Merge branch 'tracing/hw-breakpoints' into perf/core

Conflicts:
	arch/x86/kernel/kprobes.c
	kernel/trace/Makefile

Merge reason: hw-breakpoints perf integration is looking
              good in testing and in reviews, plus conflicts
              are mounting up - so merge & resolve.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/Kconfig

@@ -126,4 +126,11 @@ config HAVE_DMA_API_DEBUG
 config HAVE_DEFAULT_NO_SPIN_MUTEXES
 	bool
 
+config HAVE_HW_BREAKPOINT
+	bool
+	depends on HAVE_PERF_EVENTS
+	select ANON_INODES
+	select PERF_EVENTS
+
+
 source "kernel/gcov/Kconfig"

arch/x86/Kconfig

@@ -49,6 +49,7 @@ config X86
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
+	select HAVE_HW_BREAKPOINT
 	select HAVE_ARCH_KMEMCHECK
 
 config OUTPUT_FORMAT

arch/x86/include/asm/Kbuild

@@ -10,6 +10,7 @@ header-y += ptrace-abi.h
 header-y += sigcontext32.h
 header-y += ucontext.h
 header-y += processor-flags.h
+header-y += hw_breakpoint.h
 
 unifdef-y += e820.h
 unifdef-y += ist.h

arch/x86/include/asm/a.out-core.h

@@ -17,6 +17,7 @@
 
 #include <linux/user.h>
 #include <linux/elfcore.h>
+#include <asm/debugreg.h>
 
 /*
  * fill in the user structure for an a.out core dump
@@ -32,14 +33,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 			>> PAGE_SHIFT;
 	dump->u_dsize -= dump->u_tsize;
 	dump->u_ssize = 0;
-	dump->u_debugreg[0] = current->thread.debugreg0;
+	aout_dump_debugregs(dump);
-	dump->u_debugreg[1] = current->thread.debugreg1;
-	dump->u_debugreg[2] = current->thread.debugreg2;
-	dump->u_debugreg[3] = current->thread.debugreg3;
-	dump->u_debugreg[4] = 0;
-	dump->u_debugreg[5] = 0;
-	dump->u_debugreg[6] = current->thread.debugreg6;
-	dump->u_debugreg[7] = current->thread.debugreg7;
 
 	if (dump->start_stack < TASK_SIZE)
 		dump->u_ssize = ((unsigned long)(TASK_SIZE - dump->start_stack))

arch/x86/include/asm/debugreg.h

@@ -18,6 +18,7 @@
 #define DR_TRAP1	(0x2)		/* db1 */
 #define DR_TRAP2	(0x4)		/* db2 */
 #define DR_TRAP3	(0x8)		/* db3 */
+#define DR_TRAP_BITS	(DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)
 
 #define DR_STEP		(0x4000)	/* single-step */
 #define DR_SWITCH	(0x8000)	/* task switch */
@@ -49,6 +50,8 @@
 
 #define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
 #define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
+#define DR_LOCAL_ENABLE (0x1)      /* Local enable for reg 0 */
+#define DR_GLOBAL_ENABLE (0x2)     /* Global enable for reg 0 */
 #define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
 
 #define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
@@ -67,4 +70,34 @@
 #define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
 #define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
 
+/*
+ * HW breakpoint additions
+ */
+#ifdef __KERNEL__
+
+DECLARE_PER_CPU(unsigned long, dr7);
+
+static inline void hw_breakpoint_disable(void)
+{
+	/* Zero the control register for HW Breakpoint */
+	set_debugreg(0UL, 7);
+
+	/* Zero-out the individual HW breakpoint address registers */
+	set_debugreg(0UL, 0);
+	set_debugreg(0UL, 1);
+	set_debugreg(0UL, 2);
+	set_debugreg(0UL, 3);
+}
+
+static inline int hw_breakpoint_active(void)
+{
+	return __get_cpu_var(dr7) & DR_GLOBAL_ENABLE_MASK;
+}
+
+extern void aout_dump_debugregs(struct user *dump);
+
+extern void hw_breakpoint_restore(void);
+
+#endif	/* __KERNEL__ */
+
 #endif /* _ASM_X86_DEBUGREG_H */

arch/x86/include/asm/hw_breakpoint.h

@@ -0,0 +1,73 @@
+#ifndef	_I386_HW_BREAKPOINT_H
+#define	_I386_HW_BREAKPOINT_H
+
+#ifdef	__KERNEL__
+#define	__ARCH_HW_BREAKPOINT_H
+
+/*
+ * The name should probably be something dealt in
+ * a higher level. While dealing with the user
+ * (display/resolving)
+ */
+struct arch_hw_breakpoint {
+	char		*name; /* Contains name of the symbol to set bkpt */
+	unsigned long	address;
+	u8		len;
+	u8		type;
+};
+
+#include <linux/kdebug.h>
+#include <linux/percpu.h>
+#include <linux/list.h>
+
+/* Available HW breakpoint length encodings */
+#define X86_BREAKPOINT_LEN_1		0x40
+#define X86_BREAKPOINT_LEN_2		0x44
+#define X86_BREAKPOINT_LEN_4		0x4c
+#define X86_BREAKPOINT_LEN_EXECUTE	0x40
+
+#ifdef CONFIG_X86_64
+#define X86_BREAKPOINT_LEN_8		0x48
+#endif
+
+/* Available HW breakpoint type encodings */
+
+/* trigger on instruction execute */
+#define X86_BREAKPOINT_EXECUTE	0x80
+/* trigger on memory write */
+#define X86_BREAKPOINT_WRITE	0x81
+/* trigger on memory read or write */
+#define X86_BREAKPOINT_RW	0x83
+
+/* Total number of available HW breakpoint registers */
+#define HBP_NUM 4
+
+struct perf_event;
+struct pmu;
+
+extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
+					 struct task_struct *tsk);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+					   unsigned long val, void *data);
+
+
+int arch_install_hw_breakpoint(struct perf_event *bp);
+void arch_uninstall_hw_breakpoint(struct perf_event *bp);
+void hw_breakpoint_pmu_read(struct perf_event *bp);
+void hw_breakpoint_pmu_unthrottle(struct perf_event *bp);
+
+extern void
+arch_fill_perf_breakpoint(struct perf_event *bp);
+
+unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type);
+int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, unsigned *type);
+
+extern int arch_bp_generic_fields(int x86_len, int x86_type,
+				  int *gen_len, int *gen_type);
+
+extern struct pmu perf_ops_bp;
+
+#endif	/* __KERNEL__ */
+#endif	/* _I386_HW_BREAKPOINT_H */
+

arch/x86/include/asm/processor.h

@@ -30,6 +30,7 @@ struct mm_struct;
 #include <linux/math64.h>
 #include <linux/init.h>
 
+#define HBP_NUM 4
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
@@ -422,6 +423,8 @@ extern unsigned int xstate_size;
 extern void free_thread_xstate(struct task_struct *);
 extern struct kmem_cache *task_xstate_cachep;
 
+struct perf_event;
+
 struct thread_struct {
 	/* Cached TLS descriptors: */
 	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
@@ -443,13 +446,10 @@ struct thread_struct {
 	unsigned long		fs;
 #endif
 	unsigned long		gs;
-	/* Hardware debugging registers: */
+	/* Save middle states of ptrace breakpoints */
-	unsigned long		debugreg0;
+	struct perf_event	*ptrace_bps[HBP_NUM];
-	unsigned long		debugreg1;
+	/* Debug status used for traps, single steps, etc... */
-	unsigned long		debugreg2;
+	unsigned long           debugreg6;
-	unsigned long		debugreg3;
-	unsigned long		debugreg6;
-	unsigned long		debugreg7;
 	/* Fault info: */
 	unsigned long		cr2;
 	unsigned long		trap_no;

arch/x86/kernel/Makefile

@@ -40,7 +40,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
-obj-y			+= alternative.o i8253.o pci-nommu.o
+obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o

arch/x86/kernel/kgdb.c

@@ -43,6 +43,7 @@
 #include <linux/smp.h>
 #include <linux/nmi.h>
 
+#include <asm/debugreg.h>
 #include <asm/apicdef.h>
 #include <asm/system.h>
 
@@ -434,6 +435,11 @@ single_step_cont(struct pt_regs *regs, struct die_args *args)
 			"resuming...\n");
 	kgdb_arch_handle_exception(args->trapnr, args->signr,
 				   args->err, "c", "", regs);
+	/*
+	 * Reset the BS bit in dr6 (pointed by args->err) to
+	 * denote completion of processing
+	 */
+	(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
 
 	return NOTIFY_STOP;
 }

arch/x86/kernel/kprobes.c

@@ -56,6 +56,7 @@
 #include <asm/uaccess.h>
 #include <asm/alternative.h>
 #include <asm/insn.h>
+#include <asm/debugreg.h>
 
 void jprobe_return_end(void);
 
@@ -945,8 +946,14 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 			ret = NOTIFY_STOP;
 		break;
 	case DIE_DEBUG:
-		if (post_kprobe_handler(args->regs))
+		if (post_kprobe_handler(args->regs)) {
+			/*
+			 * Reset the BS bit in dr6 (pointed by args->err) to
+			 * denote completion of processing
+			 */
+			(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
 			ret = NOTIFY_STOP;
+		}
 		break;
 	case DIE_GPF:
 		/*

arch/x86/kernel/machine_kexec_32.c

@@ -25,6 +25,7 @@
 #include <asm/desc.h>
 #include <asm/system.h>
 #include <asm/cacheflush.h>
+#include <asm/debugreg.h>
 
 static void set_idt(void *newidt, __u16 limit)
 {
@@ -202,6 +203,7 @@ void machine_kexec(struct kimage *image)
 
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
+	hw_breakpoint_disable();
 
 	if (image->preserve_context) {
 #ifdef CONFIG_X86_IO_APIC

arch/x86/kernel/machine_kexec_64.c

@@ -18,6 +18,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
+#include <asm/debugreg.h>
 
 static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
 				unsigned long addr)
@@ -282,6 +283,7 @@ void machine_kexec(struct kimage *image)
 
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
+	hw_breakpoint_disable();
 
 	if (image->preserve_context) {
 #ifdef CONFIG_X86_IO_APIC

arch/x86/kernel/process.c

@@ -10,6 +10,7 @@
 #include <linux/clockchips.h>
 #include <linux/random.h>
 #include <trace/events/power.h>
+#include <linux/hw_breakpoint.h>
 #include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/syscalls.h>
@@ -17,6 +18,7 @@
 #include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/ds.h>
+#include <asm/debugreg.h>
 
 unsigned long idle_halt;
 EXPORT_SYMBOL(idle_halt);
@@ -103,14 +105,7 @@ void flush_thread(void)
 	}
 #endif
 
-	clear_tsk_thread_flag(tsk, TIF_DEBUG);
+	flush_ptrace_hw_breakpoint(tsk);
-
-	tsk->thread.debugreg0 = 0;
-	tsk->thread.debugreg1 = 0;
-	tsk->thread.debugreg2 = 0;
-	tsk->thread.debugreg3 = 0;
-	tsk->thread.debugreg6 = 0;
-	tsk->thread.debugreg7 = 0;
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 	/*
 	 * Forget coprocessor state..
@@ -192,16 +187,6 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 	else if (next->debugctlmsr != prev->debugctlmsr)
 		update_debugctlmsr(next->debugctlmsr);
 
-	if (test_tsk_thread_flag(next_p, TIF_DEBUG)) {
-		set_debugreg(next->debugreg0, 0);
-		set_debugreg(next->debugreg1, 1);
-		set_debugreg(next->debugreg2, 2);
-		set_debugreg(next->debugreg3, 3);
-		/* no 4 and 5 */
-		set_debugreg(next->debugreg6, 6);
-		set_debugreg(next->debugreg7, 7);
-	}
-
 	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
 	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
 		/* prev and next are different */

arch/x86/kernel/process_32.c

@@ -58,6 +58,7 @@
 #include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/ds.h>
+#include <asm/debugreg.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
@@ -259,7 +260,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	task_user_gs(p) = get_user_gs(regs);
 
+	p->thread.io_bitmap_ptr = NULL;
 	tsk = current;
+	err = -ENOMEM;
+
+	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+
 	if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
 		p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
 						IO_BITMAP_BYTES, GFP_KERNEL);

arch/x86/kernel/process_64.c

@@ -52,6 +52,7 @@
 #include <asm/idle.h>
 #include <asm/syscalls.h>
 #include <asm/ds.h>
+#include <asm/debugreg.h>
 
 asmlinkage extern void ret_from_fork(void);
 
@@ -297,12 +298,16 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	p->thread.fs = me->thread.fs;
 	p->thread.gs = me->thread.gs;
+	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);
 	savesegment(fs, p->thread.fsindex);
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
 
+	err = -ENOMEM;
+	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+
 	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
 		p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL);
 		if (!p->thread.io_bitmap_ptr) {
@@ -341,6 +346,7 @@ out:
 		kfree(p->thread.io_bitmap_ptr);
 		p->thread.io_bitmap_max = 0;
 	}
+
 	return err;
 }
 
@@ -495,6 +501,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 */
 	if (preload_fpu)
 		__math_state_restore();
+
 	return prev_p;
 }
 

arch/x86/kernel/ptrace.c

@@ -22,6 +22,8 @@
 #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>
@@ -34,6 +36,7 @@
 #include <asm/prctl.h>
 #include <asm/proto.h>
 #include <asm/ds.h>
+#include <asm/hw_breakpoint.h>
 
 #include "tls.h"
 
@@ -249,11 +252,6 @@ static int set_segment_reg(struct task_struct *task,
 	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)
@@ -378,15 +376,6 @@ static int set_segment_reg(struct task_struct *task,
 	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)
@@ -566,96 +555,226 @@ static int genregs_set(struct task_struct *target,
 	return ret;
 }
 
-/*
+static void ptrace_triggered(struct perf_event *bp, void *data)
- * 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.
- */
-static unsigned long ptrace_get_debugreg(struct task_struct *child, int n)
 {
-	switch (n) {
+	int i;
-	case 0:		return child->thread.debugreg0;
+	struct thread_struct *thread = &(current->thread);
-	case 1:		return child->thread.debugreg1;
+
-	case 2:		return child->thread.debugreg2;
+	/*
-	case 3:		return child->thread.debugreg3;
+	 * Store in the virtual DR6 register the fact that the breakpoint
-	case 6:		return child->thread.debugreg6;
+	 * was hit so the thread's debugger will see it.
-	case 7:		return child->thread.debugreg7;
+	 */
+	for (i = 0; i < HBP_NUM; i++) {
+		if (thread->ptrace_bps[i] == bp)
+			break;
 	}
+
+	thread->debugreg6 |= (DR_TRAP0 << i);
+}
+
+/*
+ * Walk through every ptrace breakpoints for this thread and
+ * build the dr7 value on top of their attributes.
+ *
+ */
+static unsigned long ptrace_get_dr7(struct perf_event *bp[])
+{
+	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 dr7;
+}
+
+/*
+ * 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;
+	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;
+		}
+
+		/*
+		 * 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;
+		}
+
+		rc = arch_bp_generic_fields(len, type, &gen_len, &gen_type);
+		if (rc)
+			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;
+
+		if (!bp) { /* incorrect bp, or we have a bug in bp API */
+			rc = -EINVAL;
+			break;
+		}
+		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);
+}
+
+/*
+ * 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;
+
+	if (!t->ptrace_bps[nr]) {
+		/*
+		 * Put stub len and type to register (reserve) an inactive but
+		 * correct bp
+		 */
+		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);
+	}
+
+	if (!bp)
+		return -EIO;
+	/*
+	 * 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;
 }
 
-static int ptrace_set_debugreg(struct task_struct *child,
+/*
-			       int n, unsigned long data)
+ * Handle PTRACE_POKEUSR calls for the debug register area.
+ */
+int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val)
 {
-	int i;
+	struct thread_struct *thread = &(tsk->thread);
+	int rc = 0;
 
-	if (unlikely(n == 4 || n == 5))
+	/* There are no DR4 or DR5 registers */
+	if (n == 4 || n == 5)
 		return -EIO;
 
-	if (n < 4 && unlikely(data >= debugreg_addr_limit(child)))
+	if (n == 6) {
-		return -EIO;
+		thread->debugreg6 = val;
-
+		goto ret_path;
-	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;
-
-	case 6:
-		if ((data & ~0xffffffffUL) != 0)
-			return -EIO;
-		child->thread.debugreg6 = data;
-		break;
-
-	case 7:
-		/*
-		 * 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)
-		 */
-#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;
 	}
+	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);
 
-	return 0;
+ret_path:
+	return rc;
 }
 
 /*

arch/x86/kernel/signal.c

@@ -799,15 +799,6 @@ static void do_signal(struct pt_regs *regs)
 
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 	if (signr > 0) {
-		/*
-		 * Re-enable any watchpoints before delivering the
-		 * signal to user space. The processor register will
-		 * have been cleared if the watchpoint triggered
-		 * inside the kernel.
-		 */
-		if (current->thread.debugreg7)
-			set_debugreg(current->thread.debugreg7, 7);
-
 		/* Whee! Actually deliver the signal.  */
 		if (handle_signal(signr, &info, &ka, oldset, regs) == 0) {
 			/*

arch/x86/kernel/traps.c

@@ -529,77 +529,56 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
-	unsigned long condition;
+	unsigned long dr6;
 	int si_code;
 
-	get_debugreg(condition, 6);
+	get_debugreg(dr6, 6);
 
 	/* Catch kmemcheck conditions first of all! */
-	if (condition & DR_STEP && kmemcheck_trap(regs))
+	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
 		return;
 
+	/* DR6 may or may not be cleared by the CPU */
+	set_debugreg(0, 6);
 	/*
 	 * The processor cleared BTF, so don't mark that we need it set.
 	 */
 	clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR);
 	tsk->thread.debugctlmsr = 0;
 
-	if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
+	/* Store the virtualized DR6 value */
-						SIGTRAP) == NOTIFY_STOP)
+	tsk->thread.debugreg6 = dr6;
+
+	if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code,
+							SIGTRAP) == NOTIFY_STOP)
 		return;
 
 	/* It's safe to allow irq's after DR6 has been saved */
 	preempt_conditional_sti(regs);
 
-	/* Mask out spurious debug traps due to lazy DR7 setting */
+	if (regs->flags & X86_VM_MASK) {
-	if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
+		handle_vm86_trap((struct kernel_vm86_regs *) regs,
-		if (!tsk->thread.debugreg7)
+				error_code, 1);
-			goto clear_dr7;
+		return;
 	}
 
-#ifdef CONFIG_X86_32
-	if (regs->flags & X86_VM_MASK)
-		goto debug_vm86;
-#endif
-
-	/* Save debug status register where ptrace can see it */
-	tsk->thread.debugreg6 = condition;
-
 	/*
-	 * Single-stepping through TF: make sure we ignore any events in
+	 * Single-stepping through system calls: ignore any exceptions in
-	 * kernel space (but re-enable TF when returning to user mode).
+	 * kernel space, but re-enable TF when returning to user mode.
+	 *
+	 * We already checked v86 mode above, so we can check for kernel mode
+	 * by just checking the CPL of CS.
 	 */
-	if (condition & DR_STEP) {
+	if ((dr6 & DR_STEP) && !user_mode(regs)) {
-		if (!user_mode(regs))
+		tsk->thread.debugreg6 &= ~DR_STEP;
-			goto clear_TF_reenable;
+		set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
+		regs->flags &= ~X86_EFLAGS_TF;
 	}
-
+	si_code = get_si_code(tsk->thread.debugreg6);
-	si_code = get_si_code(condition);
+	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS))
-	/* Ok, finally something we can handle */
+		send_sigtrap(tsk, regs, error_code, si_code);
-	send_sigtrap(tsk, regs, error_code, si_code);
-
-	/*
-	 * Disable additional traps. They'll be re-enabled when
-	 * the signal is delivered.
-	 */
-clear_dr7:
-	set_debugreg(0, 7);
 	preempt_conditional_cli(regs);
-	return;
 
-#ifdef CONFIG_X86_32
-debug_vm86:
-	/* reenable preemption: handle_vm86_trap() might sleep */
-	dec_preempt_count();
-	handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
-	conditional_cli(regs);
-	return;
-#endif
-
-clear_TF_reenable:
-	set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
-	regs->flags &= ~X86_EFLAGS_TF;
-	preempt_conditional_cli(regs);
 	return;
 }
 

arch/x86/kvm/x86.c

@@ -42,6 +42,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
+#include <asm/debugreg.h>
 #include <asm/uaccess.h>
 #include <asm/msr.h>
 #include <asm/desc.h>
@@ -3643,14 +3644,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	trace_kvm_entry(vcpu->vcpu_id);
 	kvm_x86_ops->run(vcpu, kvm_run);
 
-	if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) {
+	/*
-		set_debugreg(current->thread.debugreg0, 0);
+	 * If the guest has used debug registers, at least dr7
-		set_debugreg(current->thread.debugreg1, 1);
+	 * will be disabled while returning to the host.
-		set_debugreg(current->thread.debugreg2, 2);
+	 * If we don't have active breakpoints in the host, we don't
-		set_debugreg(current->thread.debugreg3, 3);
+	 * care about the messed up debug address registers. But if
-		set_debugreg(current->thread.debugreg6, 6);
+	 * we have some of them active, restore the old state.
-		set_debugreg(current->thread.debugreg7, 7);
+	 */
-	}
+	if (hw_breakpoint_active())
+		hw_breakpoint_restore();
 
 	set_bit(KVM_REQ_KICK, &vcpu->requests);
 	local_irq_enable();