#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 <linux/signal.h>
+#include <linux/workqueue.h>
+#include <linux/perf_event.h>
+#include <linux/hw_breakpoint.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/prctl.h>
#include <asm/proto.h>
#include <asm/ds.h>
+#include <asm/hw_breakpoint.h>
#include "tls.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
enum x86_regset {
REGSET_GENERAL,
REGSET_FP,
REGSET_XFP,
+ REGSET_IOPERM64 = REGSET_XFP,
REGSET_TLS,
+ REGSET_IOPERM32,
+};
+
+struct pt_regs_offset {
+ const char *name;
+ int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+#ifdef CONFIG_X86_64
+ REG_OFFSET_NAME(r15),
+ REG_OFFSET_NAME(r14),
+ REG_OFFSET_NAME(r13),
+ REG_OFFSET_NAME(r12),
+ REG_OFFSET_NAME(r11),
+ REG_OFFSET_NAME(r10),
+ REG_OFFSET_NAME(r9),
+ REG_OFFSET_NAME(r8),
+#endif
+ REG_OFFSET_NAME(bx),
+ REG_OFFSET_NAME(cx),
+ REG_OFFSET_NAME(dx),
+ REG_OFFSET_NAME(si),
+ REG_OFFSET_NAME(di),
+ REG_OFFSET_NAME(bp),
+ REG_OFFSET_NAME(ax),
+#ifdef CONFIG_X86_32
+ REG_OFFSET_NAME(ds),
+ REG_OFFSET_NAME(es),
+ REG_OFFSET_NAME(fs),
+ REG_OFFSET_NAME(gs),
+#endif
+ REG_OFFSET_NAME(orig_ax),
+ REG_OFFSET_NAME(ip),
+ REG_OFFSET_NAME(cs),
+ REG_OFFSET_NAME(flags),
+ REG_OFFSET_NAME(sp),
+ REG_OFFSET_NAME(ss),
+ REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name: the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+ const struct pt_regs_offset *roff;
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (!strcmp(roff->name, name))
+ return roff->offset;
+ return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset: the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+ const struct pt_regs_offset *roff;
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (roff->offset == offset)
+ return roff->name;
+ return NULL;
+}
+
+static const int arg_offs_table[] = {
+#ifdef CONFIG_X86_32
+ [0] = offsetof(struct pt_regs, ax),
+ [1] = offsetof(struct pt_regs, dx),
+ [2] = offsetof(struct pt_regs, cx)
+#else /* CONFIG_X86_64 */
+ [0] = offsetof(struct pt_regs, di),
+ [1] = offsetof(struct pt_regs, si),
+ [2] = offsetof(struct pt_regs, dx),
+ [3] = offsetof(struct pt_regs, cx),
+ [4] = offsetof(struct pt_regs, r8),
+ [5] = offsetof(struct pt_regs, r9)
+#endif
};
+/**
+ * regs_get_argument_nth() - get Nth argument at function call
+ * @regs: pt_regs which contains registers at function entry.
+ * @n: argument number.
+ *
+ * regs_get_argument_nth() returns @n th argument of a function call.
+ * Since usually the kernel stack will be changed right after function entry,
+ * you must use this at function entry. If the @n th entry is NOT in the
+ * kernel stack or pt_regs, this returns 0.
+ */
+unsigned long regs_get_argument_nth(struct pt_regs *regs, unsigned int n)
+{
+ if (n < ARRAY_SIZE(arg_offs_table))
+ return *(unsigned long *)((char *)regs + arg_offs_table[n]);
+ else {
+ /*
+ * The typical case: arg n is on the stack.
+ * (Note: stack[0] = return address, so skip it)
+ */
+ n -= ARRAY_SIZE(arg_offs_table);
+ return regs_get_kernel_stack_nth(regs, 1 + n);
+ }
+}
+
/*
* does not yet catch signals sent when the child dies.
* in exit.c or in signal.c.
#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;
}
break;
case offsetof(struct user_regs_struct, gs):
- task->thread.gs = value;
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;
}
-static unsigned long debugreg_addr_limit(struct task_struct *task)
-{
- return TASK_SIZE - 3;
-}
-
#else /* CONFIG_X86_64 */
#define FLAG_MASK (FLAG_MASK_32 | X86_EFLAGS_NT)
return 0;
}
-static unsigned long debugreg_addr_limit(struct task_struct *task)
-{
-#ifdef CONFIG_IA32_EMULATION
- if (test_tsk_thread_flag(task, TIF_IA32))
- return IA32_PAGE_OFFSET - 3;
-#endif
- return TASK_SIZE64 - 7;
-}
-
#endif /* CONFIG_X86_32 */
static unsigned long get_flags(struct task_struct *task)
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 ret;
}
+static void ptrace_triggered(struct perf_event *bp, int nmi,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ int i;
+ struct thread_struct *thread = &(current->thread);
+
+ /*
+ * Store in the virtual DR6 register the fact that the breakpoint
+ * was hit so the thread's debugger will see it.
+ */
+ for (i = 0; i < HBP_NUM; i++) {
+ if (thread->ptrace_bps[i] == bp)
+ break;
+ }
+
+ thread->debugreg6 |= (DR_TRAP0 << i);
+}
+
/*
- * This function is trivial and will be inlined by the compiler.
- * Having it separates the implementation details of debug
- * registers from the interface details of ptrace.
+ * Walk through every ptrace breakpoints for this thread and
+ * build the dr7 value on top of their attributes.
+ *
*/
-static unsigned long ptrace_get_debugreg(struct task_struct *child, int n)
+static unsigned long ptrace_get_dr7(struct perf_event *bp[])
{
- switch (n) {
- case 0: return child->thread.debugreg0;
- case 1: return child->thread.debugreg1;
- case 2: return child->thread.debugreg2;
- case 3: return child->thread.debugreg3;
- case 6: return child->thread.debugreg6;
- case 7: return child->thread.debugreg7;
+ int i;
+ int dr7 = 0;
+ struct arch_hw_breakpoint *info;
+
+ for (i = 0; i < HBP_NUM; i++) {
+ if (bp[i] && !bp[i]->attr.disabled) {
+ info = counter_arch_bp(bp[i]);
+ dr7 |= encode_dr7(i, info->len, info->type);
+ }
}
- return 0;
+
+ return dr7;
}
-static int ptrace_set_debugreg(struct task_struct *child,
- int n, unsigned long data)
+static int
+ptrace_modify_breakpoint(struct perf_event *bp, int len, int type,
+ struct task_struct *tsk, int disabled)
{
- int i;
+ int err;
+ int gen_len, gen_type;
+ struct perf_event_attr attr;
- if (unlikely(n == 4 || n == 5))
- return -EIO;
+ /*
+ * We shoud have at least an inactive breakpoint at this
+ * slot. It means the user is writing dr7 without having
+ * written the address register first
+ */
+ if (!bp)
+ return -EINVAL;
- if (n < 4 && unlikely(data >= debugreg_addr_limit(child)))
- return -EIO;
+ err = arch_bp_generic_fields(len, type, &gen_len, &gen_type);
+ if (err)
+ return err;
- switch (n) {
- case 0: child->thread.debugreg0 = data; break;
- case 1: child->thread.debugreg1 = data; break;
- case 2: child->thread.debugreg2 = data; break;
- case 3: child->thread.debugreg3 = data; break;
+ attr = bp->attr;
+ attr.bp_len = gen_len;
+ attr.bp_type = gen_type;
+ attr.disabled = disabled;
- case 6:
- if ((data & ~0xffffffffUL) != 0)
- return -EIO;
- child->thread.debugreg6 = data;
- break;
+ return modify_user_hw_breakpoint(bp, &attr);
+}
+
+/*
+ * Handle ptrace writes to debug register 7.
+ */
+static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
+{
+ struct thread_struct *thread = &(tsk->thread);
+ unsigned long old_dr7;
+ int i, orig_ret = 0, rc = 0;
+ int enabled, second_pass = 0;
+ unsigned len, type;
+ struct perf_event *bp;
+
+ data &= ~DR_CONTROL_RESERVED;
+ old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
+restore:
+ /*
+ * Loop through all the hardware breakpoints, making the
+ * appropriate changes to each.
+ */
+ for (i = 0; i < HBP_NUM; i++) {
+ enabled = decode_dr7(data, i, &len, &type);
+ bp = thread->ptrace_bps[i];
+
+ if (!enabled) {
+ if (bp) {
+ /*
+ * Don't unregister the breakpoints right-away,
+ * unless all register_user_hw_breakpoint()
+ * requests have succeeded. This prevents
+ * any window of opportunity for debug
+ * register grabbing by other users.
+ */
+ if (!second_pass)
+ continue;
+
+ rc = ptrace_modify_breakpoint(bp, len, type,
+ tsk, 1);
+ if (rc)
+ break;
+ }
+ continue;
+ }
+
+ rc = ptrace_modify_breakpoint(bp, len, type, tsk, 0);
+ if (rc)
+ break;
+ }
+ /*
+ * Make a second pass to free the remaining unused breakpoints
+ * or to restore the original breakpoints if an error occurred.
+ */
+ if (!second_pass) {
+ second_pass = 1;
+ if (rc < 0) {
+ orig_ret = rc;
+ data = old_dr7;
+ }
+ goto restore;
+ }
+ return ((orig_ret < 0) ? orig_ret : rc);
+}
+
+/*
+ * Handle PTRACE_PEEKUSR calls for the debug register area.
+ */
+static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
+{
+ struct thread_struct *thread = &(tsk->thread);
+ unsigned long val = 0;
- case 7:
+ if (n < HBP_NUM) {
+ struct perf_event *bp;
+ bp = thread->ptrace_bps[n];
+ if (!bp)
+ return 0;
+ val = bp->hw.info.address;
+ } else if (n == 6) {
+ val = thread->debugreg6;
+ } else if (n == 7) {
+ val = ptrace_get_dr7(thread->ptrace_bps);
+ }
+ return val;
+}
+
+static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
+ unsigned long addr)
+{
+ struct perf_event *bp;
+ struct thread_struct *t = &tsk->thread;
+ struct perf_event_attr attr;
+
+ if (!t->ptrace_bps[nr]) {
+ hw_breakpoint_init(&attr);
/*
- * 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. [32-bit]
- * - 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)
+ * Put stub len and type to register (reserve) an inactive but
+ * correct bp
*/
-#ifdef CONFIG_X86_32
-#define DR7_MASK 0x5f54
-#else
-#define DR7_MASK 0x5554
-#endif
- data &= ~DR_CONTROL_RESERVED;
- for (i = 0; i < 4; i++)
- if ((DR7_MASK >> ((data >> (16 + 4*i)) & 0xf)) & 1)
- return -EIO;
- child->thread.debugreg7 = data;
- if (data)
- set_tsk_thread_flag(child, TIF_DEBUG);
- else
- clear_tsk_thread_flag(child, TIF_DEBUG);
- break;
+ attr.bp_addr = addr;
+ attr.bp_len = HW_BREAKPOINT_LEN_1;
+ attr.bp_type = HW_BREAKPOINT_W;
+ attr.disabled = 1;
+
+ bp = register_user_hw_breakpoint(&attr, ptrace_triggered, tsk);
+
+ /*
+ * CHECKME: the previous code returned -EIO if the addr wasn't
+ * a valid task virtual addr. The new one will return -EINVAL in
+ * this case.
+ * -EINVAL may be what we want for in-kernel breakpoints users,
+ * but -EIO looks better for ptrace, since we refuse a register
+ * writing for the user. And anyway this is the previous
+ * behaviour.
+ */
+ if (IS_ERR(bp))
+ return PTR_ERR(bp);
+
+ t->ptrace_bps[nr] = bp;
+ } else {
+ int err;
+
+ bp = t->ptrace_bps[nr];
+
+ attr = bp->attr;
+ attr.bp_addr = addr;
+ err = modify_user_hw_breakpoint(bp, &attr);
+ if (err)
+ return err;
}
+
return 0;
}
-#ifdef X86_BTS
+/*
+ * Handle PTRACE_POKEUSR calls for the debug register area.
+ */
+int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val)
+{
+ struct thread_struct *thread = &(tsk->thread);
+ int rc = 0;
+
+ /* There are no DR4 or DR5 registers */
+ if (n == 4 || n == 5)
+ return -EIO;
+
+ if (n == 6) {
+ thread->debugreg6 = val;
+ goto ret_path;
+ }
+ if (n < HBP_NUM) {
+ rc = ptrace_set_breakpoint_addr(tsk, n, val);
+ if (rc)
+ return rc;
+ }
+ /* All that's left is DR7 */
+ if (n == 7)
+ rc = ptrace_write_dr7(tsk, val);
+
+ret_path:
+ return rc;
+}
+
+/*
+ * 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 ptrace_bts_get_size(struct task_struct *child)
+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 (!child->thread.ds_area_msr)
+ if (!target->thread.io_bitmap_ptr)
return -ENXIO;
- return ds_get_bts_index((void *)child->thread.ds_area_msr);
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ target->thread.io_bitmap_ptr,
+ 0, IO_BITMAP_BYTES);
}
-static int ptrace_bts_read_record(struct task_struct *child,
- long index,
- struct bts_struct __user *out)
+#ifdef CONFIG_X86_PTRACE_BTS
+/*
+ * A branch trace store context.
+ *
+ * Contexts may only be installed by ptrace_bts_config() and only for
+ * ptraced tasks.
+ *
+ * Contexts are destroyed when the tracee is detached from the tracer.
+ * The actual destruction work requires interrupts enabled, so the
+ * work is deferred and will be scheduled during __ptrace_unlink().
+ *
+ * Contexts hold an additional task_struct reference on the traced
+ * task, as well as a reference on the tracer's mm.
+ *
+ * Ptrace already holds a task_struct for the duration of ptrace operations,
+ * but since destruction is deferred, it may be executed after both
+ * tracer and tracee exited.
+ */
+struct bts_context {
+ /* The branch trace handle. */
+ struct bts_tracer *tracer;
+
+ /* The buffer used to store the branch trace and its size. */
+ void *buffer;
+ unsigned int size;
+
+ /* The mm that paid for the above buffer. */
+ struct mm_struct *mm;
+
+ /* The task this context belongs to. */
+ struct task_struct *task;
+
+ /* The signal to send on a bts buffer overflow. */
+ unsigned int bts_ovfl_signal;
+
+ /* The work struct to destroy a context. */
+ struct work_struct work;
+};
+
+static int alloc_bts_buffer(struct bts_context *context, unsigned int size)
{
- struct bts_struct ret;
- int retval;
- int bts_end;
- int bts_index;
+ void *buffer = NULL;
+ int err = -ENOMEM;
- if (!child->thread.ds_area_msr)
- return -ENXIO;
+ err = account_locked_memory(current->mm, current->signal->rlim, size);
+ if (err < 0)
+ return err;
- if (index < 0)
- return -EINVAL;
+ buffer = kzalloc(size, GFP_KERNEL);
+ if (!buffer)
+ goto out_refund;
- bts_end = ds_get_bts_end((void *)child->thread.ds_area_msr);
- if (bts_end <= index)
- return -EINVAL;
+ context->buffer = buffer;
+ context->size = size;
+ context->mm = get_task_mm(current);
- /* translate the ptrace bts index into the ds bts index */
- bts_index = ds_get_bts_index((void *)child->thread.ds_area_msr);
- bts_index -= (index + 1);
- if (bts_index < 0)
- bts_index += bts_end;
+ return 0;
- retval = ds_read_bts((void *)child->thread.ds_area_msr,
- bts_index, &ret);
- if (retval < 0)
- return retval;
+ out_refund:
+ refund_locked_memory(current->mm, size);
+ return err;
+}
- if (copy_to_user(out, &ret, sizeof(ret)))
- return -EFAULT;
+static inline void free_bts_buffer(struct bts_context *context)
+{
+ if (!context->buffer)
+ return;
+
+ kfree(context->buffer);
+ context->buffer = NULL;
- return sizeof(ret);
+ refund_locked_memory(context->mm, context->size);
+ context->size = 0;
+
+ mmput(context->mm);
+ context->mm = NULL;
}
-static int ptrace_bts_clear(struct task_struct *child)
+static void free_bts_context_work(struct work_struct *w)
{
- if (!child->thread.ds_area_msr)
- return -ENXIO;
+ struct bts_context *context;
+
+ context = container_of(w, struct bts_context, work);
+
+ ds_release_bts(context->tracer);
+ put_task_struct(context->task);
+ free_bts_buffer(context);
+ kfree(context);
+}
+
+static inline void free_bts_context(struct bts_context *context)
+{
+ INIT_WORK(&context->work, free_bts_context_work);
+ schedule_work(&context->work);
+}
+
+static inline struct bts_context *alloc_bts_context(struct task_struct *task)
+{
+ struct bts_context *context = kzalloc(sizeof(*context), GFP_KERNEL);
+ if (context) {
+ context->task = task;
+ task->bts = context;
+
+ get_task_struct(task);
+ }
- return ds_clear((void *)child->thread.ds_area_msr);
+ return context;
+}
+
+static int ptrace_bts_read_record(struct task_struct *child, size_t index,
+ struct bts_struct __user *out)
+{
+ struct bts_context *context;
+ const struct bts_trace *trace;
+ struct bts_struct bts;
+ const unsigned char *at;
+ int error;
+
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
+ trace = ds_read_bts(context->tracer);
+ if (!trace)
+ return -ESRCH;
+
+ 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(context->tracer, 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)
{
- int end, i;
- void *ds = (void *)child->thread.ds_area_msr;
+ struct bts_context *context;
+ const struct bts_trace *trace;
+ const unsigned char *at;
+ int error, drained = 0;
- if (!ds)
- return -ENXIO;
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
+ trace = ds_read_bts(context->tracer);
+ if (!trace)
+ return -ESRCH;
- end = ds_get_bts_index(ds);
- if (end <= 0)
- return end;
+ if (!trace->read)
+ return -EOPNOTSUPP;
- if (size < (end * sizeof(struct bts_struct)))
+ if (size < (trace->ds.top - trace->ds.begin))
return -EIO;
- for (i = 0; i < end; i++, out++) {
- struct bts_struct ret;
- int retval;
+ for (at = trace->ds.begin; (void *)at < trace->ds.top;
+ out++, drained++, at += trace->ds.size) {
+ struct bts_struct bts;
- retval = ds_read_bts(ds, i, &ret);
- if (retval < 0)
- return retval;
+ error = trace->read(context->tracer, at, &bts);
+ if (error < 0)
+ return error;
- if (copy_to_user(out, &ret, sizeof(ret)))
+ if (copy_to_user(out, &bts, sizeof(bts)))
return -EFAULT;
}
- ds_clear(ds);
+ memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
- return end;
+ error = ds_reset_bts(context->tracer);
+ if (error < 0)
+ return error;
+
+ return drained;
}
static int ptrace_bts_config(struct task_struct *child,
long cfg_size,
const struct ptrace_bts_config __user *ucfg)
{
+ struct bts_context *context;
struct ptrace_bts_config cfg;
- int bts_size, ret = 0;
- void *ds;
+ unsigned int flags = 0;
if (cfg_size < sizeof(cfg))
return -EIO;
if (copy_from_user(&cfg, ucfg, sizeof(cfg)))
return -EFAULT;
- if ((int)cfg.size < 0)
- return -EINVAL;
+ context = child->bts;
+ if (!context)
+ context = alloc_bts_context(child);
+ if (!context)
+ return -ENOMEM;
- bts_size = 0;
- ds = (void *)child->thread.ds_area_msr;
- if (ds) {
- bts_size = ds_get_bts_size(ds);
- if (bts_size < 0)
- return bts_size;
+ if (cfg.flags & PTRACE_BTS_O_SIGNAL) {
+ if (!cfg.signal)
+ return -EINVAL;
+
+ return -EOPNOTSUPP;
+ context->bts_ovfl_signal = cfg.signal;
}
- cfg.size = PAGE_ALIGN(cfg.size);
- if (bts_size != cfg.size) {
- ret = ptrace_bts_realloc(child, cfg.size,
- cfg.flags & PTRACE_BTS_O_CUT_SIZE);
- if (ret < 0)
- goto errout;
+ ds_release_bts(context->tracer);
+ context->tracer = NULL;
- ds = (void *)child->thread.ds_area_msr;
- }
+ if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) {
+ int err;
- if (cfg.flags & PTRACE_BTS_O_SIGNAL)
- ret = ds_set_overflow(ds, DS_O_SIGNAL);
- else
- ret = ds_set_overflow(ds, DS_O_WRAP);
- if (ret < 0)
- goto errout;
+ free_bts_buffer(context);
+ if (!cfg.size)
+ return 0;
+
+ err = alloc_bts_buffer(context, cfg.size);
+ if (err < 0)
+ return err;
+ }
if (cfg.flags & PTRACE_BTS_O_TRACE)
- child->thread.debugctlmsr |= ds_debugctl_mask();
- else
- child->thread.debugctlmsr &= ~ds_debugctl_mask();
+ flags |= BTS_USER;
if (cfg.flags & PTRACE_BTS_O_SCHED)
- set_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
- else
- clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
+ flags |= BTS_TIMESTAMPS;
- ret = sizeof(cfg);
+ context->tracer =
+ ds_request_bts_task(child, context->buffer, context->size,
+ NULL, (size_t)-1, flags);
+ if (unlikely(IS_ERR(context->tracer))) {
+ int error = PTR_ERR(context->tracer);
-out:
- if (child->thread.debugctlmsr)
- set_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
- else
- clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
-
- return ret;
+ free_bts_buffer(context);
+ context->tracer = NULL;
+ return error;
+ }
-errout:
- child->thread.debugctlmsr &= ~ds_debugctl_mask();
- clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
- goto out;
+ return sizeof(cfg);
}
static int ptrace_bts_status(struct task_struct *child,
long cfg_size,
struct ptrace_bts_config __user *ucfg)
{
- void *ds = (void *)child->thread.ds_area_msr;
+ struct bts_context *context;
+ const struct bts_trace *trace;
struct ptrace_bts_config cfg;
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
if (cfg_size < sizeof(cfg))
return -EIO;
- memset(&cfg, 0, sizeof(cfg));
-
- if (ds) {
- cfg.size = ds_get_bts_size(ds);
+ trace = ds_read_bts(context->tracer);
+ if (!trace)
+ return -ESRCH;
- if (ds_get_overflow(ds) == DS_O_SIGNAL)
- cfg.flags |= PTRACE_BTS_O_SIGNAL;
+ memset(&cfg, 0, sizeof(cfg));
+ cfg.size = trace->ds.end - trace->ds.begin;
+ cfg.signal = context->bts_ovfl_signal;
+ cfg.bts_size = sizeof(struct bts_struct);
- if (test_tsk_thread_flag(child, TIF_DEBUGCTLMSR) &&
- child->thread.debugctlmsr & ds_debugctl_mask())
- cfg.flags |= PTRACE_BTS_O_TRACE;
+ if (cfg.signal)
+ cfg.flags |= PTRACE_BTS_O_SIGNAL;
- if (test_tsk_thread_flag(child, TIF_BTS_TRACE_TS))
- cfg.flags |= PTRACE_BTS_O_SCHED;
- }
+ if (trace->ds.flags & BTS_USER)
+ cfg.flags |= PTRACE_BTS_O_TRACE;
- cfg.bts_size = sizeof(struct bts_struct);
+ 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_write_record(struct task_struct *child,
- const struct bts_struct *in)
+static int ptrace_bts_clear(struct task_struct *child)
{
- int retval;
+ struct bts_context *context;
+ const struct bts_trace *trace;
- if (!child->thread.ds_area_msr)
- return -ENXIO;
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
+
+ trace = ds_read_bts(context->tracer);
+ if (!trace)
+ return -ESRCH;
- retval = ds_write_bts((void *)child->thread.ds_area_msr, in);
- if (retval)
- return retval;
+ memset(trace->ds.begin, 0, trace->ds.n * trace->ds.size);
- return sizeof(*in);
+ return ds_reset_bts(context->tracer);
}
-static int ptrace_bts_realloc(struct task_struct *child,
- int size, int reduce_size)
+static int ptrace_bts_size(struct task_struct *child)
{
- unsigned long rlim, vm;
- int ret, old_size;
-
- if (size < 0)
- return -EINVAL;
+ struct bts_context *context;
+ const struct bts_trace *trace;
- old_size = ds_get_bts_size((void *)child->thread.ds_area_msr);
- if (old_size < 0)
- return old_size;
+ context = child->bts;
+ if (!context)
+ return -ESRCH;
- ret = ds_free((void **)&child->thread.ds_area_msr);
- if (ret < 0)
- goto out;
+ trace = ds_read_bts(context->tracer);
+ if (!trace)
+ return -ESRCH;
- size >>= PAGE_SHIFT;
- old_size >>= PAGE_SHIFT;
-
- current->mm->total_vm -= old_size;
- current->mm->locked_vm -= old_size;
-
- if (size == 0)
- goto out;
-
- rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
- vm = current->mm->total_vm + size;
- if (rlim < vm) {
- ret = -ENOMEM;
-
- if (!reduce_size)
- goto out;
-
- size = rlim - current->mm->total_vm;
- if (size <= 0)
- goto out;
- }
-
- rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
- vm = current->mm->locked_vm + size;
- if (rlim < vm) {
- ret = -ENOMEM;
-
- if (!reduce_size)
- goto out;
-
- size = rlim - current->mm->locked_vm;
- if (size <= 0)
- goto out;
- }
-
- ret = ds_allocate((void **)&child->thread.ds_area_msr,
- size << PAGE_SHIFT);
- if (ret < 0)
- goto out;
-
- current->mm->total_vm += size;
- current->mm->locked_vm += size;
-
-out:
- if (child->thread.ds_area_msr)
- set_tsk_thread_flag(child, TIF_DS_AREA_MSR);
- else
- clear_tsk_thread_flag(child, TIF_DS_AREA_MSR);
-
- return ret;
+ return (trace->ds.top - trace->ds.begin) / trace->ds.size;
}
-void ptrace_bts_take_timestamp(struct task_struct *tsk,
- enum bts_qualifier qualifier)
+/*
+ * Called from __ptrace_unlink() after the child has been moved back
+ * to its original parent.
+ */
+void ptrace_bts_untrace(struct task_struct *child)
{
- struct bts_struct rec = {
- .qualifier = qualifier,
- .variant.jiffies = jiffies_64
- };
-
- ptrace_bts_write_record(tsk, &rec);
+ if (unlikely(child->bts)) {
+ free_bts_context(child->bts);
+ child->bts = NULL;
+ }
}
-#endif /* X86_BTS */
+#endif /* CONFIG_X86_PTRACE_BTS */
/*
* Called by kernel/ptrace.c when detaching..
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
#endif
- if (child->thread.ds_area_msr) {
-#ifdef X86_BTS
- ptrace_bts_realloc(child, 0, 0);
-#endif
- child->thread.debugctlmsr &= ~ds_debugctl_mask();
- if (!child->thread.debugctlmsr)
- clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
- clear_tsk_thread_flag(child, TIF_BTS_TRACE_TS);
- }
}
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
return copy_regset_to_user(child, &user_x86_32_view,
REGSET_XFP,
0, sizeof(struct user_fxsr_struct),
- datap);
+ 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);
+ datap) ? -EIO : 0;
#endif
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
/*
* These bits need more cooking - not enabled yet:
*/
-#ifdef X86_BTS
+#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_SIZE:
- ret = ptrace_bts_get_size(child);
+ ret = ptrace_bts_size(child);
break;
case PTRACE_BTS_GET:
ret = ptrace_bts_drain
(child, data, (struct bts_struct __user *) addr);
break;
-#endif
+#endif /* CONFIG_X86_PTRACE_BTS */
default:
ret = ptrace_request(child, request, addr, data);
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.
+ * A 32-bit debugger setting orig_eax means to restore
+ * the state of the task restarting a 32-bit syscall.
+ * Make sure we interpret the -ERESTART* codes correctly
+ * in case the task is not actually still sitting at the
+ * exit from a 32-bit syscall with TS_COMPAT still set.
*/
- regs->orig_ax = (long) (s32) value;
+ regs->orig_ax = value;
+ if (syscall_get_nr(child, regs) >= 0)
+ task_thread_info(child)->status |= TS_COMPAT;
break;
case offsetof(struct user32, regs.eflags):
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:
.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 = {
#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 */
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
},
[REGSET_FP] = {
.core_note_type = NT_PRFPREG,
- .n = sizeof(struct user_i387_struct) / sizeof(u32),
+ .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 user_i387_struct) / sizeof(u32),
+ .n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
.size = sizeof(u32), .align = sizeof(u32),
.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
},
.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 = {
#endif
}
-#ifdef CONFIG_X86_32
-
-void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code)
+void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
+ int error_code, int si_code)
{
struct siginfo info;
memset(&info, 0, sizeof(info));
info.si_signo = SIGTRAP;
- info.si_code = TRAP_BRKPT;
+ info.si_code = si_code;
/* User-mode ip? */
info.si_addr = user_mode_vm(regs) ? (void __user *) regs->ip : NULL;
force_sig_info(SIGTRAP, &info, tsk);
}
-/* notification of system call entry/exit
- * - triggered by current->work.syscall_trace
- */
-int do_syscall_trace(struct pt_regs *regs, int entryexit)
-{
- 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;
-
- /* do the secure computing check first */
- if (!entryexit)
- secure_computing(regs->orig_ax);
-
- 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.
- */
- else if (is_singlestep)
- goto out;
- }
-
- if (!(current->ptrace & PT_PTRACED))
- goto out;
-
- /* 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;
-
- /* Fake a debug trap */
- if (is_singlestep)
- send_sigtrap(current, regs, 0);
-
- if (!test_thread_flag(TIF_SYSCALL_TRACE) && !is_sysemu)
- goto out;
-
- /* 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));
- /*
- * 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;
- }
- 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;
-}
-
-#else /* CONFIG_X86_64 */
+#ifdef CONFIG_X86_32
+# define IS_IA32 1
+#elif defined CONFIG_IA32_EMULATION
+# define IS_IA32 is_compat_task()
+#else
+# define IS_IA32 0
+#endif
-static void syscall_trace(struct pt_regs *regs)
+/*
+ * 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;
-#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);
-#endif
-
- 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 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(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_enter(regs, regs->orig_ax);
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 (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_exit(regs, regs->ax);
-#endif /* CONFIG_X86_32 */
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall_exit(regs, 0);
+
+ /*
+ * 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))
+ send_sigtrap(current, regs, 0, TRAP_BRKPT);
+}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff