/*
* Pentium III FXSR, SSE support
* Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * BTS tracing
+ * Markus Metzger <markus.t.metzger@intel.com>, Dec 2007
*/
#include <linux/kernel.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
+#include <linux/regset.h>
+#include <linux/tracehook.h>
#include <linux/user.h>
+#include <linux/elf.h>
#include <linux/security.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <asm/desc.h>
#include <asm/prctl.h>
#include <asm/proto.h>
+#include <asm/ds.h>
+
+#include "tls.h"
+
+enum x86_regset {
+ REGSET_GENERAL,
+ REGSET_FP,
+ REGSET_XFP,
+ REGSET_IOPERM64 = REGSET_XFP,
+ REGSET_TLS,
+ REGSET_IOPERM32,
+};
/*
* does not yet catch signals sent when the child dies.
#define FLAG_MASK FLAG_MASK_32
-static long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
+static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
{
BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
- regno >>= 2;
- if (regno > FS)
- --regno;
- return ®s->bx + regno;
+ return ®s->bx + (regno >> 2);
}
static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
if (offset != offsetof(struct user_regs_struct, gs))
retval = *pt_regs_access(task_pt_regs(task), offset);
else {
- retval = task->thread.gs;
if (task == current)
- savesegment(gs, retval);
+ retval = get_user_gs(task_pt_regs(task));
+ else
+ retval = task_user_gs(task);
}
return retval;
}
if (invalid_selector(value))
return -EIO;
- if (offset != offsetof(struct user_regs_struct, gs))
+ /*
+ * For %cs and %ss we cannot permit a null selector.
+ * We can permit a bogus selector as long as it has USER_RPL.
+ * Null selectors are fine for other segment registers, but
+ * we will never get back to user mode with invalid %cs or %ss
+ * and will take the trap in iret instead. Much code relies
+ * on user_mode() to distinguish a user trap frame (which can
+ * safely use invalid selectors) from a kernel trap frame.
+ */
+ switch (offset) {
+ case offsetof(struct user_regs_struct, cs):
+ case offsetof(struct user_regs_struct, ss):
+ if (unlikely(value == 0))
+ return -EIO;
+
+ default:
*pt_regs_access(task_pt_regs(task), offset) = value;
- else {
- task->thread.gs = value;
+ break;
+
+ case offsetof(struct user_regs_struct, gs):
if (task == current)
- /*
- * The user-mode %gs is not affected by
- * kernel entry, so we must update the CPU.
- */
- loadsegment(gs, value);
+ set_user_gs(task_pt_regs(task), value);
+ else
+ task_user_gs(task) = value;
}
return 0;
* Can't actually change these in 64-bit mode.
*/
case offsetof(struct user_regs_struct,cs):
+ if (unlikely(value == 0))
+ return -EIO;
#ifdef CONFIG_IA32_EMULATION
if (test_tsk_thread_flag(task, TIF_IA32))
task_pt_regs(task)->cs = value;
- break;
#endif
+ break;
case offsetof(struct user_regs_struct,ss):
+ if (unlikely(value == 0))
+ return -EIO;
#ifdef CONFIG_IA32_EMULATION
if (test_tsk_thread_flag(task, TIF_IA32))
task_pt_regs(task)->ss = value;
- break;
#endif
+ break;
}
return 0;
return set_flags(child, value);
#ifdef CONFIG_X86_64
+ /*
+ * Orig_ax is really just a flag with small positive and
+ * negative values, so make sure to always sign-extend it
+ * from 32 bits so that it works correctly regardless of
+ * whether we come from a 32-bit environment or not.
+ */
+ case offsetof(struct user_regs_struct, orig_ax):
+ value = (long) (s32) value;
+ break;
+
case offsetof(struct user_regs_struct,fs_base):
if (value >= TASK_SIZE_OF(child))
return -EIO;
return *pt_regs_access(task_pt_regs(task), offset);
}
+static int genregs_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ if (kbuf) {
+ unsigned long *k = kbuf;
+ while (count > 0) {
+ *k++ = getreg(target, pos);
+ count -= sizeof(*k);
+ pos += sizeof(*k);
+ }
+ } else {
+ unsigned long __user *u = ubuf;
+ while (count > 0) {
+ if (__put_user(getreg(target, pos), u++))
+ return -EFAULT;
+ count -= sizeof(*u);
+ pos += sizeof(*u);
+ }
+ }
+
+ return 0;
+}
+
+static int genregs_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret = 0;
+ if (kbuf) {
+ const unsigned long *k = kbuf;
+ while (count > 0 && !ret) {
+ ret = putreg(target, pos, *k++);
+ count -= sizeof(*k);
+ pos += sizeof(*k);
+ }
+ } else {
+ const unsigned long __user *u = ubuf;
+ while (count > 0 && !ret) {
+ unsigned long word;
+ ret = __get_user(word, u++);
+ if (ret)
+ break;
+ ret = putreg(target, pos, word);
+ count -= sizeof(*u);
+ pos += sizeof(*u);
+ }
+ }
+ return ret;
+}
+
/*
* This function is trivial and will be inlined by the compiler.
* Having it separates the implementation details of debug
}
/*
+ * These access the current or another (stopped) task's io permission
+ * bitmap for debugging or core dump.
+ */
+static int ioperm_active(struct task_struct *target,
+ const struct user_regset *regset)
+{
+ return target->thread.io_bitmap_max / regset->size;
+}
+
+static int ioperm_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ if (!target->thread.io_bitmap_ptr)
+ return -ENXIO;
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ target->thread.io_bitmap_ptr,
+ 0, IO_BITMAP_BYTES);
+}
+
+#ifdef CONFIG_X86_PTRACE_BTS
+static int ptrace_bts_read_record(struct task_struct *child, size_t index,
+ struct bts_struct __user *out)
+{
+ const struct bts_trace *trace;
+ struct bts_struct bts;
+ const unsigned char *at;
+ int error;
+
+ trace = ds_read_bts(child->bts);
+ if (!trace)
+ return -EPERM;
+
+ at = trace->ds.top - ((index + 1) * trace->ds.size);
+ if ((void *)at < trace->ds.begin)
+ at += (trace->ds.n * trace->ds.size);
+
+ if (!trace->read)
+ return -EOPNOTSUPP;
+
+ error = trace->read(child->bts, at, &bts);
+ if (error < 0)
+ return error;
+
+ if (copy_to_user(out, &bts, sizeof(bts)))
+ return -EFAULT;
+
+ return sizeof(bts);
+}
+
+static int ptrace_bts_drain(struct task_struct *child,
+ long size,
+ struct bts_struct __user *out)
+{
+ const struct bts_trace *trace;
+ const unsigned char *at;
+ int error, drained = 0;
+
+ trace = ds_read_bts(child->bts);
+ if (!trace)
+ return -EPERM;
+
+ if (!trace->read)
+ return -EOPNOTSUPP;
+
+ if (size < (trace->ds.top - trace->ds.begin))
+ return -EIO;
+
+ for (at = trace->ds.begin; (void *)at < trace->ds.top;
+ out++, drained++, at += trace->ds.size) {
+ struct bts_struct bts;
+ int error;
+
+ error = trace->read(child->bts, at, &bts);
+ if (error < 0)
+ return error;
+
+ if (copy_to_user(out, &bts, sizeof(bts)))
+ return -EFAULT;
+ }
+
+ memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
+
+ error = ds_reset_bts(child->bts);
+ if (error < 0)
+ return error;
+
+ return drained;
+}
+
+static int ptrace_bts_allocate_buffer(struct task_struct *child, size_t size)
+{
+ child->bts_buffer = alloc_locked_buffer(size);
+ if (!child->bts_buffer)
+ return -ENOMEM;
+
+ child->bts_size = size;
+
+ return 0;
+}
+
+static void ptrace_bts_free_buffer(struct task_struct *child)
+{
+ free_locked_buffer(child->bts_buffer, child->bts_size);
+ child->bts_buffer = NULL;
+ child->bts_size = 0;
+}
+
+static int ptrace_bts_config(struct task_struct *child,
+ long cfg_size,
+ const struct ptrace_bts_config __user *ucfg)
+{
+ struct ptrace_bts_config cfg;
+ unsigned int flags = 0;
+
+ if (cfg_size < sizeof(cfg))
+ return -EIO;
+
+ if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
+ return -EFAULT;
+
+ if (child->bts) {
+ ds_release_bts(child->bts);
+ child->bts = NULL;
+ }
+
+ if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
+ if (!cfg.signal)
+ return -EINVAL;
+
+ return -EOPNOTSUPP;
+
+ child->thread.bts_ovfl_signal = cfg.signal;
+ }
+
+ if ((cfg.flags & PTRACE_BTS_O_ALLOC) &&
+ (cfg.size != child->bts_size)) {
+ int error;
+
+ ptrace_bts_free_buffer(child);
+
+ error = ptrace_bts_allocate_buffer(child, cfg.size);
+ if (error < 0)
+ return error;
+ }
+
+ if (cfg.flags & PTRACE_BTS_O_TRACE)
+ flags |= BTS_USER;
+
+ if (cfg.flags & PTRACE_BTS_O_SCHED)
+ flags |= BTS_TIMESTAMPS;
+
+ child->bts = ds_request_bts(child, child->bts_buffer, child->bts_size,
+ /* ovfl = */ NULL, /* th = */ (size_t)-1,
+ flags);
+ if (IS_ERR(child->bts)) {
+ int error = PTR_ERR(child->bts);
+
+ ptrace_bts_free_buffer(child);
+ child->bts = NULL;
+
+ return error;
+ }
+
+ return sizeof(cfg);
+}
+
+static int ptrace_bts_status(struct task_struct *child,
+ long cfg_size,
+ struct ptrace_bts_config __user *ucfg)
+{
+ const struct bts_trace *trace;
+ struct ptrace_bts_config cfg;
+
+ if (cfg_size < sizeof(cfg))
+ return -EIO;
+
+ trace = ds_read_bts(child->bts);
+ if (!trace)
+ return -EPERM;
+
+ memset(&cfg, 0, sizeof(cfg));
+ cfg.size = trace->ds.end - trace->ds.begin;
+ cfg.signal = child->thread.bts_ovfl_signal;
+ cfg.bts_size = sizeof(struct bts_struct);
+
+ if (cfg.signal)
+ cfg.flags |= PTRACE_BTS_O_SIGNAL;
+
+ if (trace->ds.flags & BTS_USER)
+ cfg.flags |= PTRACE_BTS_O_TRACE;
+
+ if (trace->ds.flags & BTS_TIMESTAMPS)
+ cfg.flags |= PTRACE_BTS_O_SCHED;
+
+ if (copy_to_user(ucfg, &cfg, sizeof(cfg)))
+ return -EFAULT;
+
+ return sizeof(cfg);
+}
+
+static int ptrace_bts_clear(struct task_struct *child)
+{
+ const struct bts_trace *trace;
+
+ trace = ds_read_bts(child->bts);
+ if (!trace)
+ return -EPERM;
+
+ memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
+
+ return ds_reset_bts(child->bts);
+}
+
+static int ptrace_bts_size(struct task_struct *child)
+{
+ const struct bts_trace *trace;
+
+ trace = ds_read_bts(child->bts);
+ if (!trace)
+ return -EPERM;
+
+ return (trace->ds.top - trace->ds.begin) / trace->ds.size;
+}
+
+static void ptrace_bts_fork(struct task_struct *tsk)
+{
+ tsk->bts = NULL;
+ tsk->bts_buffer = NULL;
+ tsk->bts_size = 0;
+ tsk->thread.bts_ovfl_signal = 0;
+}
+
+static void ptrace_bts_untrace(struct task_struct *child)
+{
+ if (unlikely(child->bts)) {
+ ds_release_bts(child->bts);
+ child->bts = NULL;
+
+ /* We cannot update total_vm and locked_vm since
+ child's mm is already gone. But we can reclaim the
+ memory. */
+ kfree(child->bts_buffer);
+ child->bts_buffer = NULL;
+ child->bts_size = 0;
+ }
+}
+
+static void ptrace_bts_detach(struct task_struct *child)
+{
+ /*
+ * Ptrace_detach() races with ptrace_untrace() in case
+ * the child dies and is reaped by another thread.
+ *
+ * We only do the memory accounting at this point and
+ * leave the buffer deallocation and the bts tracer
+ * release to ptrace_bts_untrace() which will be called
+ * later on with tasklist_lock held.
+ */
+ release_locked_buffer(child->bts_buffer, child->bts_size);
+}
+#else
+static inline void ptrace_bts_fork(struct task_struct *tsk) {}
+static inline void ptrace_bts_detach(struct task_struct *child) {}
+static inline void ptrace_bts_untrace(struct task_struct *child) {}
+#endif /* CONFIG_X86_PTRACE_BTS */
+
+void x86_ptrace_fork(struct task_struct *child, unsigned long clone_flags)
+{
+ ptrace_bts_fork(child);
+}
+
+void x86_ptrace_untrace(struct task_struct *child)
+{
+ ptrace_bts_untrace(child);
+}
+
+/*
* Called by kernel/ptrace.c when detaching..
*
* Make sure the single step bit is not set.
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
#endif
+ ptrace_bts_detach(child);
}
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+static const struct user_regset_view user_x86_32_view; /* Initialized below. */
+#endif
+
long arch_ptrace(struct task_struct *child, long request, long addr, long data)
{
- int i, ret;
+ int ret;
unsigned long __user *datap = (unsigned long __user *)data;
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:
- ret = generic_ptrace_peekdata(child, addr, data);
- break;
-
/* read the word at location addr in the USER area. */
case PTRACE_PEEKUSR: {
unsigned long tmp;
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 = generic_ptrace_pokedata(child, addr, data);
- break;
-
case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
ret = -EIO;
if ((addr & (sizeof(data) - 1)) || addr < 0 ||
}
break;
- case PTRACE_GETREGS: { /* Get all gp regs from the child. */
- if (!access_ok(VERIFY_WRITE, datap, sizeof(struct user_regs_struct))) {
- ret = -EIO;
- break;
- }
- for (i = 0; i < sizeof(struct user_regs_struct); 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, sizeof(struct user_regs_struct))) {
- ret = -EIO;
- break;
- }
- for (i = 0; i < sizeof(struct user_regs_struct); 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_GETREGS: /* Get all gp regs from the child. */
+ return copy_regset_to_user(child,
+ task_user_regset_view(current),
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct),
+ datap);
+
+ case PTRACE_SETREGS: /* Set all gp regs in the child. */
+ return copy_regset_from_user(child,
+ task_user_regset_view(current),
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct),
+ datap);
+
+ case PTRACE_GETFPREGS: /* Get the child FPU state. */
+ return copy_regset_to_user(child,
+ task_user_regset_view(current),
+ REGSET_FP,
+ 0, sizeof(struct user_i387_struct),
+ datap);
+
+ case PTRACE_SETFPREGS: /* Set the child FPU state. */
+ return copy_regset_from_user(child,
+ task_user_regset_view(current),
+ REGSET_FP,
+ 0, sizeof(struct user_i387_struct),
+ datap);
#ifdef CONFIG_X86_32
- 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_GETFPXREGS: /* Get the child extended FPU state. */
+ return copy_regset_to_user(child, &user_x86_32_view,
+ REGSET_XFP,
+ 0, sizeof(struct user_fxsr_struct),
+ datap) ? -EIO : 0;
+
+ case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */
+ return copy_regset_from_user(child, &user_x86_32_view,
+ REGSET_XFP,
+ 0, sizeof(struct user_fxsr_struct),
+ datap) ? -EIO : 0;
#endif
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
break;
#endif
+ /*
+ * These bits need more cooking - not enabled yet:
+ */
+#ifdef CONFIG_X86_PTRACE_BTS
+ case PTRACE_BTS_CONFIG:
+ ret = ptrace_bts_config
+ (child, data, (struct ptrace_bts_config __user *)addr);
+ break;
+
+ case PTRACE_BTS_STATUS:
+ ret = ptrace_bts_status
+ (child, data, (struct ptrace_bts_config __user *)addr);
+ break;
+
+ case PTRACE_BTS_SIZE:
+ ret = ptrace_bts_size(child);
+ break;
+
+ case PTRACE_BTS_GET:
+ ret = ptrace_bts_read_record
+ (child, data, (struct bts_struct __user *) addr);
+ break;
+
+ case PTRACE_BTS_CLEAR:
+ ret = ptrace_bts_clear(child);
+ break;
+
+ case PTRACE_BTS_DRAIN:
+ ret = ptrace_bts_drain
+ (child, data, (struct bts_struct __user *) addr);
+ break;
+#endif /* CONFIG_X86_PTRACE_BTS */
+
default:
ret = ptrace_request(child, request, addr, data);
break;
return ret;
}
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_IA32_EMULATION
+
+#include <linux/compat.h>
+#include <linux/syscalls.h>
+#include <asm/ia32.h>
+#include <asm/user32.h>
+
+#define R32(l,q) \
+ case offsetof(struct user32, regs.l): \
+ regs->q = value; break
-void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
+#define SEG32(rs) \
+ case offsetof(struct user32, regs.rs): \
+ return set_segment_reg(child, \
+ offsetof(struct user_regs_struct, rs), \
+ value); \
+ break
+
+static int putreg32(struct task_struct *child, unsigned regno, u32 value)
{
- struct siginfo info;
+ struct pt_regs *regs = task_pt_regs(child);
+
+ switch (regno) {
+
+ SEG32(cs);
+ SEG32(ds);
+ SEG32(es);
+ SEG32(fs);
+ SEG32(gs);
+ SEG32(ss);
+
+ R32(ebx, bx);
+ R32(ecx, cx);
+ R32(edx, dx);
+ R32(edi, di);
+ R32(esi, si);
+ R32(ebp, bp);
+ R32(eax, ax);
+ R32(eip, ip);
+ R32(esp, sp);
+
+ case offsetof(struct user32, regs.orig_eax):
+ /*
+ * Sign-extend the value so that orig_eax = -1
+ * causes (long)orig_ax < 0 tests to fire correctly.
+ */
+ regs->orig_ax = (long) (s32) value;
+ break;
- tsk->thread.trap_no = 1;
- tsk->thread.error_code = error_code;
+ case offsetof(struct user32, regs.eflags):
+ return set_flags(child, value);
- memset(&info, 0, sizeof(info));
- info.si_signo = SIGTRAP;
- info.si_code = TRAP_BRKPT;
+ case offsetof(struct user32, u_debugreg[0]) ...
+ offsetof(struct user32, u_debugreg[7]):
+ regno -= offsetof(struct user32, u_debugreg[0]);
+ return ptrace_set_debugreg(child, regno / 4, value);
- /* User-mode ip? */
- info.si_addr = user_mode_vm(regs) ? (void __user *) regs->ip : NULL;
+ default:
+ if (regno > sizeof(struct user32) || (regno & 3))
+ return -EIO;
- /* Send us the fake SIGTRAP */
- force_sig_info(SIGTRAP, &info, tsk);
+ /*
+ * Other dummy fields in the virtual user structure
+ * are ignored
+ */
+ break;
+ }
+ return 0;
}
-/* notification of system call entry/exit
- * - triggered by current->work.syscall_trace
- */
-__attribute__((regparm(3)))
-int do_syscall_trace(struct pt_regs *regs, int entryexit)
+#undef R32
+#undef SEG32
+
+#define R32(l,q) \
+ case offsetof(struct user32, regs.l): \
+ *val = regs->q; break
+
+#define SEG32(rs) \
+ case offsetof(struct user32, regs.rs): \
+ *val = get_segment_reg(child, \
+ offsetof(struct user_regs_struct, rs)); \
+ break
+
+static int getreg32(struct task_struct *child, unsigned regno, u32 *val)
{
- int is_sysemu = test_thread_flag(TIF_SYSCALL_EMU);
- /*
- * With TIF_SYSCALL_EMU set we want to ignore TIF_SINGLESTEP for syscall
- * interception
- */
- int is_singlestep = !is_sysemu && test_thread_flag(TIF_SINGLESTEP);
- int ret = 0;
+ struct pt_regs *regs = task_pt_regs(child);
+
+ switch (regno) {
+
+ SEG32(ds);
+ SEG32(es);
+ SEG32(fs);
+ SEG32(gs);
+
+ R32(cs, cs);
+ R32(ss, ss);
+ R32(ebx, bx);
+ R32(ecx, cx);
+ R32(edx, dx);
+ R32(edi, di);
+ R32(esi, si);
+ R32(ebp, bp);
+ R32(eax, ax);
+ R32(orig_eax, orig_ax);
+ R32(eip, ip);
+ R32(esp, sp);
+
+ case offsetof(struct user32, regs.eflags):
+ *val = get_flags(child);
+ break;
- /* do the secure computing check first */
- if (!entryexit)
- secure_computing(regs->orig_ax);
+ case offsetof(struct user32, u_debugreg[0]) ...
+ offsetof(struct user32, u_debugreg[7]):
+ regno -= offsetof(struct user32, u_debugreg[0]);
+ *val = ptrace_get_debugreg(child, regno / 4);
+ break;
- if (unlikely(current->audit_context)) {
- if (entryexit)
- audit_syscall_exit(AUDITSC_RESULT(regs->ax),
- regs->ax);
- /* Debug traps, when using PTRACE_SINGLESTEP, must be sent only
- * on the syscall exit path. Normally, when TIF_SYSCALL_AUDIT is
- * not used, entry.S will call us only on syscall exit, not
- * entry; so when TIF_SYSCALL_AUDIT is used we must avoid
- * calling send_sigtrap() on syscall entry.
- *
- * Note that when PTRACE_SYSEMU_SINGLESTEP is used,
- * is_singlestep is false, despite his name, so we will still do
- * the correct thing.
+ default:
+ if (regno > sizeof(struct user32) || (regno & 3))
+ return -EIO;
+
+ /*
+ * Other dummy fields in the virtual user structure
+ * are ignored
*/
- else if (is_singlestep)
- goto out;
+ *val = 0;
+ break;
}
+ return 0;
+}
- if (!(current->ptrace & PT_PTRACED))
- goto out;
+#undef R32
+#undef SEG32
- /* If a process stops on the 1st tracepoint with SYSCALL_TRACE
- * and then is resumed with SYSEMU_SINGLESTEP, it will come in
- * here. We have to check this and return */
- if (is_sysemu && entryexit)
- return 0;
+static int genregs32_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ if (kbuf) {
+ compat_ulong_t *k = kbuf;
+ while (count > 0) {
+ getreg32(target, pos, k++);
+ count -= sizeof(*k);
+ pos += sizeof(*k);
+ }
+ } else {
+ compat_ulong_t __user *u = ubuf;
+ while (count > 0) {
+ compat_ulong_t word;
+ getreg32(target, pos, &word);
+ if (__put_user(word, u++))
+ return -EFAULT;
+ count -= sizeof(*u);
+ pos += sizeof(*u);
+ }
+ }
- /* Fake a debug trap */
- if (is_singlestep)
- send_sigtrap(current, regs, 0);
+ return 0;
+}
- if (!test_thread_flag(TIF_SYSCALL_TRACE) && !is_sysemu)
- goto out;
+static int genregs32_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret = 0;
+ if (kbuf) {
+ const compat_ulong_t *k = kbuf;
+ while (count > 0 && !ret) {
+ ret = putreg32(target, pos, *k++);
+ count -= sizeof(*k);
+ pos += sizeof(*k);
+ }
+ } else {
+ const compat_ulong_t __user *u = ubuf;
+ while (count > 0 && !ret) {
+ compat_ulong_t word;
+ ret = __get_user(word, u++);
+ if (ret)
+ break;
+ ret = putreg32(target, pos, word);
+ count -= sizeof(*u);
+ pos += sizeof(*u);
+ }
+ }
+ return ret;
+}
- /* the 0x80 provides a way for the tracing parent to distinguish
- between a syscall stop and SIGTRAP delivery */
- /* Note that the debugger could change the result of test_thread_flag!*/
- ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80:0));
+long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
+ compat_ulong_t caddr, compat_ulong_t cdata)
+{
+ unsigned long addr = caddr;
+ unsigned long data = cdata;
+ void __user *datap = compat_ptr(data);
+ int ret;
+ __u32 val;
- /*
- * 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;
+ switch (request) {
+ case PTRACE_PEEKUSR:
+ ret = getreg32(child, addr, &val);
+ if (ret == 0)
+ ret = put_user(val, (__u32 __user *)datap);
+ break;
+
+ case PTRACE_POKEUSR:
+ ret = putreg32(child, addr, data);
+ break;
+
+ case PTRACE_GETREGS: /* Get all gp regs from the child. */
+ return copy_regset_to_user(child, &user_x86_32_view,
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct32),
+ datap);
+
+ case PTRACE_SETREGS: /* Set all gp regs in the child. */
+ return copy_regset_from_user(child, &user_x86_32_view,
+ REGSET_GENERAL, 0,
+ sizeof(struct user_regs_struct32),
+ datap);
+
+ case PTRACE_GETFPREGS: /* Get the child FPU state. */
+ return copy_regset_to_user(child, &user_x86_32_view,
+ REGSET_FP, 0,
+ sizeof(struct user_i387_ia32_struct),
+ datap);
+
+ case PTRACE_SETFPREGS: /* Set the child FPU state. */
+ return copy_regset_from_user(
+ child, &user_x86_32_view, REGSET_FP,
+ 0, sizeof(struct user_i387_ia32_struct), datap);
+
+ case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */
+ return copy_regset_to_user(child, &user_x86_32_view,
+ REGSET_XFP, 0,
+ sizeof(struct user32_fxsr_struct),
+ datap);
+
+ case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */
+ return copy_regset_from_user(child, &user_x86_32_view,
+ REGSET_XFP, 0,
+ sizeof(struct user32_fxsr_struct),
+ datap);
+
+ case PTRACE_GET_THREAD_AREA:
+ case PTRACE_SET_THREAD_AREA:
+#ifdef CONFIG_X86_PTRACE_BTS
+ case PTRACE_BTS_CONFIG:
+ case PTRACE_BTS_STATUS:
+ case PTRACE_BTS_SIZE:
+ case PTRACE_BTS_GET:
+ case PTRACE_BTS_CLEAR:
+ case PTRACE_BTS_DRAIN:
+#endif /* CONFIG_X86_PTRACE_BTS */
+ return arch_ptrace(child, request, addr, data);
+
+ default:
+ return compat_ptrace_request(child, request, addr, data);
}
- ret = is_sysemu;
-out:
- if (unlikely(current->audit_context) && !entryexit)
- audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax,
- regs->bx, regs->cx, regs->dx, regs->si);
- if (ret == 0)
- return 0;
- regs->orig_ax = -1; /* force skip of syscall restarting */
- if (unlikely(current->audit_context))
- audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
- return 1;
+ return ret;
}
-#else /* CONFIG_X86_64 */
+#endif /* CONFIG_IA32_EMULATION */
+
+#ifdef CONFIG_X86_64
+
+static const struct user_regset x86_64_regsets[] = {
+ [REGSET_GENERAL] = {
+ .core_note_type = NT_PRSTATUS,
+ .n = sizeof(struct user_regs_struct) / sizeof(long),
+ .size = sizeof(long), .align = sizeof(long),
+ .get = genregs_get, .set = genregs_set
+ },
+ [REGSET_FP] = {
+ .core_note_type = NT_PRFPREG,
+ .n = sizeof(struct user_i387_struct) / sizeof(long),
+ .size = sizeof(long), .align = sizeof(long),
+ .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+ },
+ [REGSET_IOPERM64] = {
+ .core_note_type = NT_386_IOPERM,
+ .n = IO_BITMAP_LONGS,
+ .size = sizeof(long), .align = sizeof(long),
+ .active = ioperm_active, .get = ioperm_get
+ },
+};
+
+static const struct user_regset_view user_x86_64_view = {
+ .name = "x86_64", .e_machine = EM_X86_64,
+ .regsets = x86_64_regsets, .n = ARRAY_SIZE(x86_64_regsets)
+};
+
+#else /* CONFIG_X86_32 */
+
+#define user_regs_struct32 user_regs_struct
+#define genregs32_get genregs_get
+#define genregs32_set genregs_set
+
+#define user_i387_ia32_struct user_i387_struct
+#define user32_fxsr_struct user_fxsr_struct
+
+#endif /* CONFIG_X86_64 */
-static void syscall_trace(struct pt_regs *regs)
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+static const struct user_regset x86_32_regsets[] = {
+ [REGSET_GENERAL] = {
+ .core_note_type = NT_PRSTATUS,
+ .n = sizeof(struct user_regs_struct32) / sizeof(u32),
+ .size = sizeof(u32), .align = sizeof(u32),
+ .get = genregs32_get, .set = genregs32_set
+ },
+ [REGSET_FP] = {
+ .core_note_type = NT_PRFPREG,
+ .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
+ .size = sizeof(u32), .align = sizeof(u32),
+ .active = fpregs_active, .get = fpregs_get, .set = fpregs_set
+ },
+ [REGSET_XFP] = {
+ .core_note_type = NT_PRXFPREG,
+ .n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
+ .size = sizeof(u32), .align = sizeof(u32),
+ .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+ },
+ [REGSET_TLS] = {
+ .core_note_type = NT_386_TLS,
+ .n = GDT_ENTRY_TLS_ENTRIES, .bias = GDT_ENTRY_TLS_MIN,
+ .size = sizeof(struct user_desc),
+ .align = sizeof(struct user_desc),
+ .active = regset_tls_active,
+ .get = regset_tls_get, .set = regset_tls_set
+ },
+ [REGSET_IOPERM32] = {
+ .core_note_type = NT_386_IOPERM,
+ .n = IO_BITMAP_BYTES / sizeof(u32),
+ .size = sizeof(u32), .align = sizeof(u32),
+ .active = ioperm_active, .get = ioperm_get
+ },
+};
+
+static const struct user_regset_view user_x86_32_view = {
+ .name = "i386", .e_machine = EM_386,
+ .regsets = x86_32_regsets, .n = ARRAY_SIZE(x86_32_regsets)
+};
+#endif
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
{
+#ifdef CONFIG_IA32_EMULATION
+ if (test_tsk_thread_flag(task, TIF_IA32))
+#endif
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+ return &user_x86_32_view;
+#endif
+#ifdef CONFIG_X86_64
+ return &user_x86_64_view;
+#endif
+}
+
+void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
+ int error_code, int si_code)
+{
+ struct siginfo info;
-#if 0
- printk("trace %s ip %lx sp %lx ax %d origrax %d caller %lx tiflags %x ptrace %x\n",
- current->comm,
- regs->ip, regs->sp, regs->ax, regs->orig_ax, __builtin_return_address(0),
- current_thread_info()->flags, current->ptrace);
+ tsk->thread.trap_no = 1;
+ tsk->thread.error_code = error_code;
+
+ memset(&info, 0, sizeof(info));
+ info.si_signo = SIGTRAP;
+ info.si_code = si_code;
+
+ /* User-mode ip? */
+ info.si_addr = user_mode_vm(regs) ? (void __user *) regs->ip : NULL;
+
+ /* Send us the fake SIGTRAP */
+ force_sig_info(SIGTRAP, &info, tsk);
+}
+
+
+#ifdef CONFIG_X86_32
+# define IS_IA32 1
+#elif defined CONFIG_IA32_EMULATION
+# define IS_IA32 test_thread_flag(TIF_IA32)
+#else
+# define IS_IA32 0
#endif
- ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
- ? 0x80 : 0));
+/*
+ * We must return the syscall number to actually look up in the table.
+ * This can be -1L to skip running any syscall at all.
+ */
+asmregparm long syscall_trace_enter(struct pt_regs *regs)
+{
+ long ret = 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 we stepped into a sysenter/syscall insn, it trapped in
+ * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
+ * If user-mode had set TF itself, then it's still clear from
+ * do_debug() and we need to set it again to restore the user
+ * state. If we entered on the slow path, TF was already set.
*/
- if (current->exit_code) {
- send_sig(current->exit_code, current, 1);
- current->exit_code = 0;
- }
-}
+ if (test_thread_flag(TIF_SINGLESTEP))
+ regs->flags |= X86_EFLAGS_TF;
-asmlinkage void syscall_trace_enter(struct pt_regs *regs)
-{
/* do the secure computing check first */
secure_computing(regs->orig_ax);
- if (test_thread_flag(TIF_SYSCALL_TRACE)
- && (current->ptrace & PT_PTRACED))
- syscall_trace(regs);
+ if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
+ ret = -1L;
+
+ if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
+ tracehook_report_syscall_entry(regs))
+ ret = -1L;
if (unlikely(current->audit_context)) {
- if (test_thread_flag(TIF_IA32)) {
+ if (IS_IA32)
audit_syscall_entry(AUDIT_ARCH_I386,
regs->orig_ax,
regs->bx, regs->cx,
regs->dx, regs->si);
- } else {
+#ifdef CONFIG_X86_64
+ else
audit_syscall_entry(AUDIT_ARCH_X86_64,
regs->orig_ax,
regs->di, regs->si,
regs->dx, regs->r10);
- }
+#endif
}
+
+ return ret ?: regs->orig_ax;
}
-asmlinkage void syscall_trace_leave(struct pt_regs *regs)
+asmregparm void syscall_trace_leave(struct pt_regs *regs)
{
if (unlikely(current->audit_context))
audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
- if ((test_thread_flag(TIF_SYSCALL_TRACE)
- || test_thread_flag(TIF_SINGLESTEP))
- && (current->ptrace & PT_PTRACED))
- syscall_trace(regs);
-}
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall_exit(regs, 0);
-#endif /* CONFIG_X86_32 */
+ /*
+ * If TIF_SYSCALL_EMU is set, we only get here because of
+ * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
+ * We already reported this syscall instruction in
+ * syscall_trace_enter(), so don't do any more now.
+ */
+ if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
+ return;
+
+ /*
+ * If we are single-stepping, synthesize a trap to follow the
+ * system call instruction.
+ */
+ if (test_thread_flag(TIF_SINGLESTEP) &&
+ tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL))
+ send_sigtrap(current, regs, 0, TRAP_BRKPT);
+}