Linux-2.6.12-rc2v2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

1 files changed, 717 insertions, 0 deletions

diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c
new file mode 100644
index 000000000000..b2f17640ceff
--- /dev/null
+++ b/arch/i386/kernel/ptrace.c
@@ -0,0 +1,717 @@
+/* ptrace.c */
+/* By Ross Biro 1/23/92 */
+/*
+ * Pentium III FXSR, SSE support
+ *      Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/smp_lock.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+#include <linux/security.h>
+#include <linux/audit.h>
+#include <linux/seccomp.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/debugreg.h>
+#include <asm/ldt.h>
+#include <asm/desc.h>
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+/* determines which flags the user has access to. */
+/* 1 = access 0 = no access */
+#define FLAG_MASK 0x00044dd5
+
+/* set's the trap flag. */
+#define TRAP_FLAG 0x100
+
+/*
+ * Offset of eflags on child stack..
+ */
+#define EFL_OFFSET ((EFL-2)*4-sizeof(struct pt_regs))
+
+static inline struct pt_regs *get_child_regs(struct task_struct *task)
+{
+        void *stack_top = (void *)task->thread.esp0;
+        return stack_top - sizeof(struct pt_regs);
+}
+
+/*
+ * this routine will get a word off of the processes privileged stack. 
+ * the offset is how far from the base addr as stored in the TSS.  
+ * this routine assumes that all the privileged stacks are in our
+ * data space.
+ */   
+static inline int get_stack_long(struct task_struct *task, int offset)
+{
+        unsigned char *stack;
+
+        stack = (unsigned char *)task->thread.esp0;
+        stack += offset;
+        return (*((int *)stack));
+}
+
+/*
+ * this routine will put a word on the processes privileged stack. 
+ * the offset is how far from the base addr as stored in the TSS.  
+ * this routine assumes that all the privileged stacks are in our
+ * data space.
+ */
+static inline int put_stack_long(struct task_struct *task, int offset,
+        unsigned long data)
+{
+        unsigned char * stack;
+
+        stack = (unsigned char *) task->thread.esp0;
+        stack += offset;
+        *(unsigned long *) stack = data;
+        return 0;
+}
+
+static int putreg(struct task_struct *child,
+        unsigned long regno, unsigned long value)
+{
+        switch (regno >> 2) {
+                case FS:
+                        if (value && (value & 3) != 3)
+                                return -EIO;
+                        child->thread.fs = value;
+                        return 0;
+                case GS:
+                        if (value && (value & 3) != 3)
+                                return -EIO;
+                        child->thread.gs = value;
+                        return 0;
+                case DS:
+                case ES:
+                        if (value && (value & 3) != 3)
+                                return -EIO;
+                        value &= 0xffff;
+                        break;
+                case SS:
+                case CS:
+                        if ((value & 3) != 3)
+                                return -EIO;
+                        value &= 0xffff;
+                        break;
+                case EFL:
+                        value &= FLAG_MASK;
+                        value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
+                        break;
+        }
+        if (regno > GS*4)
+                regno -= 2*4;
+        put_stack_long(child, regno - sizeof(struct pt_regs), value);
+        return 0;
+}
+
+static unsigned long getreg(struct task_struct *child,
+        unsigned long regno)
+{
+        unsigned long retval = ~0UL;
+
+        switch (regno >> 2) {
+                case FS:
+                        retval = child->thread.fs;
+                        break;
+                case GS:
+                        retval = child->thread.gs;
+                        break;
+                case DS:
+                case ES:
+                case SS:
+                case CS:
+                        retval = 0xffff;
+                        /* fall through */
+                default:
+                        if (regno > GS*4)
+                                regno -= 2*4;
+                        regno = regno - sizeof(struct pt_regs);
+                        retval &= get_stack_long(child, regno);
+        }
+        return retval;
+}
+
+#define LDT_SEGMENT 4
+
+static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_regs *regs)
+{
+        unsigned long addr, seg;
+
+        addr = regs->eip;
+        seg = regs->xcs & 0xffff;
+        if (regs->eflags & VM_MASK) {
+                addr = (addr & 0xffff) + (seg << 4);
+                return addr;
+        }
+
+        /*
+         * We'll assume that the code segments in the GDT
+         * are all zero-based. That is largely true: the
+         * TLS segments are used for data, and the PNPBIOS
+         * and APM bios ones we just ignore here.
+         */
+        if (seg & LDT_SEGMENT) {
+                u32 *desc;
+                unsigned long base;
+
+                down(&child->mm->context.sem);
+                desc = child->mm->context.ldt + (seg & ~7);
+                base = (desc[0] >> 16) | ((desc[1] & 0xff) << 16) | (desc[1] & 0xff000000);
+
+                /* 16-bit code segment? */
+                if (!((desc[1] >> 22) & 1))
+                        addr &= 0xffff;
+                addr += base;
+                up(&child->mm->context.sem);
+        }
+        return addr;
+}
+
+static inline int is_at_popf(struct task_struct *child, struct pt_regs *regs)
+{
+        int i, copied;
+        unsigned char opcode[16];
+        unsigned long addr = convert_eip_to_linear(child, regs);
+
+        copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0);
+        for (i = 0; i < copied; i++) {
+                switch (opcode[i]) {
+                /* popf */
+                case 0x9d:
+                        return 1;
+                /* opcode and address size prefixes */
+                case 0x66: case 0x67:
+                        continue;
+                /* irrelevant prefixes (segment overrides and repeats) */
+                case 0x26: case 0x2e:
+                case 0x36: case 0x3e:
+                case 0x64: case 0x65:
+                case 0xf0: case 0xf2: case 0xf3:
+                        continue;
+
+                /*
+                 * pushf: NOTE! We should probably not let
+                 * the user see the TF bit being set. But
+                 * it's more pain than it's worth to avoid
+                 * it, and a debugger could emulate this
+                 * all in user space if it _really_ cares.
+                 */
+                case 0x9c:
+                default:
+                        return 0;
+                }
+        }
+        return 0;
+}
+
+static void set_singlestep(struct task_struct *child)
+{
+        struct pt_regs *regs = get_child_regs(child);
+
+        /*
+         * Always set TIF_SINGLESTEP - this guarantees that 
+         * we single-step system calls etc..  This will also
+         * cause us to set TF when returning to user mode.
+         */
+        set_tsk_thread_flag(child, TIF_SINGLESTEP);
+
+        /*
+         * If TF was already set, don't do anything else
+         */
+        if (regs->eflags & TRAP_FLAG)
+                return;
+
+        /* Set TF on the kernel stack.. */
+        regs->eflags |= TRAP_FLAG;
+
+        /*
+         * ..but if TF is changed by the instruction we will trace,
+         * don't mark it as being "us" that set it, so that we
+         * won't clear it by hand later.
+         */
+        if (is_at_popf(child, regs))
+                return;
+        
+        child->ptrace |= PT_DTRACE;
+}
+
+static void clear_singlestep(struct task_struct *child)
+{
+        /* Always clear TIF_SINGLESTEP... */
+        clear_tsk_thread_flag(child, TIF_SINGLESTEP);
+
+        /* But touch TF only if it was set by us.. */
+        if (child->ptrace & PT_DTRACE) {
+                struct pt_regs *regs = get_child_regs(child);
+                regs->eflags &= ~TRAP_FLAG;
+                child->ptrace &= ~PT_DTRACE;
+        }
+}
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure the single step bit is not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{ 
+        clear_singlestep(child);
+}
+
+/*
+ * Perform get_thread_area on behalf of the traced child.
+ */
+static int
+ptrace_get_thread_area(struct task_struct *child,
+                       int idx, struct user_desc __user *user_desc)
+{
+        struct user_desc info;
+        struct desc_struct *desc;
+
+/*
+ * Get the current Thread-Local Storage area:
+ */
+
+#define GET_BASE(desc) ( \
+        (((desc)->a >> 16) & 0x0000ffff) | \
+        (((desc)->b << 16) & 0x00ff0000) | \
+        ( (desc)->b        & 0xff000000)   )
+
+#define GET_LIMIT(desc) ( \
+        ((desc)->a & 0x0ffff) | \
+         ((desc)->b & 0xf0000) )
+
+#define GET_32BIT(desc)         (((desc)->b >> 22) & 1)
+#define GET_CONTENTS(desc)      (((desc)->b >> 10) & 3)
+#define GET_WRITABLE(desc)      (((desc)->b >>  9) & 1)
+#define GET_LIMIT_PAGES(desc)   (((desc)->b >> 23) & 1)
+#define GET_PRESENT(desc)       (((desc)->b >> 15) & 1)
+#define GET_USEABLE(desc)       (((desc)->b >> 20) & 1)
+
+        if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+                return -EINVAL;
+
+        desc = child->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
+
+        info.entry_number = idx;
+        info.base_addr = GET_BASE(desc);
+        info.limit = GET_LIMIT(desc);
+        info.seg_32bit = GET_32BIT(desc);
+        info.contents = GET_CONTENTS(desc);
+        info.read_exec_only = !GET_WRITABLE(desc);
+        info.limit_in_pages = GET_LIMIT_PAGES(desc);
+        info.seg_not_present = !GET_PRESENT(desc);
+        info.useable = GET_USEABLE(desc);
+
+        if (copy_to_user(user_desc, &info, sizeof(info)))
+                return -EFAULT;
+
+        return 0;
+}
+
+/*
+ * Perform set_thread_area on behalf of the traced child.
+ */
+static int
+ptrace_set_thread_area(struct task_struct *child,
+                       int idx, struct user_desc __user *user_desc)
+{
+        struct user_desc info;
+        struct desc_struct *desc;
+
+        if (copy_from_user(&info, user_desc, sizeof(info)))
+                return -EFAULT;
+
+        if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+                return -EINVAL;
+
+        desc = child->thread.tls_array + idx - GDT_ENTRY_TLS_MIN;
+        if (LDT_empty(&info)) {
+                desc->a = 0;
+                desc->b = 0;
+        } else {
+                desc->a = LDT_entry_a(&info);
+                desc->b = LDT_entry_b(&info);
+        }
+
+        return 0;
+}
+
+asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
+{
+        struct task_struct *child;
+        struct user * dummy = NULL;
+        int i, ret;
+        unsigned long __user *datap = (unsigned long __user *)data;
+
+        lock_kernel();
+        ret = -EPERM;
+        if (request == PTRACE_TRACEME) {
+                /* are we already being traced? */
+                if (current->ptrace & PT_PTRACED)
+                        goto out;
+                ret = security_ptrace(current->parent, current);
+                if (ret)
+                        goto out;
+                /* set the ptrace bit in the process flags. */
+                current->ptrace |= PT_PTRACED;
+                ret = 0;
+                goto out;
+        }
+        ret = -ESRCH;
+        read_lock(&tasklist_lock);
+        child = find_task_by_pid(pid);
+        if (child)
+                get_task_struct(child);
+        read_unlock(&tasklist_lock);
+        if (!child)
+                goto out;
+
+        ret = -EPERM;
+        if (pid == 1)           /* you may not mess with init */
+                goto out_tsk;
+
+        if (request == PTRACE_ATTACH) {
+                ret = ptrace_attach(child);
+                goto out_tsk;
+        }
+
+        ret = ptrace_check_attach(child, request == PTRACE_KILL);
+        if (ret < 0)
+                goto out_tsk;
+
+        switch (request) {
+        /* when I and D space are separate, these will need to be fixed. */
+        case PTRACE_PEEKTEXT: /* read word at location addr. */ 
+        case PTRACE_PEEKDATA: {
+                unsigned long tmp;
+                int copied;
+
+                copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+                ret = -EIO;
+                if (copied != sizeof(tmp))
+                        break;
+                ret = put_user(tmp, datap);
+                break;
+        }
+
+        /* read the word at location addr in the USER area. */
+        case PTRACE_PEEKUSR: {
+                unsigned long tmp;
+
+                ret = -EIO;
+                if ((addr & 3) || addr < 0 || 
+                    addr > sizeof(struct user) - 3)
+                        break;
+
+                tmp = 0;  /* Default return condition */
+                if(addr < FRAME_SIZE*sizeof(long))
+                        tmp = getreg(child, addr);
+                if(addr >= (long) &dummy->u_debugreg[0] &&
+                   addr <= (long) &dummy->u_debugreg[7]){
+                        addr -= (long) &dummy->u_debugreg[0];
+                        addr = addr >> 2;
+                        tmp = child->thread.debugreg[addr];
+                }
+                ret = put_user(tmp, datap);
+                break;
+        }
+
+        /* when I and D space are separate, this will have to be fixed. */
+        case PTRACE_POKETEXT: /* write the word at location addr. */
+        case PTRACE_POKEDATA:
+                ret = 0;
+                if (access_process_vm(child, addr, &data, sizeof(data), 1) == sizeof(data))
+                        break;
+                ret = -EIO;
+                break;
+
+        case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
+                ret = -EIO;
+                if ((addr & 3) || addr < 0 || 
+                    addr > sizeof(struct user) - 3)
+                        break;
+
+                if (addr < FRAME_SIZE*sizeof(long)) {
+                        ret = putreg(child, addr, data);
+                        break;
+                }
+                /* We need to be very careful here.  We implicitly
+                   want to modify a portion of the task_struct, and we
+                   have to be selective about what portions we allow someone
+                   to modify. */
+
+                  ret = -EIO;
+                  if(addr >= (long) &dummy->u_debugreg[0] &&
+                     addr <= (long) &dummy->u_debugreg[7]){
+
+                          if(addr == (long) &dummy->u_debugreg[4]) break;
+                          if(addr == (long) &dummy->u_debugreg[5]) break;
+                          if(addr < (long) &dummy->u_debugreg[4] &&
+                             ((unsigned long) data) >= TASK_SIZE-3) break;
+                          
+                          /* Sanity-check data. Take one half-byte at once with
+                           * check = (val >> (16 + 4*i)) & 0xf. It contains the
+                           * R/Wi and LENi bits; bits 0 and 1 are R/Wi, and bits
+                           * 2 and 3 are LENi. Given a list of invalid values,
+                           * we do mask |= 1 << invalid_value, so that
+                           * (mask >> check) & 1 is a correct test for invalid
+                           * values.
+                           *
+                           * R/Wi contains the type of the breakpoint /
+                           * watchpoint, LENi contains the length of the watched
+                           * data in the watchpoint case.
+                           *
+                           * The invalid values are:
+                           * - LENi == 0x10 (undefined), so mask |= 0x0f00.
+                           * - R/Wi == 0x10 (break on I/O reads or writes), so
+                           *   mask |= 0x4444.
+                           * - R/Wi == 0x00 && LENi != 0x00, so we have mask |=
+                           *   0x1110.
+                           *
+                           * Finally, mask = 0x0f00 | 0x4444 | 0x1110 == 0x5f54.
+                           *
+                           * See the Intel Manual "System Programming Guide",
+                           * 15.2.4
+                           *
+                           * Note that LENi == 0x10 is defined on x86_64 in long
+                           * mode (i.e. even for 32-bit userspace software, but
+                           * 64-bit kernel), so the x86_64 mask value is 0x5454.
+                           * See the AMD manual no. 24593 (AMD64 System
+                           * Programming)*/
+
+                          if(addr == (long) &dummy->u_debugreg[7]) {
+                                  data &= ~DR_CONTROL_RESERVED;
+                                  for(i=0; i<4; i++)
+                                          if ((0x5f54 >> ((data >> (16 + 4*i)) & 0xf)) & 1)
+                                                  goto out_tsk;
+                          }
+
+                          addr -= (long) &dummy->u_debugreg;
+                          addr = addr >> 2;
+                          child->thread.debugreg[addr] = data;
+                          ret = 0;
+                  }
+                  break;
+
+        case PTRACE_SYSCALL:    /* continue and stop at next (return from) syscall */
+        case PTRACE_CONT:       /* restart after signal. */
+                ret = -EIO;
+                if ((unsigned long) data > _NSIG)
+                        break;
+                if (request == PTRACE_SYSCALL) {
+                        set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+                }
+                else {
+                        clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+                }
+                child->exit_code = data;
+                /* make sure the single step bit is not set. */
+                clear_singlestep(child);
+                wake_up_process(child);
+                ret = 0;
+                break;
+
+/*
+ * make the child exit.  Best I can do is send it a sigkill. 
+ * perhaps it should be put in the status that it wants to 
+ * exit.
+ */
+        case PTRACE_KILL:
+                ret = 0;
+                if (child->exit_state == EXIT_ZOMBIE)   /* already dead */
+                        break;
+                child->exit_code = SIGKILL;
+                /* make sure the single step bit is not set. */
+                clear_singlestep(child);
+                wake_up_process(child);
+                break;
+
+        case PTRACE_SINGLESTEP: /* set the trap flag. */
+                ret = -EIO;
+                if ((unsigned long) data > _NSIG)
+                        break;
+                clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+                set_singlestep(child);
+                child->exit_code = data;
+                /* give it a chance to run. */
+                wake_up_process(child);
+                ret = 0;
+                break;
+
+        case PTRACE_DETACH:
+                /* detach a process that was attached. */
+                ret = ptrace_detach(child, data);
+                break;
+
+        case PTRACE_GETREGS: { /* Get all gp regs from the child. */
+                if (!access_ok(VERIFY_WRITE, datap, FRAME_SIZE*sizeof(long))) {
+                        ret = -EIO;
+                        break;
+                }
+                for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
+                        __put_user(getreg(child, i), datap);
+                        datap++;
+                }
+                ret = 0;
+                break;
+        }
+
+        case PTRACE_SETREGS: { /* Set all gp regs in the child. */
+                unsigned long tmp;
+                if (!access_ok(VERIFY_READ, datap, FRAME_SIZE*sizeof(long))) {
+                        ret = -EIO;
+                        break;
+                }
+                for ( i = 0; i < FRAME_SIZE*sizeof(long); i += sizeof(long) ) {
+                        __get_user(tmp, datap);
+                        putreg(child, i, tmp);
+                        datap++;
+                }
+                ret = 0;
+                break;
+        }
+
+        case PTRACE_GETFPREGS: { /* Get the child FPU state. */
+                if (!access_ok(VERIFY_WRITE, datap,
+                               sizeof(struct user_i387_struct))) {
+                        ret = -EIO;
+                        break;
+                }
+                ret = 0;
+                if (!tsk_used_math(child))
+                        init_fpu(child);
+                get_fpregs((struct user_i387_struct __user *)data, child);
+                break;
+        }
+
+        case PTRACE_SETFPREGS: { /* Set the child FPU state. */
+                if (!access_ok(VERIFY_READ, datap,
+                               sizeof(struct user_i387_struct))) {
+                        ret = -EIO;
+                        break;
+                }
+                set_stopped_child_used_math(child);
+                set_fpregs(child, (struct user_i387_struct __user *)data);
+                ret = 0;
+                break;
+        }
+
+        case PTRACE_GETFPXREGS: { /* Get the child extended FPU state. */
+                if (!access_ok(VERIFY_WRITE, datap,
+                               sizeof(struct user_fxsr_struct))) {
+                        ret = -EIO;
+                        break;
+                }
+                if (!tsk_used_math(child))
+                        init_fpu(child);
+                ret = get_fpxregs((struct user_fxsr_struct __user *)data, child);
+                break;
+        }
+
+        case PTRACE_SETFPXREGS: { /* Set the child extended FPU state. */
+                if (!access_ok(VERIFY_READ, datap,
+                               sizeof(struct user_fxsr_struct))) {
+                        ret = -EIO;
+                        break;
+                }
+                set_stopped_child_used_math(child);
+                ret = set_fpxregs(child, (struct user_fxsr_struct __user *)data);
+                break;
+        }
+
+        case PTRACE_GET_THREAD_AREA:
+                ret = ptrace_get_thread_area(child, addr,
+                                        (struct user_desc __user *) data);
+                break;
+
+        case PTRACE_SET_THREAD_AREA:
+                ret = ptrace_set_thread_area(child, addr,
+                                        (struct user_desc __user *) data);
+                break;
+
+        default:
+                ret = ptrace_request(child, request, addr, data);
+                break;
+        }
+out_tsk:
+        put_task_struct(child);
+out:
+        unlock_kernel();
+        return ret;
+}
+
+void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
+{
+        struct siginfo info;
+
+        tsk->thread.trap_no = 1;
+        tsk->thread.error_code = error_code;
+
+        memset(&info, 0, sizeof(info));
+        info.si_signo = SIGTRAP;
+        info.si_code = TRAP_BRKPT;
+
+        /* User-mode eip? */
+        info.si_addr = user_mode(regs) ? (void __user *) regs->eip : NULL;
+
+        /* Send us the fakey SIGTRAP */
+        force_sig_info(SIGTRAP, &info, tsk);
+}
+
+/* notification of system call entry/exit
+ * - triggered by current->work.syscall_trace
+ */
+__attribute__((regparm(3)))
+void do_syscall_trace(struct pt_regs *regs, int entryexit)
+{
+        /* do the secure computing check first */
+        secure_computing(regs->orig_eax);
+
+        if (unlikely(current->audit_context)) {
+                if (!entryexit)
+                        audit_syscall_entry(current, regs->orig_eax,
+                                            regs->ebx, regs->ecx,
+                                            regs->edx, regs->esi);
+                else
+                        audit_syscall_exit(current, regs->eax);
+        }
+
+        if (!(current->ptrace & PT_PTRACED))
+                return;
+
+        /* Fake a debug trap */
+        if (test_thread_flag(TIF_SINGLESTEP))
+                send_sigtrap(current, regs, 0);
+
+        if (!test_thread_flag(TIF_SYSCALL_TRACE))
+                return;
+
+        /* the 0x80 provides a way for the tracing parent to distinguish
+           between a syscall stop and SIGTRAP delivery */
+        ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80 : 0));
+
+        /*
+         * this isn't the same as continuing with a signal, but it will do
+         * for normal use.  strace only continues with a signal if the
+         * stopping signal is not SIGTRAP.  -brl
+         */
+        if (current->exit_code) {
+                send_sig(current->exit_code, current, 1);
+                current->exit_code = 0;
+        }
+}