[PATCH] kprobes: prevent possible race conditions x86_64 changes

This patch contains the x86_64 architecture specific changes to prevent the
possible race conditions.

Signed-off-by: Prasanna S Panchamukhi <prasanna@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

5 files changed, 39 insertions, 27 deletions

diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S
index 096d470e280f..be51dbe1f75e 100644
--- a/arch/x86_64/kernel/entry.S
+++ b/arch/x86_64/kernel/entry.S
@@ -784,8 +784,9 @@ ENTRY(execve)
         ret
         CFI_ENDPROC
 
-ENTRY(page_fault)
+KPROBE_ENTRY(page_fault)
         errorentry do_page_fault
+        .previous .text
 
 ENTRY(coprocessor_error)
         zeroentry do_coprocessor_error
@@ -797,13 +798,14 @@ ENTRY(device_not_available)
         zeroentry math_state_restore
 
         /* runs on exception stack */
-ENTRY(debug)
+KPROBE_ENTRY(debug)
         CFI_STARTPROC
         pushq $0
         CFI_ADJUST_CFA_OFFSET 8         
         paranoidentry do_debug
         jmp paranoid_exit
         CFI_ENDPROC
+        .previous .text
 
         /* runs on exception stack */   
 ENTRY(nmi)
@@ -854,8 +856,9 @@ paranoid_schedule:
         jmp paranoid_userspace
         CFI_ENDPROC
 
-ENTRY(int3)
+KPROBE_ENTRY(int3)
         zeroentry do_int3       
+        .previous .text
 
 ENTRY(overflow)
         zeroentry do_overflow
@@ -892,8 +895,9 @@ ENTRY(stack_segment)
         jmp paranoid_exit
         CFI_ENDPROC
 
-ENTRY(general_protection)
+KPROBE_ENTRY(general_protection)
         errorentry do_general_protection
+        .previous .text
 
 ENTRY(alignment_check)
         errorentry do_alignment_check
diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c
index 5c6dc7051482..c21cceaea275 100644
--- a/arch/x86_64/kernel/kprobes.c
+++ b/arch/x86_64/kernel/kprobes.c
@@ -74,7 +74,7 @@ static inline int is_IF_modifier(kprobe_opcode_t *insn)
         return 0;
 }
 
-int arch_prepare_kprobe(struct kprobe *p)
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
         /* insn: must be on special executable page on x86_64. */
         up(&kprobe_mutex);
@@ -189,7 +189,7 @@ static inline s32 *is_riprel(u8 *insn)
         return NULL;
 }
 
-void arch_copy_kprobe(struct kprobe *p)
+void __kprobes arch_copy_kprobe(struct kprobe *p)
 {
         s32 *ripdisp;
         memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE);
@@ -215,21 +215,21 @@ void arch_copy_kprobe(struct kprobe *p)
         p->opcode = *p->addr;
 }
 
-void arch_arm_kprobe(struct kprobe *p)
+void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
         *p->addr = BREAKPOINT_INSTRUCTION;
         flush_icache_range((unsigned long) p->addr,
                            (unsigned long) p->addr + sizeof(kprobe_opcode_t));
 }
 
-void arch_disarm_kprobe(struct kprobe *p)
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
         *p->addr = p->opcode;
         flush_icache_range((unsigned long) p->addr,
                            (unsigned long) p->addr + sizeof(kprobe_opcode_t));
 }
 
-void arch_remove_kprobe(struct kprobe *p)
+void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
         up(&kprobe_mutex);
         free_insn_slot(p->ainsn.insn);
@@ -261,7 +261,7 @@ static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs)
                 kprobe_saved_rflags &= ~IF_MASK;
 }
 
-static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
         regs->eflags |= TF_MASK;
         regs->eflags &= ~IF_MASK;
@@ -272,7 +272,8 @@ static void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
                 regs->rip = (unsigned long)p->ainsn.insn;
 }
 
-void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
+                                      struct pt_regs *regs)
 {
         unsigned long *sara = (unsigned long *)regs->rsp;
         struct kretprobe_instance *ri;
@@ -295,7 +296,7 @@ void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled thorough out this function.
  */
-int kprobe_handler(struct pt_regs *regs)
+int __kprobes kprobe_handler(struct pt_regs *regs)
 {
         struct kprobe *p;
         int ret = 0;
@@ -399,7 +400,7 @@ no_kprobe:
 /*
  * Called when we hit the probe point at kretprobe_trampoline
  */
-int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
         struct kretprobe_instance *ri = NULL;
         struct hlist_head *head;
@@ -478,7 +479,7 @@ int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
  * that is atop the stack is the address following the copied instruction.
  * We need to make it the address following the original instruction.
  */
-static void resume_execution(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
         unsigned long *tos = (unsigned long *)regs->rsp;
         unsigned long next_rip = 0;
@@ -536,7 +537,7 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs)
  * Interrupts are disabled on entry as trap1 is an interrupt gate and they
  * remain disabled thoroughout this function.  And we hold kprobe lock.
  */
-int post_kprobe_handler(struct pt_regs *regs)
+int __kprobes post_kprobe_handler(struct pt_regs *regs)
 {
         if (!kprobe_running())
                 return 0;
@@ -571,7 +572,7 @@ out:
 }
 
 /* Interrupts disabled, kprobe_lock held. */
-int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
         if (current_kprobe->fault_handler
             && current_kprobe->fault_handler(current_kprobe, regs, trapnr))
@@ -590,8 +591,8 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 /*
  * Wrapper routine for handling exceptions.
  */
-int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
-                             void *data)
+int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
+                                       unsigned long val, void *data)
 {
         struct die_args *args = (struct die_args *)data;
         switch (val) {
@@ -619,7 +620,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
         return NOTIFY_DONE;
 }
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
         struct jprobe *jp = container_of(p, struct jprobe, kp);
         unsigned long addr;
@@ -640,7 +641,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
         return 1;
 }
 
-void jprobe_return(void)
+void __kprobes jprobe_return(void)
 {
         preempt_enable_no_resched();
         asm volatile ("       xchg   %%rbx,%%rsp     \n"
@@ -651,7 +652,7 @@ void jprobe_return(void)
                       (jprobe_saved_rsp):"memory");
 }
 
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
         u8 *addr = (u8 *) (regs->rip - 1);
         unsigned long stack_addr = (unsigned long)jprobe_saved_rsp;
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 6ead433a3885..f238d6078a5a 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/nmi.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -419,8 +420,9 @@ void die_nmi(char *str, struct pt_regs *regs)
         do_exit(SIGSEGV);
 }
 
-static void do_trap(int trapnr, int signr, char *str, 
-                           struct pt_regs * regs, long error_code, siginfo_t *info)
+static void __kprobes do_trap(int trapnr, int signr, char *str,
+                              struct pt_regs * regs, long error_code,
+                              siginfo_t *info)
 {
         conditional_sti(regs);
 
@@ -504,7 +506,8 @@ DO_ERROR(18, SIGSEGV, "reserved", reserved)
 DO_ERROR(12, SIGBUS,  "stack segment", stack_segment)
 DO_ERROR( 8, SIGSEGV, "double fault", double_fault)
 
-asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
+asmlinkage void __kprobes do_general_protection(struct pt_regs * regs,
+                                                long error_code)
 {
         conditional_sti(regs);
 
@@ -622,7 +625,7 @@ asmlinkage void default_do_nmi(struct pt_regs *regs)
                 io_check_error(reason, regs);
 }
 
-asmlinkage void do_int3(struct pt_regs * regs, long error_code)
+asmlinkage void __kprobes do_int3(struct pt_regs * regs, long error_code)
 {
         if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) {
                 return;
@@ -653,7 +656,8 @@ asmlinkage struct pt_regs *sync_regs(struct pt_regs *eregs)
 }
 
 /* runs on IST stack. */
-asmlinkage void do_debug(struct pt_regs * regs, unsigned long error_code)
+asmlinkage void __kprobes do_debug(struct pt_regs * regs,
+                                   unsigned long error_code)
 {
         unsigned long condition;
         struct task_struct *tsk = current;
diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S
index 2a94f9b60b2d..d4abb07af52d 100644
--- a/arch/x86_64/kernel/vmlinux.lds.S
+++ b/arch/x86_64/kernel/vmlinux.lds.S
@@ -21,6 +21,7 @@ SECTIONS
         *(.text)
         SCHED_TEXT
         LOCK_TEXT
+        KPROBES_TEXT
         *(.fixup)
         *(.gnu.warning)
         } = 0x9090
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index ca914c3bd49c..816732d8858c 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -23,6 +23,7 @@
 #include <linux/vt_kern.h>              /* For unblank_screen() */
 #include <linux/compiler.h>
 #include <linux/module.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -294,7 +295,8 @@ int exception_trace = 1;
  *      bit 2 == 0 means kernel, 1 means user-mode
  *      bit 3 == 1 means fault was an instruction fetch
  */
-asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code)
+asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
+                                        unsigned long error_code)
 {
         struct task_struct *tsk;
         struct mm_struct *mm;