#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/ds.h>
#include <asm/hw_breakpoint.h>
-#include <trace/syscall.h>
-
#include "tls.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
enum x86_regset {
REGSET_GENERAL,
REGSET_FP,
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.
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);
+}
+
/*
- * Decode the length and type bits for a particular breakpoint as
- * stored in debug register 7. Return the "enabled" status.
+ * Walk through every ptrace breakpoints for this thread and
+ * build the dr7 value on top of their attributes.
+ *
*/
-static int decode_dr7(unsigned long dr7, int bpnum, unsigned *len,
- unsigned *type)
+static unsigned long ptrace_get_dr7(struct perf_event *bp[])
{
- int bp_info = dr7 >> (DR_CONTROL_SHIFT + bpnum * DR_CONTROL_SIZE);
+ int i;
+ int dr7 = 0;
+ struct arch_hw_breakpoint *info;
- *len = (bp_info & 0xc) | 0x40;
- *type = (bp_info & 0x3) | 0x80;
- return (dr7 >> (bpnum * DR_ENABLE_SIZE)) & 0x3;
+ 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 dr7;
}
-static void ptrace_triggered(struct hw_breakpoint *bp, struct pt_regs *regs)
+static int
+ptrace_modify_breakpoint(struct perf_event *bp, int len, int type,
+ struct task_struct *tsk, int disabled)
{
- struct thread_struct *thread = &(current->thread);
- int i;
+ int err;
+ int gen_len, gen_type;
+ struct perf_event_attr attr;
/*
- * Store in the virtual DR6 register the fact that the breakpoint
- * was hit so the thread's debugger will see it.
+ * 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
*/
- for (i = 0; i < hbp_kernel_pos; i++)
- /*
- * We will check bp->info.address against the address stored in
- * thread's hbp structure and not debugreg[i]. This is to ensure
- * that the corresponding bit for 'i' in DR7 register is enabled
- */
- if (bp->info.address == thread->hbp[i]->info.address)
- break;
+ if (!bp)
+ return -EINVAL;
- thread->debugreg6 |= (DR_TRAP0 << i);
+ err = arch_bp_generic_fields(len, type, &gen_len, &gen_type);
+ if (err)
+ return err;
+
+ attr = bp->attr;
+ attr.bp_len = gen_len;
+ attr.bp_type = gen_type;
+ attr.disabled = disabled;
+
+ return modify_user_hw_breakpoint(bp, &attr);
}
/*
static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
{
struct thread_struct *thread = &(tsk->thread);
- unsigned long old_dr7 = thread->debugreg7;
+ unsigned long old_dr7;
int i, orig_ret = 0, rc = 0;
int enabled, second_pass = 0;
unsigned len, type;
- struct hw_breakpoint *bp;
+ 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
*/
for (i = 0; i < HBP_NUM; i++) {
enabled = decode_dr7(data, i, &len, &type);
- bp = thread->hbp[i];
+ bp = thread->ptrace_bps[i];
if (!enabled) {
if (bp) {
- /* Don't unregister the breakpoints right-away,
+ /*
+ * Don't unregister the breakpoints right-away,
* unless all register_user_hw_breakpoint()
* requests have succeeded. This prevents
* any window of opportunity for debug
*/
if (!second_pass)
continue;
- unregister_user_hw_breakpoint(tsk, bp);
- kfree(bp);
+
+ rc = ptrace_modify_breakpoint(bp, len, type,
+ tsk, 1);
+ if (rc)
+ break;
}
continue;
}
- if (!bp) {
- rc = -ENOMEM;
- bp = kzalloc(sizeof(struct hw_breakpoint), GFP_KERNEL);
- if (bp) {
- bp->info.address = thread->debugreg[i];
- bp->triggered = ptrace_triggered;
- bp->info.len = len;
- bp->info.type = type;
- rc = register_user_hw_breakpoint(tsk, bp);
- if (rc)
- kfree(bp);
- }
- } else
- rc = modify_user_hw_breakpoint(tsk, bp);
+
+ rc = ptrace_modify_breakpoint(bp, len, type, tsk, 0);
if (rc)
break;
}
struct thread_struct *thread = &(tsk->thread);
unsigned long val = 0;
- if (n < HBP_NUM)
- val = thread->debugreg[n];
- else if (n == 6)
+ 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 = thread->debugreg7;
+ } 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);
+ /*
+ * Put stub len and type to register (reserve) an inactive but
+ * correct bp
+ */
+ 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;
+}
+
/*
* Handle PTRACE_POKEUSR calls for the debug register area.
*/
return -EIO;
if (n == 6) {
- tsk->thread.debugreg6 = val;
+ thread->debugreg6 = val;
goto ret_path;
}
if (n < HBP_NUM) {
- if (thread->hbp[n]) {
- if (arch_check_va_in_userspace(val,
- thread->hbp[n]->info.len) == 0) {
- rc = -EIO;
- goto ret_path;
- }
- thread->hbp[n]->info.address = val;
- }
- thread->debugreg[n] = val;
+ rc = ptrace_set_breakpoint_addr(tsk, n, val);
+ if (rc)
+ return rc;
}
/* All that's left is DR7 */
if (n == 7)
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):
tracehook_report_syscall_entry(regs))
ret = -1L;
- if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
- ftrace_syscall_enter(regs);
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_enter(regs, regs->orig_ax);
if (unlikely(current->audit_context)) {
if (IS_IA32)
if (unlikely(current->audit_context))
audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
- if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
- ftrace_syscall_exit(regs);
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_exit(regs, regs->ax);
if (test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, 0);