr_t handler, restorer; - - if (!access_ok(VERIFY_READ, act, sizeof(*act)) || - __get_user(handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_flags, &act->sa_flags) || - __get_user(restorer, &act->sa_restorer) || - __get_user(mask, &act->sa_mask)) - return -EFAULT; - - new_ka.sa.sa_handler = compat_ptr(handler); - new_ka.sa.sa_restorer = compat_ptr(restorer); - - siginitset(&new_ka.sa.sa_mask, mask); - } - - ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); - - if (!ret && oact) { - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || - __put_user(ptr_to_compat(old_ka.sa.sa_handler), - &oact->sa_handler) || - __put_user(ptr_to_compat(old_ka.sa.sa_restorer), - &oact->sa_restorer) || - __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) - return -EFAULT; - } - - return ret; -} - -asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, - compat_sigset_t __user *oset, - unsigned int sigsetsize) -{ - sigset_t s; - compat_sigset_t s32; - int ret; - mm_segment_t old_fs = get_fs(); - - if (set) { - if (copy_from_user(&s32, set, sizeof(compat_sigset_t))) - return -EFAULT; - switch (_NSIG_WORDS) { - case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32); - case 3: s.sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32); - case 2: s.sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32); - case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); - } - } - set_fs(KERNEL_DS); - ret = sys_rt_sigprocmask(how, - set ? (sigset_t __user *)&s : NULL, - oset ? (sigset_t __user *)&s : NULL, - sigsetsize); - set_fs(old_fs); - if (ret) - return ret; - if (oset) { - switch (_NSIG_WORDS) { - case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3]; - case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2]; - case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1]; - case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0]; - } - if (copy_to_user(oset, &s32, sizeof(compat_sigset_t))) - return -EFAULT; - } - return 0; -} - -static inline long get_tv32(struct timeval *o, struct compat_timeval __user *i) -{ - int err = -EFAULT; - - if (access_ok(VERIFY_READ, i, sizeof(*i))) { - err = __get_user(o->tv_sec, &i->tv_sec); - err |= __get_user(o->tv_usec, &i->tv_usec); - } - return err; -} - -static inline long put_tv32(struct compat_timeval __user *o, struct timeval *i) -{ - int err = -EFAULT; - - if (access_ok(VERIFY_WRITE, o, sizeof(*o))) { - err = __put_user(i->tv_sec, &o->tv_sec); - err |= __put_user(i->tv_usec, &o->tv_usec); - } - return err; -} - -asmlinkage long sys32_alarm(unsigned int seconds) -{ - return alarm_setitimer(seconds); -} - -/* - * Translations due to time_t size differences. Which affects all - * sorts of things, like timeval and itimerval. - */ -asmlinkage long sys32_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - if (tv) { - struct timeval ktv; - - do_gettimeofday(&ktv); - if (put_tv32(tv, &ktv)) - return -EFAULT; - } - if (tz) { - if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) - return -EFAULT; - } - return 0; -} - -asmlinkage long sys32_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) -{ - struct timeval ktv; - struct timespec kts; - struct timezone ktz; - - if (tv) { - if (get_tv32(&ktv, tv)) - return -EFAULT; - kts.tv_sec = ktv.tv_sec; - kts.tv_nsec = ktv.tv_usec * NSEC_PER_USEC; - } - if (tz) { - if (copy_from_user(&ktz, tz, sizeof(ktz))) - return -EFAULT; - } - - return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); -} - -struct sel_arg_struct { - unsigned int n; - unsigned int inp; - unsigned int outp; - unsigned int exp; - unsigned int tvp; -}; - -asmlinkage long sys32_old_select(struct sel_arg_struct __user *arg) -{ - struct sel_arg_struct a; - - if (copy_from_user(&a, arg, sizeof(a))) - return -EFAULT; - return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), - compat_ptr(a.exp), compat_ptr(a.tvp)); -} - -asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr, +asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr, int options) { return compat_sys_wait4(pid, stat_addr, options, NULL); } -/* 32-bit timeval and related flotsam. */ - -asmlinkage long sys32_sysfs(int option, u32 arg1, u32 arg2) -{ - return sys_sysfs(option, arg1, arg2); -} - -asmlinkage long sys32_sched_rr_get_interval(compat_pid_t pid, - struct compat_timespec __user *interval) -{ - struct timespec t; - int ret; - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t); - set_fs(old_fs); - if (put_compat_timespec(&t, interval)) - return -EFAULT; - return ret; -} - -asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set, - compat_size_t sigsetsize) -{ - sigset_t s; - compat_sigset_t s32; - int ret; - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - ret = sys_rt_sigpending((sigset_t __user *)&s, sigsetsize); - set_fs(old_fs); - if (!ret) { - switch (_NSIG_WORDS) { - case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3]; - case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2]; - case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1]; - case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0]; - } - if (copy_to_user(set, &s32, sizeof(compat_sigset_t))) - return -EFAULT; - } - return ret; -} - -asmlinkage long sys32_rt_sigqueueinfo(int pid, int sig, - compat_siginfo_t __user *uinfo) -{ - siginfo_t info; - int ret; - mm_segment_t old_fs = get_fs(); - - if (copy_siginfo_from_user32(&info, uinfo)) - return -EFAULT; - set_fs(KERNEL_DS); - ret = sys_rt_sigqueueinfo(pid, sig, (siginfo_t __user *)&info); - set_fs(old_fs); - return ret; -} - -/* These are here just in case some old ia32 binary calls it. */ -asmlinkage long sys32_pause(void) -{ - current->state = TASK_INTERRUPTIBLE; - schedule(); - return -ERESTARTNOHAND; -} - - -#ifdef CONFIG_SYSCTL_SYSCALL -struct sysctl_ia32 { - unsigned int name; - int nlen; - unsigned int oldval; - unsigned int oldlenp; - unsigned int newval; - unsigned int newlen; - unsigned int __unused[4]; -}; - - -asmlinkage long sys32_sysctl(struct sysctl_ia32 __user *args32) -{ - struct sysctl_ia32 a32; - mm_segment_t old_fs = get_fs(); - void __user *oldvalp, *newvalp; - size_t oldlen; - int __user *namep; - long ret; - - if (copy_from_user(&a32, args32, sizeof(a32))) - return -EFAULT; - - /* - * We need to pre-validate these because we have to disable - * address checking before calling do_sysctl() because of - * OLDLEN but we can't run the risk of the user specifying bad - * addresses here. Well, since we're dealing with 32 bit - * addresses, we KNOW that access_ok() will always succeed, so - * this is an expensive NOP, but so what... - */ - namep = compat_ptr(a32.name); - oldvalp = compat_ptr(a32.oldval); - newvalp = compat_ptr(a32.newval); - - if ((oldvalp && get_user(oldlen, (int __user *)compat_ptr(a32.oldlenp))) - || !access_ok(VERIFY_WRITE, namep, 0) - || !access_ok(VERIFY_WRITE, oldvalp, 0) - || !access_ok(VERIFY_WRITE, newvalp, 0)) - return -EFAULT; - - set_fs(KERNEL_DS); - lock_kernel(); - ret = do_sysctl(namep, a32.nlen, oldvalp, (size_t __user *)&oldlen, - newvalp, (size_t) a32.newlen); - unlock_kernel(); - set_fs(old_fs); - - if (oldvalp && put_user(oldlen, (int __user *)compat_ptr(a32.oldlenp))) - return -EFAULT; - - return ret; -} -#endif - /* warning: next two assume little endian */ asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, u32 poslo, u32 poshi) @@ -654,190 +180,18 @@ asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, ((loff_t)AA(poshi) << 32) | AA(poslo)); } -asmlinkage long sys32_pwrite(unsigned int fd, char __user *ubuf, u32 count, - u32 poslo, u32 poshi) +asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, + u32 count, u32 poslo, u32 poshi) { return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); } -asmlinkage long sys32_personality(unsigned long personality) -{ - int ret; - - if (personality(current->personality) == PER_LINUX32 && - personality == PER_LINUX) - personality = PER_LINUX32; - ret = sys_personality(personality); - if (ret == PER_LINUX32) - ret = PER_LINUX; - return ret; -} - -asmlinkage long sys32_sendfile(int out_fd, int in_fd, - compat_off_t __user *offset, s32 count) -{ - mm_segment_t old_fs = get_fs(); - int ret; - off_t of; - - if (offset && get_user(of, offset)) - return -EFAULT; - - set_fs(KERNEL_DS); - ret = sys_sendfile(out_fd, in_fd, offset ? (off_t __user *)&of : NULL, - count); - set_fs(old_fs); - - if (offset && put_user(of, offset)) - return -EFAULT; - return ret; -} - -asmlinkage long sys32_mmap2(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff) -{ - struct mm_struct *mm = current->mm; - unsigned long error; - struct file *file = NULL; - - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); - if (!(flags & MAP_ANONYMOUS)) { - file = fget(fd); - if (!file) - return -EBADF; - } - - down_write(&mm->mmap_sem); - error = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); - up_write(&mm->mmap_sem); - - if (file) - fput(file); - return error; -} - -asmlinkage long sys32_olduname(struct oldold_utsname __user *name) -{ - char *arch = "x86_64"; - int err; - - if (!name) - return -EFAULT; - if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) - return -EFAULT; - - down_read(&uts_sem); - - err = __copy_to_user(&name->sysname, &utsname()->sysname, - __OLD_UTS_LEN); - err |= __put_user(0, name->sysname+__OLD_UTS_LEN); - err |= __copy_to_user(&name->nodename, &utsname()->nodename, - __OLD_UTS_LEN); - err |= __put_user(0, name->nodename+__OLD_UTS_LEN); - err |= __copy_to_user(&name->release, &utsname()->release, - __OLD_UTS_LEN); - err |= __put_user(0, name->release+__OLD_UTS_LEN); - err |= __copy_to_user(&name->version, &utsname()->version, - __OLD_UTS_LEN); - err |= __put_user(0, name->version+__OLD_UTS_LEN); - - if (personality(current->personality) == PER_LINUX32) - arch = "i686"; - - err |= __copy_to_user(&name->machine, arch, strlen(arch) + 1); - - up_read(&uts_sem); - - err = err ? -EFAULT : 0; - - return err; -} - -long sys32_uname(struct old_utsname __user *name) -{ - int err; - - if (!name) - return -EFAULT; - down_read(&uts_sem); - err = copy_to_user(name, utsname(), sizeof(*name)); - up_read(&uts_sem); - if (personality(current->personality) == PER_LINUX32) - err |= copy_to_user(&name->machine, "i686", 5); - - return err ? -EFAULT : 0; -} - -long sys32_ustat(unsigned dev, struct ustat32 __user *u32p) -{ - struct ustat u; - mm_segment_t seg; - int ret; - - seg = get_fs(); - set_fs(KERNEL_DS); - ret = sys_ustat(dev, (struct ustat __user *)&u); - set_fs(seg); - if (ret < 0) - return ret; - - if (!access_ok(VERIFY_WRITE, u32p, sizeof(struct ustat32)) || - __put_user((__u32) u.f_tfree, &u32p->f_tfree) || - __put_user((__u32) u.f_tinode, &u32p->f_tfree) || - __copy_to_user(&u32p->f_fname, u.f_fname, sizeof(u.f_fname)) || - __copy_to_user(&u32p->f_fpack, u.f_fpack, sizeof(u.f_fpack))) - ret = -EFAULT; - return ret; -} - -asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, - compat_uptr_t __user *envp, struct pt_regs *regs) -{ - long error; - char *filename; - - filename = getname(name); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - return error; - error = compat_do_execve(filename, argv, envp, regs); - if (error == 0) { - task_lock(current); - current->ptrace &= ~PT_DTRACE; - task_unlock(current); - } - putname(filename); - return error; -} - -asmlinkage long sys32_clone(unsigned int clone_flags, unsigned int newsp, - struct pt_regs *regs) -{ - void __user *parent_tid = (void __user *)regs->dx; - void __user *child_tid = (void __user *)regs->di; - - if (!newsp) - newsp = regs->sp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); -} - /* * Some system calls that need sign extended arguments. This could be * done by a generic wrapper. */ -long sys32_lseek(unsigned int fd, int offset, unsigned int whence) -{ - return sys_lseek(fd, offset, whence); -} - -long sys32_kill(int pid, int sig) -{ - return sys_kill(pid, sig); -} - long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, __u32 len_low, __u32 len_high, int advice) { @@ -861,12 +215,6 @@ long sys32_vm86_warning(void) return -ENOSYS; } -long sys32_lookup_dcookie(u32 addr_low, u32 addr_high, - char __user *buf, size_t len) -{ - return sys_lookup_dcookie(((u64)addr_high << 32) | addr_low, buf, len); -} - asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi, size_t count) { diff --git a/arch/x86/ia32/syscall_ia32.c b/arch/x86/ia32/syscall_ia32.c new file mode 100644 index 00000000000..4754ba0f5d9 --- /dev/null +++ b/arch/x86/ia32/syscall_ia32.c @@ -0,0 +1,25 @@ +/* System call table for ia32 emulation. */ + +#include <linux/linkage.h> +#include <linux/sys.h> +#include <linux/cache.h> +#include <asm/asm-offsets.h> + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void compat(void) ; +#include <asm/syscalls_32.h> +#undef __SYSCALL_I386 + +#define __SYSCALL_I386(nr, sym, compat) [nr] = compat, + +typedef void (*sys_call_ptr_t)(void); + +extern void compat_ni_syscall(void); + +const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { + /* + * Smells like a compiler bug -- it doesn't work + * when the & below is removed. + */ + [0 ... __NR_ia32_syscall_max] = &compat_ni_syscall, +#include <asm/syscalls_32.h> +}; |