[PATCH] Kprobes: rearrange preempt_disable/enable() calls

The following set of patches are aimed at improving kprobes scalability.  We
currently serialize kprobe registration, unregistration and handler execution
using a single spinlock - kprobe_lock.

With these changes, kprobe handlers can run without any locks held.  It also
allows for simultaneous kprobe handler executions on different processors as
we now track kprobe execution on a per processor basis.  It is now necessary
that the handlers be re-entrant since handlers can run concurrently on
multiple processors.

All changes have been tested on i386, ia64, ppc64 and x86_64, while sparc64
has been compile tested only.

The patches can be viewed as 3 logical chunks:

patch 1: 	Reorder preempt_(dis/en)able calls
patches 2-7: 	Introduce per_cpu data areas to track kprobe execution
patches 8-9: 	Use RCU to synchronize kprobe (un)registration and handler
		execution.

Thanks to Maneesh Soni, James Keniston and Anil Keshavamurthy for their
review and suggestions. Thanks again to Anil, Hien Nguyen and Kevin Stafford
for testing the patches.

This patch:

Reorder preempt_disable/enable() calls in arch kprobes files in preparation to
introduce locking changes.  No functional changes introduced by this patch.

Signed-off-by: Ananth N Mavinakayahanalli <ananth@in.ibm.com>
Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 18 insertions, 17 deletions

diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 6345b430b105..fd35039859e6 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -158,8 +158,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	kprobe_opcode_t *addr = NULL;
 	unsigned long *lp;
 
-	/* We're in an interrupt, but this is clear and BUG()-safe. */
-	preempt_disable();
 	/* Check if the application is using LDT entry for its code segment and
 	 * calculate the address by reading the base address from the LDT entry.
 	 */
@@ -232,6 +230,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 		goto no_kprobe;
 	}
 
+	/*
+	 * This preempt_disable() matches the preempt_enable_no_resched()
+	 * in post_kprobe_handler()
+	 */
+	preempt_disable();
 	kprobe_status = KPROBE_HIT_ACTIVE;
 	set_current_kprobe(p, regs);
 
@@ -245,7 +248,6 @@ ss_probe:
 	return 1;
 
 no_kprobe:
-	preempt_enable_no_resched();
 	return ret;
 }
 
@@ -313,11 +315,11 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	unlock_kprobes();
 	preempt_enable_no_resched();
 
-        /*
-         * By returning a non-zero value, we are telling
-         * kprobe_handler() that we have handled unlocking
-         * and re-enabling preemption.
-         */
+	/*
+	 * By returning a non-zero value, we are telling
+	 * kprobe_handler() that we have handled unlocking
+	 * and re-enabling preemption
+	 */
         return 1;
 }
 
@@ -453,29 +455,29 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 				       unsigned long val, void *data)
 {
 	struct die_args *args = (struct die_args *)data;
+	int ret = NOTIFY_DONE;
+
+	preempt_disable();
 	switch (val) {
 	case DIE_INT3:
 		if (kprobe_handler(args->regs))
-			return NOTIFY_STOP;
+			ret = NOTIFY_STOP;
 		break;
 	case DIE_DEBUG:
 		if (post_kprobe_handler(args->regs))
-			return NOTIFY_STOP;
+			ret = NOTIFY_STOP;
 		break;
 	case DIE_GPF:
-		if (kprobe_running() &&
-		    kprobe_fault_handler(args->regs, args->trapnr))
-			return NOTIFY_STOP;
-		break;
 	case DIE_PAGE_FAULT:
 		if (kprobe_running() &&
 		    kprobe_fault_handler(args->regs, args->trapnr))
-			return NOTIFY_STOP;
+			ret = NOTIFY_STOP;
 		break;
 	default:
 		break;
 	}
-	return NOTIFY_DONE;
+	preempt_enable();
+	return ret;
 }
 
 int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
@@ -502,7 +504,6 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 
 void __kprobes jprobe_return(void)
 {
-	preempt_enable_no_resched();
 	asm volatile ("       xchgl   %%ebx,%%esp     \n"
 		      "       int3			\n"
 		      "       .globl jprobe_return_end	\n"