#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 <trace/syscall.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_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 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_SIZE_MAX - 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, void *data)
+{
+ 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)
+/*
+ * Handle ptrace writes to debug register 7.
+ */
+static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
{
- int i;
+ 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;
+ int gen_len, gen_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;
+ thread->ptrace_bps[i] = NULL;
+ unregister_hw_breakpoint(bp);
+ }
+ continue;
+ }
- 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) {
+ rc = -EINVAL;
+ break;
+ }
- if (n < 4 && unlikely(data >= debugreg_addr_limit(child)))
- return -EIO;
+ rc = arch_bp_generic_fields(len, type, &gen_len, &gen_type);
+ if (rc)
+ break;
- 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;
+ /*
+ * This is a temporary thing as bp is unregistered/registered
+ * to simulate modification
+ */
+ bp = modify_user_hw_breakpoint(bp, bp->attr.bp_addr, gen_len,
+ gen_type, bp->callback,
+ tsk, true);
+ thread->ptrace_bps[i] = NULL;
+
+ /* Incorrect bp, or we have a bug in bp API */
+ if (IS_ERR(bp)) {
+ rc = PTR_ERR(bp);
+ bp = NULL;
+ break;
+ }
+ thread->ptrace_bps[i] = bp;
+ }
+ /*
+ * 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);
+}
- case 6:
- if ((data & ~0xffffffffUL) != 0)
- return -EIO;
- child->thread.debugreg6 = data;
- break;
+/*
+ * 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;
+
+ 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;
- case 7:
+ if (!t->ptrace_bps[nr]) {
/*
- * 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;
+ bp = register_user_hw_breakpoint(addr, HW_BREAKPOINT_LEN_1,
+ HW_BREAKPOINT_W,
+ ptrace_triggered, tsk,
+ false);
+ } else {
+ bp = t->ptrace_bps[nr];
+ t->ptrace_bps[nr] = NULL;
+ bp = modify_user_hw_breakpoint(bp, addr, bp->attr.bp_len,
+ bp->attr.bp_type,
+ bp->callback,
+ tsk,
+ bp->attr.disabled);
}
+ /*
+ * 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;
return 0;
}
/*
+ * 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.
*/
struct work_struct work;
};
-static inline void alloc_bts_buffer(struct bts_context *context,
- unsigned int size)
+static int alloc_bts_buffer(struct bts_context *context, unsigned int size)
{
- void *buffer;
+ void *buffer = NULL;
+ int err = -ENOMEM;
- buffer = alloc_locked_buffer(size);
- if (buffer) {
- context->buffer = buffer;
- context->size = size;
- context->mm = get_task_mm(current);
- }
+ err = account_locked_memory(current->mm, current->signal->rlim, size);
+ if (err < 0)
+ return err;
+
+ buffer = kzalloc(size, GFP_KERNEL);
+ if (!buffer)
+ goto out_refund;
+
+ context->buffer = buffer;
+ context->size = size;
+ context->mm = get_task_mm(current);
+
+ return 0;
+
+ out_refund:
+ refund_locked_memory(current->mm, size);
+ return err;
}
static inline void free_bts_buffer(struct bts_context *context)
kfree(context->buffer);
context->buffer = NULL;
- refund_locked_buffer_memory(context->mm, context->size);
+ refund_locked_memory(context->mm, context->size);
context->size = 0;
mmput(context->mm);
context->tracer = NULL;
if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) {
+ int err;
+
free_bts_buffer(context);
if (!cfg.size)
return 0;
- alloc_bts_buffer(context, cfg.size);
- if (!context->buffer)
- return -ENOMEM;
+ err = alloc_bts_buffer(context, cfg.size);
+ if (err < 0)
+ return err;
}
if (cfg.flags & PTRACE_BTS_O_TRACE)
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);