summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--arch/Kconfig4
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/include/asm/a.out-core.h8
-rw-r--r--arch/x86/include/asm/debugreg.h29
-rw-r--r--arch/x86/include/asm/hw_breakpoint.h55
-rw-r--r--arch/x86/include/asm/processor.h8
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/hw_breakpoint.c391
-rw-r--r--arch/x86/kernel/kgdb.c6
-rw-r--r--arch/x86/kernel/kprobes.c9
-rw-r--r--arch/x86/kernel/machine_kexec_32.c2
-rw-r--r--arch/x86/kernel/machine_kexec_64.c2
-rw-r--r--arch/x86/kernel/process.c22
-rw-r--r--arch/x86/kernel/process_32.c28
-rw-r--r--arch/x86/kernel/process_64.c31
-rw-r--r--arch/x86/kernel/ptrace.c231
-rw-r--r--arch/x86/kernel/signal.c9
-rw-r--r--arch/x86/kernel/smpboot.c3
-rw-r--r--arch/x86/kernel/traps.c73
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--arch/x86/mm/kmmio.c8
-rw-r--r--arch/x86/power/cpu.c24
-rw-r--r--include/asm-generic/hw_breakpoint.h139
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/hw_breakpoint.c378
-rw-r--r--kernel/trace/Kconfig21
-rw-r--r--kernel/trace/Makefile1
-rw-r--r--kernel/trace/trace.h11
-rw-r--r--kernel/trace/trace_entries.h16
-rw-r--r--kernel/trace/trace_ksym.c551
-rw-r--r--kernel/trace/trace_selftest.c53
-rw-r--r--samples/Kconfig6
-rw-r--r--samples/Makefile3
-rw-r--r--samples/hw_breakpoint/Makefile1
-rw-r--r--samples/hw_breakpoint/data_breakpoint.c83
35 files changed, 2019 insertions, 199 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 7f418bbc261..acb66439794 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -126,4 +126,8 @@ config HAVE_DMA_API_DEBUG
config HAVE_DEFAULT_NO_SPIN_MUTEXES
bool
+config HAVE_HW_BREAKPOINT
+ bool
+
+
source "kernel/gcov/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 07e01149e3b..1b7c74350a0 100644
--- a/arch/x86/Kconfig
+++ b/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
diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h
index bb70e397aa8..fc4685dd6e4 100644
--- a/arch/x86/include/asm/a.out-core.h
+++ b/arch/x86/include/asm/a.out-core.h
@@ -32,10 +32,10 @@ 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;
- dump->u_debugreg[1] = current->thread.debugreg1;
- dump->u_debugreg[2] = current->thread.debugreg2;
- dump->u_debugreg[3] = current->thread.debugreg3;
+ dump->u_debugreg[0] = current->thread.debugreg[0];
+ dump->u_debugreg[1] = current->thread.debugreg[1];
+ dump->u_debugreg[2] = current->thread.debugreg[2];
+ dump->u_debugreg[3] = current->thread.debugreg[3];
dump->u_debugreg[4] = 0;
dump->u_debugreg[5] = 0;
dump->u_debugreg[6] = current->thread.debugreg6;
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 3ea6f37be9e..23439fbb1d0 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/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 +70,30 @@
#define DR_LOCAL_SLOWDOWN (0x100) /* Local slow the pipeline */
#define DR_GLOBAL_SLOWDOWN (0x200) /* Global slow the pipeline */
+/*
+ * HW breakpoint additions
+ */
+#ifdef __KERNEL__
+
+/* For process management */
+extern void flush_thread_hw_breakpoint(struct task_struct *tsk);
+extern int copy_thread_hw_breakpoint(struct task_struct *tsk,
+ struct task_struct *child, unsigned long clone_flags);
+
+/* For CPU management */
+extern void load_debug_registers(void);
+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);
+}
+
+#endif /* __KERNEL__ */
+
#endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
new file mode 100644
index 00000000000..1acb4d45de7
--- /dev/null
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -0,0 +1,55 @@
+#ifndef _I386_HW_BREAKPOINT_H
+#define _I386_HW_BREAKPOINT_H
+
+#ifdef __KERNEL__
+#define __ARCH_HW_BREAKPOINT_H
+
+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 <asm-generic/hw_breakpoint.h>
+
+/* Available HW breakpoint length encodings */
+#define HW_BREAKPOINT_LEN_1 0x40
+#define HW_BREAKPOINT_LEN_2 0x44
+#define HW_BREAKPOINT_LEN_4 0x4c
+#define HW_BREAKPOINT_LEN_EXECUTE 0x40
+
+#ifdef CONFIG_X86_64
+#define HW_BREAKPOINT_LEN_8 0x48
+#endif
+
+/* Available HW breakpoint type encodings */
+
+/* trigger on instruction execute */
+#define HW_BREAKPOINT_EXECUTE 0x80
+/* trigger on memory write */
+#define HW_BREAKPOINT_WRITE 0x81
+/* trigger on memory read or write */
+#define HW_BREAKPOINT_RW 0x83
+
+/* Total number of available HW breakpoint registers */
+#define HBP_NUM 4
+
+extern struct hw_breakpoint *hbp_kernel[HBP_NUM];
+DECLARE_PER_CPU(struct hw_breakpoint*, this_hbp_kernel[HBP_NUM]);
+extern unsigned int hbp_user_refcount[HBP_NUM];
+
+extern void arch_install_thread_hw_breakpoint(struct task_struct *tsk);
+extern void arch_uninstall_thread_hw_breakpoint(void);
+extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len);
+extern int arch_validate_hwbkpt_settings(struct hw_breakpoint *bp,
+ struct task_struct *tsk);
+extern void arch_update_user_hw_breakpoint(int pos, struct task_struct *tsk);
+extern void arch_flush_thread_hw_breakpoint(struct task_struct *tsk);
+extern void arch_update_kernel_hw_breakpoint(void *);
+extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
+ unsigned long val, void *data);
+#endif /* __KERNEL__ */
+#endif /* _I386_HW_BREAKPOINT_H */
+
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c3429e8b242..61aafb71c7e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/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").
@@ -444,12 +445,11 @@ struct thread_struct {
#endif
unsigned long gs;
/* Hardware debugging registers: */
- unsigned long debugreg0;
- unsigned long debugreg1;
- unsigned long debugreg2;
- unsigned long debugreg3;
+ unsigned long debugreg[HBP_NUM];
unsigned long debugreg6;
unsigned long debugreg7;
+ /* Hardware breakpoint info */
+ struct hw_breakpoint *hbp[HBP_NUM];
/* Fault info: */
unsigned long cr2;
unsigned long trap_no;
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d8e5d0cdd67..4f2e66e29ec 100644
--- a/arch/x86/kernel/Makefile
+++ b/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
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
new file mode 100644
index 00000000000..9316a9de4de
--- /dev/null
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -0,0 +1,391 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2007 Alan Stern
+ * Copyright (C) 2009 IBM Corporation
+ */
+
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers.
+ */
+
+#include <linux/irqflags.h>
+#include <linux/notifier.h>
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/percpu.h>
+#include <linux/kdebug.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm/hw_breakpoint.h>
+#include <asm/processor.h>
+#include <asm/debugreg.h>
+
+/* Unmasked kernel DR7 value */
+static unsigned long kdr7;
+
+/*
+ * Masks for the bits corresponding to registers DR0 - DR3 in DR7 register.
+ * Used to clear and verify the status of bits corresponding to DR0 - DR3
+ */
+static const unsigned long dr7_masks[HBP_NUM] = {
+ 0x000f0003, /* LEN0, R/W0, G0, L0 */
+ 0x00f0000c, /* LEN1, R/W1, G1, L1 */
+ 0x0f000030, /* LEN2, R/W2, G2, L2 */
+ 0xf00000c0 /* LEN3, R/W3, G3, L3 */
+};
+
+
+/*
+ * Encode the length, type, Exact, and Enable bits for a particular breakpoint
+ * as stored in debug register 7.
+ */
+static unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type)
+{
+ unsigned long bp_info;
+
+ bp_info = (len | type) & 0xf;
+ bp_info <<= (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE);
+ bp_info |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE)) |
+ DR_GLOBAL_SLOWDOWN;
+ return bp_info;
+}
+
+void arch_update_kernel_hw_breakpoint(void *unused)
+{
+ struct hw_breakpoint *bp;
+ int i, cpu = get_cpu();
+ unsigned long temp_kdr7 = 0;
+
+ /* Don't allow debug exceptions while we update the registers */
+ set_debugreg(0UL, 7);
+
+ for (i = hbp_kernel_pos; i < HBP_NUM; i++) {
+ per_cpu(this_hbp_kernel[i], cpu) = bp = hbp_kernel[i];
+ if (bp) {
+ temp_kdr7 |= encode_dr7(i, bp->info.len, bp->info.type);
+ set_debugreg(bp->info.address, i);
+ }
+ }
+
+ /* No need to set DR6. Update the debug registers with kernel-space
+ * breakpoint values from kdr7 and user-space requests from the
+ * current process
+ */
+ kdr7 = temp_kdr7;
+ set_debugreg(kdr7 | current->thread.debugreg7, 7);
+ put_cpu();
+}
+
+/*
+ * Install the thread breakpoints in their debug registers.
+ */
+void arch_install_thread_hw_breakpoint(struct task_struct *tsk)
+{
+ struct thread_struct *thread = &(tsk->thread);
+
+ switch (hbp_kernel_pos) {
+ case 4:
+ set_debugreg(thread->debugreg[3], 3);
+ case 3:
+ set_debugreg(thread->debugreg[2], 2);
+ case 2:
+ set_debugreg(thread->debugreg[1], 1);
+ case 1:
+ set_debugreg(thread->debugreg[0], 0);
+ default:
+ break;
+ }
+
+ /* No need to set DR6 */
+ set_debugreg((kdr7 | thread->debugreg7), 7);
+}
+
+/*
+ * Install the debug register values for just the kernel, no thread.
+ */
+void arch_uninstall_thread_hw_breakpoint(void)
+{
+ /* Clear the user-space portion of debugreg7 by setting only kdr7 */
+ set_debugreg(kdr7, 7);
+
+}
+
+static int get_hbp_len(u8 hbp_len)
+{
+ unsigned int len_in_bytes = 0;
+
+ switch (hbp_len) {
+ case HW_BREAKPOINT_LEN_1:
+ len_in_bytes = 1;
+ break;
+ case HW_BREAKPOINT_LEN_2:
+ len_in_bytes = 2;
+ break;
+ case HW_BREAKPOINT_LEN_4:
+ len_in_bytes = 4;
+ break;
+#ifdef CONFIG_X86_64
+ case HW_BREAKPOINT_LEN_8:
+ len_in_bytes = 8;
+ break;
+#endif
+ }
+ return len_in_bytes;
+}
+
+/*
+ * Check for virtual address in user space.
+ */
+int arch_check_va_in_userspace(unsigned long va, u8 hbp_len)
+{
+ unsigned int len;
+
+ len = get_hbp_len(hbp_len);
+
+ return (va <= TASK_SIZE - len);
+}
+
+/*
+ * Check for virtual address in kernel space.
+ */
+static int arch_check_va_in_kernelspace(unsigned long va, u8 hbp_len)
+{
+ unsigned int len;
+
+ len = get_hbp_len(hbp_len);
+
+ return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
+}
+
+/*
+ * Store a breakpoint's encoded address, length, and type.
+ */
+static int arch_store_info(struct hw_breakpoint *bp, struct task_struct *tsk)
+{
+ /*
+ * User-space requests will always have the address field populated
+ * Symbol names from user-space are rejected
+ */
+ if (tsk && bp->info.name)
+ return -EINVAL;
+ /*
+ * For kernel-addresses, either the address or symbol name can be
+ * specified.
+ */
+ if (bp->info.name)
+ bp->info.address = (unsigned long)
+ kallsyms_lookup_name(bp->info.name);
+ if (bp->info.address)
+ return 0;
+ return -EINVAL;
+}
+
+/*
+ * Validate the arch-specific HW Breakpoint register settings
+ */
+int arch_validate_hwbkpt_settings(struct hw_breakpoint *bp,
+ struct task_struct *tsk)
+{
+ unsigned int align;
+ int ret = -EINVAL;
+
+ switch (bp->info.type) {
+ /*
+ * Ptrace-refactoring code
+ * For now, we'll allow instruction breakpoint only for user-space
+ * addresses
+ */
+ case HW_BREAKPOINT_EXECUTE:
+ if ((!arch_check_va_in_userspace(bp->info.address,
+ bp->info.len)) &&
+ bp->info.len != HW_BREAKPOINT_LEN_EXECUTE)
+ return ret;
+ break;
+ case HW_BREAKPOINT_WRITE:
+ break;
+ case HW_BREAKPOINT_RW:
+ break;
+ default:
+ return ret;
+ }
+
+ switch (bp->info.len) {
+ case HW_BREAKPOINT_LEN_1:
+ align = 0;
+ break;
+ case HW_BREAKPOINT_LEN_2:
+ align = 1;
+ break;
+ case HW_BREAKPOINT_LEN_4:
+ align = 3;
+ break;
+#ifdef CONFIG_X86_64
+ case HW_BREAKPOINT_LEN_8:
+ align = 7;
+ break;
+#endif
+ default:
+ return ret;
+ }
+
+ if (bp->triggered)
+ ret = arch_store_info(bp, tsk);
+
+ if (ret < 0)
+ return ret;
+ /*
+ * Check that the low-order bits of the address are appropriate
+ * for the alignment implied by len.
+ */
+ if (bp->info.address & align)
+ return -EINVAL;
+
+ /* Check that the virtual address is in the proper range */
+ if (tsk) {
+ if (!arch_check_va_in_userspace(bp->info.address, bp->info.len))
+ return -EFAULT;
+ } else {
+ if (!arch_check_va_in_kernelspace(bp->info.address,
+ bp->info.len))
+ return -EFAULT;
+ }
+ return 0;
+}
+
+void arch_update_user_hw_breakpoint(int pos, struct task_struct *tsk)
+{
+ struct thread_struct *thread = &(tsk->thread);
+ struct hw_breakpoint *bp = thread->hbp[pos];
+
+ thread->debugreg7 &= ~dr7_masks[pos];
+ if (bp) {
+ thread->debugreg[pos] = bp->info.address;
+ thread->debugreg7 |= encode_dr7(pos, bp->info.len,
+ bp->info.type);
+ } else
+ thread->debugreg[pos] = 0;
+}
+
+void arch_flush_thread_hw_breakpoint(struct task_struct *tsk)
+{
+ int i;
+ struct thread_struct *thread = &(tsk->thread);
+
+ thread->debugreg7 = 0;
+ for (i = 0; i < HBP_NUM; i++)
+ thread->debugreg[i] = 0;
+}
+
+/*
+ * Handle debug exception notifications.
+ *
+ * Return value is either NOTIFY_STOP or NOTIFY_DONE as explained below.
+ *
+ * NOTIFY_DONE returned if one of the following conditions is true.
+ * i) When the causative address is from user-space and the exception
+ * is a valid one, i.e. not triggered as a result of lazy debug register
+ * switching
+ * ii) When there are more bits than trap<n> set in DR6 register (such
+ * as BD, BS or BT) indicating that more than one debug condition is
+ * met and requires some more action in do_debug().
+ *
+ * NOTIFY_STOP returned for all other cases
+ *
+ */
+static int __kprobes hw_breakpoint_handler(struct die_args *args)
+{
+ int i, cpu, rc = NOTIFY_STOP;
+ struct hw_breakpoint *bp;
+ unsigned long dr7, dr6;
+ unsigned long *dr6_p;
+
+ /* The DR6 value is pointed by args->err */
+ dr6_p = (unsigned long *)ERR_PTR(args->err);
+ dr6 = *dr6_p;
+
+ /* Do an early return if no trap bits are set in DR6 */
+ if ((dr6 & DR_TRAP_BITS) == 0)
+ return NOTIFY_DONE;
+
+ /* Lazy debug register switching */
+ if (!test_tsk_thread_flag(current, TIF_DEBUG))
+ arch_uninstall_thread_hw_breakpoint();
+
+ get_debugreg(dr7, 7);
+ /* Disable breakpoints during exception handling */
+ set_debugreg(0UL, 7);
+ /*
+ * Assert that local interrupts are disabled
+ * Reset the DRn bits in the virtualized register value.
+ * The ptrace trigger routine will add in whatever is needed.
+ */
+ current->thread.debugreg6 &= ~DR_TRAP_BITS;
+ cpu = get_cpu();
+
+ /* Handle all the breakpoints that were triggered */
+ for (i = 0; i < HBP_NUM; ++i) {
+ if (likely(!(dr6 & (DR_TRAP0 << i))))
+ continue;
+ /*
+ * Find the corresponding hw_breakpoint structure and
+ * invoke its triggered callback.
+ */
+ if (i >= hbp_kernel_pos)
+ bp = per_cpu(this_hbp_kernel[i], cpu);
+ else {
+ bp = current->thread.hbp[i];
+ if (bp)
+ rc = NOTIFY_DONE;
+ }
+ /*
+ * Reset the 'i'th TRAP bit in dr6 to denote completion of
+ * exception handling
+ */
+ (*dr6_p) &= ~(DR_TRAP0 << i);
+ /*
+ * bp can be NULL due to lazy debug register switching
+ * or due to the delay between updates of hbp_kernel_pos
+ * and this_hbp_kernel.
+ */
+ if (!bp)
+ continue;
+
+ (bp->triggered)(bp, args->regs);
+ }
+ if (dr6 & (~DR_TRAP_BITS))
+ rc = NOTIFY_DONE;
+
+ set_debugreg(dr7, 7);
+ put_cpu();
+ return rc;
+}
+
+/*
+ * Handle debug exception notifications.
+ */
+int __kprobes hw_breakpoint_exceptions_notify(
+ struct notifier_block *unused, unsigned long val, void *data)
+{
+ if (val != DIE_DEBUG)
+ return NOTIFY_DONE;
+
+ return hw_breakpoint_handler(data);
+}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 8d82a77a3f3..34e86b67550 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/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;
}
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 7b5169d2b00..b5b1848c533 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -54,6 +54,7 @@
#include <asm/pgtable.h>
#include <asm/uaccess.h>
#include <asm/alternative.h>
+#include <asm/debugreg.h>
void jprobe_return_end(void);
@@ -967,8 +968,14 @@ 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:
/*
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index c1c429d0013..c843f8406da 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/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
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 84c3bf209e9..4a8bb82248a 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/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
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 5284cd2b577..2275ce5776d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -17,6 +17,8 @@
#include <asm/uaccess.h>
#include <asm/i387.h>
#include <asm/ds.h>
+#include <asm/debugreg.h>
+#include <asm/hw_breakpoint.h>
unsigned long idle_halt;
EXPORT_SYMBOL(idle_halt);
@@ -45,6 +47,8 @@ void free_thread_xstate(struct task_struct *tsk)
kmem_cache_free(task_xstate_cachep, tsk->thread.xstate);
tsk->thread.xstate = NULL;
}
+ if (unlikely(test_tsk_thread_flag(tsk, TIF_DEBUG)))
+ flush_thread_hw_breakpoint(tsk);
WARN(tsk->thread.ds_ctx, "leaking DS context\n");
}
@@ -105,12 +109,8 @@ void flush_thread(void)
clear_tsk_thread_flag(tsk, TIF_DEBUG);
- tsk->thread.debugreg0 = 0;
- tsk->thread.debugreg1 = 0;
- tsk->thread.debugreg2 = 0;
- tsk->thread.debugreg3 = 0;
- tsk->thread.debugreg6 = 0;
- tsk->thread.debugreg7 = 0;
+ if (unlikely(test_tsk_thread_flag(tsk, TIF_DEBUG)))
+ flush_thread_hw_breakpoint(tsk);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
/*
* Forget coprocessor state..
@@ -192,16 +192,6 @@ 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 */
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 4cf79567cda..209e7480176 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -58,6 +58,8 @@
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/ds.h>
+#include <asm/debugreg.h>
+#include <asm/hw_breakpoint.h>
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
@@ -259,7 +261,13 @@ 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;
+ if (unlikely(test_tsk_thread_flag(tsk, TIF_DEBUG)))
+ if (copy_thread_hw_breakpoint(tsk, p, clone_flags))
+ goto out;
+
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);
@@ -279,10 +287,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
err = do_set_thread_area(p, -1,
(struct user_desc __user *)childregs->si, 0);
+out:
if (err && p->thread.io_bitmap_ptr) {
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
+ if (err)
+ flush_thread_hw_breakpoint(p);
clear_tsk_thread_flag(p, TIF_DS_AREA_MSR);
p->thread.ds_ctx = NULL;
@@ -426,6 +437,23 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
lazy_load_gs(next->gs);
percpu_write(current_task, next_p);
+ /*
+ * There's a problem with moving the arch_install_thread_hw_breakpoint()
+ * call before current is updated. Suppose a kernel breakpoint is
+ * triggered in between the two, the hw-breakpoint handler will see that
+ * the 'current' task does not have TIF_DEBUG flag set and will think it
+ * is leftover from an old task (lazy switching) and will erase it. Then
+ * until the next context switch, no user-breakpoints will be installed.
+ *
+ * The real problem is that it's impossible to update both current and
+ * physical debug registers at the same instant, so there will always be
+ * a window in which they disagree and a breakpoint might get triggered.
+ * Since we use lazy switching, we are forced to assume that a
+ * disagreement means that current is correct and the exception is due
+ * to lazy debug register switching.
+ */
+ if (unlikely(test_tsk_thread_flag(next_p, TIF_DEBUG)))
+ arch_install_thread_hw_breakpoint(next_p);
return prev_p;
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ad535b68317..72edac026a7 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,6 +52,8 @@
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/ds.h>
+#include <asm/debugreg.h>
+#include <asm/hw_breakpoint.h>
asmlinkage extern void ret_from_fork(void);
@@ -242,6 +244,8 @@ void release_thread(struct task_struct *dead_task)
BUG();
}
}
+ if (unlikely(dead_task->thread.debugreg7))
+ flush_thread_hw_breakpoint(dead_task);
}
static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr)
@@ -297,12 +301,18 @@ 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;
+ if (unlikely(test_tsk_thread_flag(me, TIF_DEBUG)))
+ if (copy_thread_hw_breakpoint(me, p, clone_flags))
+ goto out;
+
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 +351,9 @@ out:
kfree(p->thread.io_bitmap_ptr);
p->thread.io_bitmap_max = 0;
}
+ if (err)
+ flush_thread_hw_breakpoint(p);
+
return err;
}
@@ -495,6 +508,24 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
*/
if (preload_fpu)
__math_state_restore();
+ /*
+ * There's a problem with moving the arch_install_thread_hw_breakpoint()
+ * call before current is updated. Suppose a kernel breakpoint is
+ * triggered in between the two, the hw-breakpoint handler will see that
+ * the 'current' task does not have TIF_DEBUG flag set and will think it
+ * is leftover from an old task (lazy switching) and will erase it. Then
+ * until the next context switch, no user-breakpoints will be installed.
+ *
+ * The real problem is that it's impossible to update both current and
+ * physical debug registers at the same instant, so there will always be
+ * a window in which they disagree and a breakpoint might get triggered.
+ * Since we use lazy switching, we are forced to assume that a
+ * disagreement means that current is correct and the exception is due
+ * to lazy debug register switching.
+ */
+ if (unlikely(test_tsk_thread_flag(next_p, TIF_DEBUG)))
+ arch_install_thread_hw_breakpoint(next_p);
+
return prev_p;
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 7b058a2dc66..267cb85b479 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -34,6 +34,7 @@
#include <asm/prctl.h>
#include <asm/proto.h>
#include <asm/ds.h>
+#include <asm/hw_breakpoint.h>
#include "tls.h"
@@ -137,11 +138,6 @@ 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)
@@ -266,15 +262,6 @@ 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)
@@ -455,95 +442,159 @@ static int genregs_set(struct task_struct *target,
}
/*
- * 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.
+ * Decode the length and type bits for a particular breakpoint as
+ * stored in debug register 7. Return the "enabled" status.
*/
-static unsigned long ptrace_get_debugreg(struct task_struct *child, int n)
+static int decode_dr7(unsigned long dr7, int bpnum, unsigned *len,
+ unsigned *type)
{
- 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;
- }
- return 0;
+ int bp_info = dr7 >> (DR_CONTROL_SHIFT + bpnum * DR_CONTROL_SIZE);
+
+ *len = (bp_info & 0xc) | 0x40;
+ *type = (bp_info & 0x3) | 0x80;
+ return (dr7 >> (bpnum * DR_ENABLE_SIZE)) & 0x3;
}
-static int ptrace_set_debugreg(struct task_struct *child,
- int n, unsigned long data)
+static void ptrace_triggered(struct hw_breakpoint *bp, struct pt_regs *regs)
{
+ struct thread_struct *thread = &(current->thread);
int i;
- if (unlikely(n == 4 || n == 5))
- return -EIO;
+ /*
+ * 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_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 (n < 4 && unlikely(data >= debugreg_addr_limit(child)))
- return -EIO;
+ thread->debugreg6 |= (DR_TRAP0 << i);
+}
- 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;
+/*
+ * 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 = thread->debugreg7;
+ int i, orig_ret = 0, rc = 0;
+ int enabled, second_pass = 0;
+ unsigned len, type;
+ struct hw_breakpoint *bp;
+
+ data &= ~DR_CONTROL_RESERVED;
+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->hbp[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;
+ unregister_user_hw_breakpoint(tsk, bp);
+ kfree(bp);
+ }
+ 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);
+ 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);
+}
- 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)
+ val = thread->debugreg[n];
+ else if (n == 6)
+ val = thread->debugreg6;
+ else if (n == 7)
+ val = thread->debugreg7;
+ return val;
+}
- 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;
+/*
+ * 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) {
+ tsk->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;
+ }
+ /* All that's left is DR7 */
+ if (n == 7)
+ rc = ptrace_write_dr7(tsk, val);
- return 0;
+ret_path:
+ return rc;
}
/*
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 6a44a76055a..fbf3b07c856 100644
--- a/arch/x86/kernel/signal.c
+++ b/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) {
/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 565ebc65920..213a7a3e456 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -64,6 +64,7 @@
#include <asm/apic.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
+#include <asm/debugreg.h>
#include <linux/mc146818rtc.h>
#include <asm/smpboot_hooks.h>
@@ -327,6 +328,7 @@ notrace static void __cpuinit start_secondary(void *unused)
x86_cpuinit.setup_percpu_clockev();
wmb();
+ load_debug_registers();
cpu_idle();
}
@@ -1267,6 +1269,7 @@ void cpu_disable_common(void)
remove_cpu_from_maps(cpu);
unlock_vector_lock();
fixup_irqs();
+ hw_breakpoint_disable();
}
int native_cpu_disable(void)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7e37dcee0cc..33399176512 100644
--- a/arch/x86/kernel/traps.c
+++ b/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,
- SIGTRAP) == NOTIFY_STOP)
+ /* Store the virtualized DR6 value */
+ 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 (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
- if (!tsk->thread.debugreg7)
- goto clear_dr7;
+ if (regs->flags & X86_VM_MASK) {
+ handle_vm86_trap((struct kernel_vm86_regs *) regs,
+ error_code, 1);
+ 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
- * kernel space (but re-enable TF when returning to user mode).
+ * Single-stepping through system calls: ignore any exceptions in
+ * 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 (!user_mode(regs))
- goto clear_TF_reenable;
+ if ((dr6 & DR_STEP) && !user_mode(regs)) {
+ tsk->thread.debugreg6 &= ~DR_STEP;
+ set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
+ regs->flags &= ~X86_EFLAGS_TF;
}
-
- si_code = get_si_code(condition);
- /* Ok, finally something we can handle */
- 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);
+ si_code = get_si_code(tsk->thread.debugreg6);
+ if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS))
+ send_sigtrap(tsk, regs, error_code, si_code);
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;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b9695322f5..fc2974adf9b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3644,10 +3644,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
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);
- set_debugreg(current->thread.debugreg1, 1);
- set_debugreg(current->thread.debugreg2, 2);
- set_debugreg(current->thread.debugreg3, 3);
+ set_debugreg(current->thread.debugreg[0], 0);
+ set_debugreg(current->thread.debugreg[1], 1);
+ set_debugreg(current->thread.debugreg[2], 2);
+ set_debugreg(current->thread.debugreg[3], 3);
set_debugreg(current->thread.debugreg6, 6);
set_debugreg(current->thread.debugreg7, 7);
}
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 16ccbd77917..11a4ad4d625 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -540,8 +540,14 @@ kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args)
struct die_args *arg = args;
if (val == DIE_DEBUG && (arg->err & DR_STEP))
- if (post_kmmio_handler(arg->err, arg->regs) == 1)
+ if (post_kmmio_handler(arg->err, arg->regs) == 1) {
+ /*
+ * Reset the BS bit in dr6 (pointed by args->err) to
+ * denote completion of processing
+ */
+ (*(unsigned long *)ERR_PTR(arg->err)) &= ~DR_STEP;
return NOTIFY_STOP;
+ }
return NOTIFY_DONE;
}
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 8aa85f17667..e09a44fc466 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -18,6 +18,7 @@
#include <asm/mce.h>
#include <asm/xcr.h>
#include <asm/suspend.h>
+#include <asm/debugreg.h>
#ifdef CONFIG_X86_32
static struct saved_context saved_context;
@@ -104,6 +105,7 @@ static void __save_processor_state(struct saved_context *ctxt)
ctxt->cr4 = read_cr4();
ctxt->cr8 = read_cr8();
#endif
+ hw_breakpoint_disable();
}
/* Needed by apm.c */
@@ -146,27 +148,7 @@ static void fix_processor_context(void)
/*
* Now maybe reload the debug registers
*/
- if (current->thread.debugreg7) {
-#ifdef CONFIG_X86_32
- set_debugreg(current->thread.debugreg0, 0);
- set_debugreg(current->thread.debugreg1, 1);
- set_debugreg(current->thread.debugreg2, 2);
- set_debugreg(current->thread.debugreg3, 3);
- /* no 4 and 5 */
- set_debugreg(current->thread.debugreg6, 6);
- set_debugreg(current->thread.debugreg7, 7);
-#else
- /* CONFIG_X86_64 */
- loaddebug(&current->thread, 0);
- loaddebug(&current->thread, 1);
- loaddebug(&current->thread, 2);
- loaddebug(&current->thread, 3);
- /* no 4 and 5 */
- loaddebug(&current->thread, 6);
- loaddebug(&current->thread, 7);
-#endif
- }
-
+ load_debug_registers();
}
/**
diff --git a/include/asm-generic/hw_breakpoint.h b/include/asm-generic/hw_breakpoint.h
new file mode 100644
index 00000000000..9bf2d12eb74
--- /dev/null
+++ b/include/asm-generic/hw_breakpoint.h
@@ -0,0 +1,139 @@
+#ifndef _ASM_GENERIC_HW_BREAKPOINT_H
+#define _ASM_GENERIC_HW_BREAKPOINT_H
+
+#ifndef __ARCH_HW_BREAKPOINT_H
+#error "Please don't include this file directly"
+#endif
+
+#ifdef __KERNEL__
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/kallsyms.h>
+
+/**
+ * struct hw_breakpoint - unified kernel/user-space hardware breakpoint
+ * @triggered: callback invoked after target address access
+ * @info: arch-specific breakpoint info (address, length, and type)
+ *
+ * %hw_breakpoint structures are the kernel's way of representing
+ * hardware breakpoints. These are data breakpoints
+ * (also known as "watchpoints", triggered on data access), and the breakpoint's
+ * target address can be located in either kernel space or user space.
+ *
+ * The breakpoint's address, length, and type are highly
+ * architecture-specific. The values are encoded in the @info field; you
+ * specify them when registering the breakpoint. To examine the encoded
+ * values use hw_breakpoint_get_{kaddress,uaddress,len,type}(), declared
+ * below.
+ *
+ * The address is specified as a regular kernel pointer (for kernel-space
+ * breakponts) or as an %__user pointer (for user-space breakpoints).
+ * With register_user_hw_breakpoint(), the address must refer to a
+ * location in user space. The breakpoint will be active only while the
+ * requested task is running. Conversely with
+ * register_kernel_hw_breakpoint(), the address must refer to a location
+ * in kernel space, and the breakpoint will be active on all CPUs
+ * regardless of the current task.
+ *
+ * The length is the breakpoint's extent in bytes, which is subject to
+ * certain limitations. include/asm/hw_breakpoint.h contains macros
+ * defining the available lengths for a specific architecture. Note that
+ * the address's alignment must match the length. The breakpoint will
+ * catch accesses to any byte in the range from address to address +
+ * (length - 1).
+ *
+ * The breakpoint's type indicates the sort of access that will cause it
+ * to trigger. Possible values may include:
+ *
+ * %HW_BREAKPOINT_RW (triggered on read or write access),
+ * %HW_BREAKPOINT_WRITE (triggered on write access), and
+ * %HW_BREAKPOINT_READ (triggered on read access).
+ *
+ * Appropriate macros are defined in include/asm/hw_breakpoint.h; not all
+ * possibilities are available on all architectures. Execute breakpoints
+ * must have length equal to the special value %HW_BREAKPOINT_LEN_EXECUTE.
+ *
+ * When a breakpoint gets hit, the @triggered callback is
+ * invoked in_interrupt with a pointer to the %hw_breakpoint structure and the
+ * processor registers.
+ * Data breakpoints occur after the memory access has taken place.
+ * Breakpoints are disabled during execution @triggered, to avoid
+ * recursive traps and allow unhindered access to breakpointed memory.
+ *
+ * This sample code sets a breakpoint on pid_max and registers a callback
+ * function for writes to that variable. Note that it is not portable
+ * as written, because not all architectures support HW_BREAKPOINT_LEN_4.
+ *
+ * ----------------------------------------------------------------------
+ *
+ * #include <asm/hw_breakpoint.h>
+ *
+ * struct hw_breakpoint my_bp;
+ *
+ * static void my_triggered(struct hw_breakpoint *bp, struct pt_regs *regs)
+ * {
+ * printk(KERN_DEBUG "Inside triggered routine of breakpoint exception\n");
+ * dump_stack();
+ * .......<more debugging output>........
+ * }
+ *
+ * static struct hw_breakpoint my_bp;
+ *
+ * static int init_module(void)
+ * {
+ * ..........<do anything>............
+ * my_bp.info.type = HW_BREAKPOINT_WRITE;
+ * my_bp.info.len = HW_BREAKPOINT_LEN_4;
+ *
+ * my_bp.installed = (void *)my_bp_installed;
+ *
+ * rc = register_kernel_hw_breakpoint(&my_bp);
+ * ..........<do anything>............
+ * }
+ *
+ * static void cleanup_module(void)
+ * {
+ * ..........<do anything>............
+ * unregister_kernel_hw_breakpoint(&my_bp);
+ * ..........<do anything>............
+ * }
+ *
+ * ----------------------------------------------------------------------
+ */
+struct hw_breakpoint {
+ void (*triggered)(struct hw_breakpoint *, struct pt_regs *);
+ struct arch_hw_breakpoint info;
+};
+
+/*
+ * len and type values are defined in include/asm/hw_breakpoint.h.
+ * Available values vary according to the architecture. On i386 the
+ * possibilities are:
+ *
+ * HW_BREAKPOINT_LEN_1
+ * HW_BREAKPOINT_LEN_2
+ * HW_BREAKPOINT_LEN_4
+ * HW_BREAKPOINT_RW
+ * HW_BREAKPOINT_READ
+ *
+ * On other architectures HW_BREAKPOINT_LEN_8 may be available, and the
+ * 1-, 2-, and 4-byte lengths may be unavailable. There also may be
+ * HW_BREAKPOINT_WRITE. You can use #ifdef to check at compile time.
+ */
+
+extern int register_user_hw_breakpoint(struct task_struct *tsk,
+ struct hw_breakpoint *bp);
+extern int modify_user_hw_breakpoint(struct task_struct *tsk,
+ struct hw_breakpoint *bp);
+extern void unregister_user_hw_breakpoint(struct task_struct *tsk,
+ struct hw_breakpoint *bp);
+/*
+ * Kernel breakpoints are not associated with any particular thread.
+ */
+extern int register_kernel_hw_breakpoint(struct hw_breakpoint *bp);
+extern void unregister_kernel_hw_breakpoint(struct hw_breakpoint *bp);
+
+extern unsigned int hbp_kernel_pos;
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_GENERIC_HW_BREAKPOINT_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index b8d4cd8ac0b..17b575ec7d0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -95,6 +95,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
obj-$(CONFIG_SLOW_WORK) += slow-work.o
obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
new file mode 100644
index 00000000000..c1f64e65a9f
--- /dev/null
+++ b/kernel/hw_breakpoint.c
@@ -0,0 +1,378 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) 2007 Alan Stern
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers.
+ * This file contains the arch-independent routines.
+ */
+
+#include <linux/irqflags.h>
+#include <linux/kallsyms.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm/hw_breakpoint.h>
+#include <asm/processor.h>
+
+#ifdef CONFIG_X86
+#include <asm/debugreg.h>
+#endif
+/*
+ * Spinlock that protects all (un)register operations over kernel/user-space
+ * breakpoint requests
+ */
+static DEFINE_SPINLOCK(hw_breakpoint_lock);
+
+/* Array of kernel-space breakpoint structures */
+struct hw_breakpoint *hbp_kernel[HBP_NUM];
+
+/*
+ * Per-processor copy of hbp_kernel[]. Used only when hbp_kernel is being
+ * modified but we need the older copy to handle any hbp exceptions. It will
+ * sync with hbp_kernel[] value after updation is done through IPIs.
+ */
+DEFINE_PER_CPU(struct hw_breakpoint*, this_hbp_kernel[HBP_NUM]);
+
+/*
+ * Kernel breakpoints grow downwards, starting from HBP_NUM
+ * 'hbp_kernel_pos' denotes lowest numbered breakpoint register occupied for
+ * kernel-space request. We will initialise it here and not in an __init
+ * routine because load_debug_registers(), which uses this variable can be
+ * called very early during CPU initialisation.
+ */
+unsigned int hbp_kernel_pos = HBP_NUM;
+
+/*
+ * An array containing refcount of threads using a given bkpt register
+ * Accesses are synchronised by acquiring hw_breakpoint_lock
+ */
+unsigned int hbp_user_refcount[HBP_NUM];
+
+/*
+ * Load the debug registers during startup of a CPU.
+ */
+void load_debug_registers(void)
+{
+ unsigned long flags;
+ struct task_struct *tsk = current;
+
+ spin_lock_bh(&hw_breakpoint_lock);
+
+ /* Prevent IPIs for new kernel breakpoint updates */
+ local_irq_save(flags);
+ arch_update_kernel_hw_breakpoint(NULL);
+ local_irq_restore(flags);
+
+ if (test_tsk_thread_flag(tsk, TIF_DEBUG))
+ arch_install_thread_hw_breakpoint(tsk);
+
+ spin_unlock_bh(&hw_breakpoint_lock);
+}
+
+/*
+ * Erase all the hardware breakpoint info associated with a thread.
+ *
+ * If tsk != current then tsk must not be usable (for example, a
+ * child being cleaned up from a failed fork).
+ */
+void flush_thread_hw_breakpoint(struct task_struct *tsk)
+{
+ int i;
+ struct thread_struct *thread = &(tsk->thread);
+
+ spin_lock_bh(&hw_breakpoint_lock);
+
+ /* The thread no longer has any breakpoints associated with it */
+ clear_tsk_thread_flag(tsk, TIF_DEBUG);
+ for (i = 0; i < HBP_NUM; i++) {
+ if (thread->hbp[i]) {
+ hbp_user_refcount[i]--;
+ kfree(thread->hbp[i]);
+ thread->hbp[i] = NULL;
+ }
+ }
+
+ arch_flush_thread_hw_breakpoint(tsk);
+
+ /* Actually uninstall the breakpoints if necessary */
+ if (tsk == current)
+ arch_uninstall_thread_hw_breakpoint();
+ spin_unlock_bh(&hw_breakpoint_lock);
+}
+
+/*
+ * Copy the hardware breakpoint info from a thread to its cloned child.
+ */
+int copy_thread_hw_breakpoint(struct task_struct *tsk,
+ struct task_struct *child, unsigned long clone_flags)
+{
+ /*
+ * We will assume that breakpoint settings are not inherited
+ * and the child starts out with no debug registers set.
+ * But what about CLONE_PTRACE?
+ */
+ clear_tsk_thread_flag(child, TIF_DEBUG);
+
+ /* We will call flush routine since the debugregs are not inherited */
+ arch_flush_thread_hw_breakpoint(child);
+
+ return 0;
+}
+
+static int __register_user_hw_breakpoint(int pos, struct task_struct *tsk,
+ struct hw_breakpoint *bp)
+{
+ struct thread_struct *thread = &(tsk->thread);
+ int rc;
+
+ /* Do not overcommit. Fail if kernel has used the hbp registers */
+ if (pos >= hbp_kernel_pos)
+ return -ENOSPC;
+
+ rc = arch_validate_hwbkpt_settings(bp, tsk);
+ if (rc)
+ return rc;
+
+ thread->hbp[pos] = bp;
+ hbp_user_refcount[pos]++;
+
+ arch_update_user_hw_breakpoint(pos, tsk);
+ /*
+ * Does it need to be installed right now?
+ * Otherwise it will get installed the next time tsk runs
+ */
+ if (tsk == current)
+ arch_install_thread_hw_breakpoint(tsk);
+
+ return rc;
+}
+
+/*
+ * Modify the address of a hbp register already in use by the task
+ * Do not invoke this in-lieu of a __unregister_user_hw_breakpoint()
+ */
+static int __modify_user_hw_breakpoint(int pos, struct task_struct *tsk,
+ struct hw_breakpoint *bp)
+{
+ struct thread_struct *thread = &(tsk->thread);
+
+ if ((pos >= hbp_kernel_pos) || (arch_validate_hwbkpt_settings(bp, tsk)))
+ return -EINVAL;
+
+ if (thread->hbp[pos] == NULL)
+ return -EINVAL;
+
+ thread->hbp[pos] = bp;
+ /*
+ * 'pos' must be that of a hbp register already used by 'tsk'
+ * Otherwise arch_modify_user_hw_breakpoint() will fail
+ */
+ arch_update_user_hw_breakpoint(pos, tsk);
+
+ if (tsk == current)
+ arch_install_thread_hw_breakpoint(tsk);
+
+ return 0;
+}
+
+static void __unregister_user_hw_breakpoint(int pos, struct task_struct *tsk)
+{
+ hbp_user_refcount[pos]--;
+ tsk->thread.hbp[pos] = NULL;
+
+ arch_update_user_hw_breakpoint(pos, tsk);
+
+ if (tsk == current)
+ arch_install_thread_hw_breakpoint(tsk);
+}
+
+/**
+ * register_user_hw_breakpoint - register a hardware breakpoint for user space
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ * @bp: the breakpoint structure to register
+ *
+ * @bp.info->name or @bp.info->address, @bp.info->len, @bp.info->type and
+ * @bp->triggered must be set properly before invocation
+ *
+ */
+int register_user_hw_breakpoint(struct task_struct *tsk,
+ struct hw_breakpoint *bp)
+{
+ struct thread_struct *thread = &(tsk->thread);
+ int i, rc = -ENOSPC;
+
+ spin_lock_bh(&hw_breakpoint_lock);
+
+ for (i = 0; i < hbp_kernel_pos; i++) {
+ if (!thread->hbp[i]) {
+ rc = __register_user_hw_breakpoint(i, tsk, bp);
+ break;
+ }
+ }
+ if (!rc)
+ set_tsk_thread_flag(tsk, TIF_DEBUG);
+
+ spin_unlock_bh(&hw_breakpoint_lock);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
+
+/**
+ * modify_user_hw_breakpoint - modify a user-space hardware breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ * @bp: the breakpoint structure to unregister
+ *
+ */
+int modify_user_hw_breakpoint(struct task_struct *tsk, struct hw_breakpoint *bp)
+{
+ struct thread_struct *thread = &(tsk->thread);
+ int i, ret = -ENOENT;
+
+ spin_lock_bh(&hw_breakpoint_lock);
+ for (i = 0; i < hbp_kernel_pos; i++) {
+ if (bp == thread->hbp[i]) {
+ ret = __modify_user_hw_breakpoint(i, tsk, bp);
+ break;
+ }
+ }
+ spin_unlock_bh(&hw_breakpoint_lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
+
+/**
+ * unregister_user_hw_breakpoint - unregister a user-space hardware breakpoint
+ * @tsk: pointer to 'task_struct' of the process to which the address belongs
+ * @bp: the breakpoint structure to unregister
+ *
+ */
+void unregister_user_hw_breakpoint(struct task_struct *tsk,
+ struct hw_breakpoint *bp)
+{
+ struct thread_struct *thread = &(tsk->thread);
+ int i, pos = -1, hbp_counter = 0;
+
+ spin_lock_bh(&hw_breakpoint_lock);
+ for (i = 0; i < hbp_kernel_pos; i++) {
+ if (thread->hbp[i])
+ hbp_counter++;
+ if (bp == thread->hbp[i])
+ pos = i;
+ }
+ if (pos >= 0) {
+ __unregister_user_hw_breakpoint(pos, tsk);
+ hbp_counter--;
+ }
+ if (!hbp_counter)
+ clear_tsk_thread_flag(tsk, TIF_DEBUG);
+
+ spin_unlock_bh(&hw_breakpoint_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_user_hw_breakpoint);
+
+/**
+ * register_kernel_hw_breakpoint - register a hardware breakpoint for kernel space
+ * @bp: the breakpoint structure to register
+ *
+ * @bp.info->name or @bp.info->address, @bp.info->len, @bp.info->type and
+ * @bp->triggered must be set properly before invocation
+ *
+ */
+int register_kernel_hw_breakpoint(struct hw_breakpoint *bp)
+{
+ int rc;
+
+ rc = arch_validate_hwbkpt_settings(bp, NULL);
+ if (rc)
+ return rc;
+
+ spin_lock_bh(&hw_breakpoint_lock);
+
+ rc = -ENOSPC;
+ /* Check if we are over-committing */
+ if ((hbp_kernel_pos > 0) && (!hbp_user_refcount[hbp_kernel_pos-1])) {
+ hbp_kernel_pos--;
+ hbp_kernel[hbp_kernel_pos] = bp;
+ on_each_cpu(arch_update_kernel_hw_breakpoint, NULL, 1);
+ rc = 0;
+ }
+
+ spin_unlock_bh(&hw_breakpoint_lock);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(register_kernel_hw_breakpoint);
+
+/**
+ * unregister_kernel_hw_breakpoint - unregister a HW breakpoint for kernel space
+ * @bp: the breakpoint structure to unregister
+ *
+ * Uninstalls and unregisters @bp.
+ */
+void unregister_kernel_hw_breakpoint(struct hw_breakpoint *bp)
+{
+ int i, j;
+
+ spin_lock_bh(&hw_breakpoint_lock);
+
+ /* Find the 'bp' in our list of breakpoints for kernel */
+ for (i = hbp_kernel_pos; i < HBP_NUM; i++)
+ if (bp == hbp_kernel[i])
+ break;
+
+ /* Check if we did not find a match for 'bp'. If so return early */
+ if (i == HBP_NUM) {
+ spin_unlock_bh(&hw_breakpoint_lock);
+ return;
+ }
+
+ /*
+ * We'll shift the breakpoints one-level above to compact if
+ * unregistration creates a hole
+ */
+ for (j = i; j > hbp_kernel_pos; j--)
+ hbp_kernel[j] = hbp_kernel[j-1];
+
+ hbp_kernel[hbp_kernel_pos] = NULL;
+ on_each_cpu(arch_update_kernel_hw_breakpoint, NULL, 1);
+ hbp_kernel_pos++;
+
+ spin_unlock_bh(&hw_breakpoint_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_kernel_hw_breakpoint);
+
+static struct notifier_block hw_breakpoint_exceptions_nb = {
+ .notifier_call = hw_breakpoint_exceptions_notify,
+ /* we need to be notified first */
+ .priority = 0x7fffffff
+};
+
+static int __init init_hw_breakpoint(void)
+{
+ return register_die_notifier(&hw_breakpoint_exceptions_nb);
+}
+
+core_initcall(init_hw_breakpoint);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index b416512ad17..06c3d5be675 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -339,6 +339,27 @@ config POWER_TRACER
power management decisions, specifically the C-state and P-state
behavior.
+config KSYM_TRACER
+ bool "Trace read and write access on kernel memory locations"
+ depends on HAVE_HW_BREAKPOINT
+ select TRACING
+ help
+ This tracer helps find read and write operations on any given kernel
+ symbol i.e. /proc/kallsyms.
+
+config PROFILE_KSYM_TRACER
+ bool "Profile all kernel memory accesses on 'watched' variables"
+ depends on KSYM_TRACER
+ help
+ This tracer profiles kernel accesses on variables watched through the
+ ksym tracer ftrace plugin. Depending upon the hardware, all read
+ and write operations on kernel variables can be monitored for
+ accesses.
+
+ The results will be displayed in:
+ /debugfs/tracing/profile_ksym
+
+ Say N if unsure.
config STACK_TRACER
bool "Trace max stack"
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 26f03ac07c2..0f84c52e58f 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -53,6 +53,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_export.o
obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o
obj-$(CONFIG_EVENT_TRACING) += power-traces.o
libftrace-y := ftrace.o
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4959ada9e0b..91c3d0e9a5a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -15,6 +15,10 @@
#include <linux/trace_seq.h>
#include <linux/ftrace_event.h>
+#ifdef CONFIG_KSYM_TRACER
+#include <asm/hw_breakpoint.h>
+#endif
+
enum trace_type {
__TRACE_FIRST_TYPE = 0,
@@ -37,6 +41,7 @@ enum trace_type {
TRACE_KMEM_ALLOC,
TRACE_KMEM_FREE,
TRACE_BLK,
+ TRACE_KSYM,
__TRACE_LAST_TYPE,
};
@@ -209,6 +214,7 @@ extern void __ftrace_bad_type(void);
TRACE_KMEM_ALLOC); \
IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \
TRACE_KMEM_FREE); \
+ IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
__ftrace_bad_type(); \
} while (0)
@@ -364,6 +370,9 @@ int register_tracer(struct tracer *type);
void unregister_tracer(struct tracer *type);
int is_tracing_stopped(void);
+#define KSYM_SELFTEST_ENTRY "ksym_selftest_dummy"
+extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
+
extern unsigned long nsecs_to_usecs(unsigned long nsecs);
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -438,6 +447,8 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
struct trace_array *tr);
extern int trace_selftest_startup_hw_branches(struct tracer *trace,
struct trace_array *tr);
+extern int trace_selftest_startup_ksym(struct tracer *trace,
+ struct trace_array *tr);
#endif /* CONFIG_FTRACE_STARTUP_TEST */
extern void *head_page(struct trace_array_cpu *data);
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index ead3d724599..e19747d4f86 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -364,3 +364,19 @@ FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
F_printk("type:%u call_site:%lx ptr:%p",
__entry->type_id, __entry->call_site, __entry->ptr)
);
+
+FTRACE_ENTRY(ksym_trace, ksym_trace_entry,
+
+ TRACE_KSYM,
+
+ F_STRUCT(
+ __field( unsigned long, ip )
+ __field( unsigned char, type )
+ __array( char , ksym_name, KSYM_NAME_LEN )
+ __array( char , cmd, TASK_COMM_LEN )
+ ),
+
+ F_printk("ip: %pF type: %d ksym_name: %s cmd: %s",
+ (void *)__entry->ip, (unsigned int)__entry->type,
+ __entry->ksym_name, __entry->cmd)
+);
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
new file mode 100644
index 00000000000..6d5609c6737
--- /dev/null
+++ b/kernel/trace/trace_ksym.c
@@ -0,0 +1,551 @@
+/*
+ * trace_ksym.c - Kernel Symbol Tracer
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+
+#include "trace_output.h"
+#include "trace_stat.h"
+#include "trace.h"
+
+/* For now, let us restrict the no. of symbols traced simultaneously to number
+ * of available hardware breakpoint registers.
+ */
+#define KSYM_TRACER_MAX HBP_NUM
+
+#define KSYM_TRACER_OP_LEN 3 /* rw- */
+
+struct trace_ksym {
+ struct hw_breakpoint *ksym_hbp;
+ unsigned long ksym_addr;
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+ unsigned long counter;
+#endif
+ struct hlist_node ksym_hlist;
+};
+
+static struct trace_array *ksym_trace_array;
+
+static unsigned int ksym_filter_entry_count;
+static unsigned int ksym_tracing_enabled;
+
+static HLIST_HEAD(ksym_filter_head);
+
+static DEFINE_MUTEX(ksym_tracer_mutex);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+
+#define MAX_UL_INT 0xffffffff
+
+void ksym_collect_stats(unsigned long hbp_hit_addr)
+{
+ struct hlist_node *node;
+ struct trace_ksym *entry;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
+ if ((entry->ksym_addr == hbp_hit_addr) &&
+ (entry->counter <= MAX_UL_INT)) {
+ entry->counter++;
+ break;
+ }
+ }
+ rcu_read_unlock();
+}
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+void ksym_hbp_handler(struct hw_breakpoint *hbp, struct pt_regs *regs)
+{
+ struct ring_buffer_event *event;
+ struct ksym_trace_entry *entry;
+ struct ring_buffer *buffer;
+ int pc;
+
+ if (!ksym_tracing_enabled)
+ return;
+
+ buffer = ksym_trace_array->buffer;
+
+ pc = preempt_count();
+
+ event = trace_buffer_lock_reserve(buffer, TRACE_KSYM,
+ sizeof(*entry), 0, pc);
+ if (!event)
+ return;
+
+ entry = ring_buffer_event_data(event);
+ entry->ip = instruction_pointer(regs);
+ entry->type = hbp->info.type;
+ strlcpy(entry->ksym_name, hbp->info.name, KSYM_SYMBOL_LEN);
+ strlcpy(entry->cmd, current->comm, TASK_COMM_LEN);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+ ksym_collect_stats(hbp->info.address);
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+ trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+/* Valid access types are represented as
+ *
+ * rw- : Set Read/Write Access Breakpoint
+ * -w- : Set Write Access Breakpoint
+ * --- : Clear Breakpoints
+ * --x : Set Execution Break points (Not available yet)
+ *
+ */
+static int ksym_trace_get_access_type(char *str)
+{
+ int access = 0;
+
+ if (str[0] == 'r')
+ access += 4;
+ else if (str[0] != '-')
+ return -EINVAL;
+
+ if (str[1] == 'w')
+ access += 2;
+ else if (str[1] != '-')
+ return -EINVAL;
+
+ if (str[2] != '-')
+ return -EINVAL;
+
+ switch (access) {
+ case 6:
+ access = HW_BREAKPOINT_RW;
+ break;
+ case 4:
+ access = -EINVAL;
+ break;
+ case 2:
+ access = HW_BREAKPOINT_WRITE;
+ break;
+ }
+
+ return access;
+}
+
+/*
+ * There can be several possible malformed requests and we attempt to capture
+ * all of them. We enumerate some of the rules
+ * 1. We will not allow kernel symbols with ':' since it is used as a delimiter.
+ * i.e. multiple ':' symbols disallowed. Possible uses are of the form
+ * <module>:<ksym_name>:<op>.
+ * 2. No delimiter symbol ':' in the input string
+ * 3. Spurious operator symbols or symbols not in their respective positions
+ * 4. <ksym_name>:--- i.e. clear breakpoint request when ksym_name not in file
+ * 5. Kernel symbol not a part of /proc/kallsyms
+ * 6. Duplicate requests
+ */
+static int parse_ksym_trace_str(char *input_string, char **ksymname,
+ unsigned long *addr)
+{
+ int ret;
+
+ *ksymname = strsep(&input_string, ":");
+ *addr = kallsyms_lookup_name(*ksymname);
+
+ /* Check for malformed request: (2), (1) and (5) */
+ if ((!input_string) ||
+ (strlen(input_string) != KSYM_TRACER_OP_LEN) ||
+ (*addr == 0))
+ return -EINVAL;;
+
+ ret = ksym_trace_get_access_type(input_string);
+
+ return ret;
+}
+
+int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
+{
+ struct trace_ksym *entry;
+ int ret = -ENOMEM;
+
+ if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
+ printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
+ " new requests for tracing can be accepted now.\n",
+ KSYM_TRACER_MAX);
+ return -ENOSPC;
+ }
+
+ entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
+ if (!entry)
+ return -ENOMEM;
+
+ entry->ksym_hbp = kzalloc(sizeof(struct hw_breakpoint), GFP_KERNEL);
+ if (!entry->ksym_hbp)
+ goto err;
+
+ entry->ksym_hbp->info.name = kstrdup(ksymname, GFP_KERNEL);
+ if (!entry->ksym_hbp->info.name)
+ goto err;
+
+ entry->ksym_hbp->info.type = op;
+ entry->ksym_addr = entry->ksym_hbp->info.address = addr;
+#ifdef CONFIG_X86
+ entry->ksym_hbp->info.len = HW_BREAKPOINT_LEN_4;
+#endif
+ entry->ksym_hbp->triggered = (void *)ksym_hbp_handler;
+
+ ret = register_kernel_hw_breakpoint(entry->ksym_hbp);
+ if (ret < 0) {
+ printk(KERN_INFO "ksym_tracer request failed. Try again"
+ " later!!\n");
+ ret = -EAGAIN;
+ goto err;
+ }
+ hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
+ ksym_filter_entry_count++;
+ return 0;
+err:
+ if (entry->ksym_hbp)
+ kfree(entry->ksym_hbp->info.name);
+ kfree(entry->ksym_hbp);
+ kfree(entry);
+ return ret;
+}
+
+static ssize_t ksym_trace_filter_read(struct file *filp, char __user *ubuf,
+ size_t count, loff_t *ppos)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node;
+ struct trace_seq *s;
+ ssize_t cnt = 0;
+ int ret;
+
+ s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (!s)
+ return -ENOMEM;
+ trace_seq_init(s);
+
+ mutex_lock(&ksym_tracer_mutex);
+
+ hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+ ret = trace_seq_printf(s, "%s:", entry->ksym_hbp->info.name);
+ if (entry->ksym_hbp->info.type == HW_BREAKPOINT_WRITE)
+ ret = trace_seq_puts(s, "-w-\n");
+ else if (entry->ksym_hbp->info.type == HW_BREAKPOINT_RW)
+ ret = trace_seq_puts(s, "rw-\n");
+ WARN_ON_ONCE(!ret);
+ }
+
+ cnt = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+ mutex_unlock(&ksym_tracer_mutex);
+
+ kfree(s);
+
+ return cnt;
+}
+
+static void __ksym_trace_reset(void)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node, *node1;
+
+ mutex_lock(&ksym_tracer_mutex);
+ hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
+ ksym_hlist) {
+ unregister_kernel_hw_breakpoint(entry->ksym_hbp);
+ ksym_filter_entry_count--;
+ hlist_del_rcu(&(entry->ksym_hlist));
+ synchronize_rcu();
+ kfree(entry->ksym_hbp->info.name);
+ kfree(entry->ksym_hbp);
+ kfree(entry);
+ }
+ mutex_unlock(&ksym_tracer_mutex);
+}
+
+static ssize_t ksym_trace_filter_write(struct file *file,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct trace_ksym *entry;
+ struct hlist_node *node;
+ char *input_string, *ksymname = NULL;
+ unsigned long ksym_addr = 0;
+ int ret, op, changed = 0;
+
+ input_string = kzalloc(count + 1, GFP_KERNEL);
+ if (!input_string)
+ return -ENOMEM;
+
+ if (copy_from_user(input_string, buffer, count)) {
+ kfree(input_string);
+ return -EFAULT;
+ }
+ input_string[count] = '\0';
+
+ strstrip(input_string);
+
+ /*
+ * Clear all breakpoints if:
+ * 1: echo > ksym_trace_filter
+ * 2: echo 0 > ksym_trace_filter
+ * 3: echo "*:---" > ksym_trace_filter
+ */
+ if (!input_string[0] || !strcmp(input_string, "0") ||
+ !strcmp(input_string, "*:---")) {
+ __ksym_trace_reset();
+ kfree(input_string);
+ return count;
+ }
+
+ ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr);
+ if (ret < 0) {
+ kfree(input_string);
+ return ret;
+ }
+
+ mutex_lock(&ksym_tracer_mutex);
+
+ ret = -EINVAL;
+ hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+ if (entry->ksym_addr == ksym_addr) {
+ /* Check for malformed request: (6) */
+ if (entry->ksym_hbp->info.type != op)
+ changed = 1;
+ else
+ goto out;
+ break;
+ }
+ }
+ if (changed) {
+ unregister_kernel_hw_breakpoint(entry->ksym_hbp);
+ entry->ksym_hbp->info.type = op;
+ if (op > 0) {
+ ret = register_kernel_hw_breakpoint(entry->ksym_hbp);
+ if (ret == 0)
+ goto out;
+ }
+ ksym_filter_entry_count--;
+ hlist_del_rcu(&(entry->ksym_hlist));
+ synchronize_rcu();
+ kfree(entry->ksym_hbp->info.name);
+ kfree(entry->ksym_hbp);
+ kfree(entry);
+ ret = 0;
+ goto out;
+ } else {
+ /* Check for malformed request: (4) */
+ if (op == 0)
+ goto out;
+ ret = process_new_ksym_entry(ksymname, op, ksym_addr);
+ }
+out:
+ mutex_unlock(&ksym_tracer_mutex);
+
+ kfree(input_string);
+
+ if (!ret)
+ ret = count;
+ return ret;
+}
+
+static const struct file_operations ksym_tracing_fops = {
+ .open = tracing_open_generic,
+ .read = ksym_trace_filter_read,
+ .write = ksym_trace_filter_write,
+};
+
+static void ksym_trace_reset(struct trace_array *tr)
+{
+ ksym_tracing_enabled = 0;
+ __ksym_trace_reset();
+}
+
+static int ksym_trace_init(struct trace_array *tr)
+{
+ int cpu, ret = 0;
+
+ for_each_online_cpu(cpu)
+ tracing_reset(tr, cpu);
+ ksym_tracing_enabled = 1;
+ ksym_trace_array = tr;
+
+ return ret;
+}
+
+static void ksym_trace_print_header(struct seq_file *m)
+{
+ seq_puts(m,
+ "# TASK-PID CPU# Symbol "
+ "Type Function\n");
+ seq_puts(m,
+ "# | | | "
+ " | |\n");
+}
+
+static enum print_line_t ksym_trace_output(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ struct ksym_trace_entry *field;
+ char str[KSYM_SYMBOL_LEN];
+ int ret;
+
+ if (entry->type != TRACE_KSYM)
+ return TRACE_TYPE_UNHANDLED;
+
+ trace_assign_type(field, entry);
+
+ ret = trace_seq_printf(s, "%11s-%-5d [%03d] %-30s ", field->cmd,
+ entry->pid, iter->cpu, field->ksym_name);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ switch (field->type) {
+ case HW_BREAKPOINT_WRITE:
+ ret = trace_seq_printf(s, " W ");
+ break;
+ case HW_BREAKPOINT_RW:
+ ret = trace_seq_printf(s, " RW ");
+ break;
+ default:
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ sprint_symbol(str, field->ip);
+ ret = trace_seq_printf(s, "%s\n", str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+struct tracer ksym_tracer __read_mostly =
+{
+ .name = "ksym_tracer",
+ .init = ksym_trace_init,
+ .reset = ksym_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_ksym,
+#endif
+ .print_header = ksym_trace_print_header,
+ .print_line = ksym_trace_output
+};
+
+__init static int init_ksym_trace(void)
+{
+ struct dentry *d_tracer;
+ struct dentry *entry;
+
+ d_tracer = tracing_init_dentry();
+ ksym_filter_entry_count = 0;
+
+ entry = debugfs_create_file("ksym_trace_filter", 0644, d_tracer,
+ NULL, &ksym_tracing_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'ksym_trace_filter' file\n");
+
+ return register_tracer(&ksym_tracer);
+}
+device_initcall(init_ksym_trace);
+
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+static int ksym_tracer_stat_headers(struct seq_file *m)
+{
+ seq_puts(m, " Access Type ");
+ seq_puts(m, " Symbol Counter\n");
+ seq_puts(m, " ----------- ");
+ seq_puts(m, " ------ -------\n");
+ return 0;
+}
+
+static int ksym_tracer_stat_show(struct seq_file *m, void *v)
+{
+ struct hlist_node *stat = v;
+ struct trace_ksym *entry;
+ int access_type = 0;
+ char fn_name[KSYM_NAME_LEN];
+
+ entry = hlist_entry(stat, struct trace_ksym, ksym_hlist);
+
+ if (entry->ksym_hbp)
+ access_type = entry->ksym_hbp->info.type;
+
+ switch (access_type) {
+ case HW_BREAKPOINT_WRITE:
+ seq_puts(m, " W ");
+ break;
+ case HW_BREAKPOINT_RW:
+ seq_puts(m, " RW ");
+ break;
+ default:
+ seq_puts(m, " NA ");
+ }
+
+ if (lookup_symbol_name(entry->ksym_addr, fn_name) >= 0)
+ seq_printf(m, " %-36s", fn_name);
+ else
+ seq_printf(m, " %-36s", "<NA>");
+ seq_printf(m, " %15lu\n", entry->counter);
+
+ return 0;
+}
+
+static void *ksym_tracer_stat_start(struct tracer_stat *trace)
+{
+ return ksym_filter_head.first;
+}
+
+static void *
+ksym_tracer_stat_next(void *v, int idx)
+{
+ struct hlist_node *stat = v;
+
+ return stat->next;
+}
+
+static struct tracer_stat ksym_tracer_stats = {
+ .name = "ksym_tracer",
+ .stat_start = ksym_tracer_stat_start,
+ .stat_next = ksym_tracer_stat_next,
+ .stat_headers = ksym_tracer_stat_headers,
+ .stat_show = ksym_tracer_stat_show
+};
+
+__init static int ksym_tracer_stat_init(void)
+{
+ int ret;
+
+ ret = register_stat_tracer(&ksym_tracer_stats);
+ if (ret) {
+ printk(KERN_WARNING "Warning: could not register "
+ "ksym tracer stats\n");
+ return 1;
+ }
+
+ return 0;
+}
+fs_initcall(ksym_tracer_stat_init);
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index d2cdbabb4ea..7179c12e4f0 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,6 +17,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
case TRACE_GRAPH_ENT:
case TRACE_GRAPH_RET:
case TRACE_HW_BRANCHES:
+ case TRACE_KSYM:
return 1;
}
return 0;
@@ -808,3 +809,55 @@ trace_selftest_startup_hw_branches(struct tracer *trace,
return ret;
}
#endif /* CONFIG_HW_BRANCH_TRACER */
+
+#ifdef CONFIG_KSYM_TRACER
+static int ksym_selftest_dummy;
+
+int
+trace_selftest_startup_ksym(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long count;
+ int ret;
+
+ /* start the tracing */
+ ret = tracer_init(trace, tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ ksym_selftest_dummy = 0;
+ /* Register the read-write tracing request */
+ ret = process_new_ksym_entry(KSYM_SELFTEST_ENTRY, HW_BREAKPOINT_RW,
+ (unsigned long)(&ksym_selftest_dummy));
+
+ if (ret < 0) {
+ printk(KERN_CONT "ksym_trace read-write startup test failed\n");
+ goto ret_path;
+ }
+ /* Perform a read and a write operation over the dummy variable to
+ * trigger the tracer
+ */
+ if (ksym_selftest_dummy == 0)
+ ksym_selftest_dummy++;
+
+ /* stop the tracing. */
+ tracing_stop();
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ /* read & write operations - one each is performed on the dummy variable
+ * triggering two entries in the trace buffer
+ */
+ if (!ret && count != 2) {
+ printk(KERN_CONT "Ksym tracer startup test failed");
+ ret = -1;
+ }
+
+ret_path:
+ return ret;
+}
+#endif /* CONFIG_KSYM_TRACER */
+
diff --git a/samples/Kconfig b/samples/Kconfig
index b92bde3c6a8..e4be84ac3d3 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -40,5 +40,11 @@ config SAMPLE_KRETPROBES
default m
depends on SAMPLE_KPROBES && KRETPROBES
+config SAMPLE_HW_BREAKPOINT
+ tristate "Build kernel hardware breakpoint examples -- loadable module only"
+ depends on HAVE_HW_BREAKPOINT && m
+ help
+ This builds kernel hardware breakpoint example modules.
+
endif # SAMPLES
diff --git a/samples/Makefile b/samples/Makefile
index 43343a03b1f..0f15e6d77fd 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -1,3 +1,4 @@
# Makefile for Linux samples code
-obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ tracepoints/ trace_events/
+obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ tracepoints/ trace_events/ \
+ hw_breakpoint/
diff --git a/samples/hw_breakpoint/Makefile b/samples/hw_breakpoint/Makefile
new file mode 100644
index 00000000000..0f5c31c2fc4
--- /dev/null
+++ b/samples/hw_breakpoint/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_SAMPLE_HW_BREAKPOINT) += data_breakpoint.o
diff --git a/samples/hw_breakpoint/data_breakpoint.c b/samples/hw_breakpoint/data_breakpoint.c
new file mode 100644
index 00000000000..9cbdbb871b7
--- /dev/null
+++ b/samples/hw_breakpoint/data_breakpoint.c
@@ -0,0 +1,83 @@
+/*
+ * data_breakpoint.c - Sample HW Breakpoint file to watch kernel data address
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * usage: insmod data_breakpoint.ko ksym=<ksym_name>
+ *
+ * This file is a kernel module that places a breakpoint over ksym_name kernel
+ * variable using Hardware Breakpoint register. The corresponding handler which
+ * prints a backtrace is invoked everytime a write operation is performed on
+ * that variable.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+#include <linux/module.h> /* Needed by all modules */
+#include <linux/kernel.h> /* Needed for KERN_INFO */
+#include <linux/init.h> /* Needed for the macros */
+
+#include <asm/hw_breakpoint.h>
+
+struct hw_breakpoint sample_hbp;
+
+static char ksym_name[KSYM_NAME_LEN] = "pid_max";
+module_param_string(ksym, ksym_name, KSYM_NAME_LEN, S_IRUGO);
+MODULE_PARM_DESC(ksym, "Kernel symbol to monitor; this module will report any"
+ " write operations on the kernel symbol");
+
+void sample_hbp_handler(struct hw_breakpoint *temp, struct pt_regs
+ *temp_regs)
+{
+ printk(KERN_INFO "%s value is changed\n", ksym_name);
+ dump_stack();
+ printk(KERN_INFO "Dump stack from sample_hbp_handler\n");
+}
+
+static int __init hw_break_module_init(void)
+{
+ int ret;
+
+#ifdef CONFIG_X86
+ sample_hbp.info.name = ksym_name;
+ sample_hbp.info.type = HW_BREAKPOINT_WRITE;
+ sample_hbp.info.len = HW_BREAKPOINT_LEN_4;
+#endif /* CONFIG_X86 */
+
+ sample_hbp.triggered = (void *)sample_hbp_handler;
+
+ ret = register_kernel_hw_breakpoint(&sample_hbp);
+
+ if (ret < 0) {
+ printk(KERN_INFO "Breakpoint registration failed\n");
+ return ret;
+ } else
+ printk(KERN_INFO "HW Breakpoint for %s write installed\n",
+ ksym_name);
+
+ return 0;
+}
+
+static void __exit hw_break_module_exit(void)
+{
+ unregister_kernel_hw_breakpoint(&sample_hbp);
+ printk(KERN_INFO "HW Breakpoint for %s write uninstalled\n", ksym_name);
+}
+
+module_init(hw_break_module_init);
+module_exit(hw_break_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("K.Prasad");
+MODULE_DESCRIPTION("ksym breakpoint");