diff options
author | Ananth N Mavinakayanahalli <ananth@in.ibm.com> | 2005-11-07 01:00:07 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@g5.osdl.org> | 2005-11-07 07:53:45 -0800 |
commit | 66ff2d0691e00e1e7bfdf398a970310c9a0fe671 (patch) | |
tree | f53bcd846be8fbaee5a5ee65f9bacc5b34392090 /arch/ia64/kernel/kprobes.c | |
parent | b385676b355549afc9a7507ce09c7df47f166521 (diff) |
[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>
Diffstat (limited to 'arch/ia64/kernel/kprobes.c')
-rw-r--r-- | arch/ia64/kernel/kprobes.c | 22 |
1 files changed, 14 insertions, 8 deletions
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 471086b808a..1e80ec80dd2 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -395,7 +395,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) /* * By returning a non-zero value, we are telling * kprobe_handler() that we have handled unlocking - * and re-enabling preemption. + * and re-enabling preemption */ return 1; } @@ -607,8 +607,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) struct pt_regs *regs = args->regs; kprobe_opcode_t *addr = (kprobe_opcode_t *)instruction_pointer(regs); - preempt_disable(); - /* Handle recursion cases */ if (kprobe_running()) { p = get_kprobe(addr); @@ -665,6 +663,11 @@ static int __kprobes pre_kprobes_handler(struct die_args *args) goto no_kprobe; } + /* + * This preempt_disable() matches the preempt_enable_no_resched() + * in post_kprobes_handler() + */ + preempt_disable(); kprobe_status = KPROBE_HIT_ACTIVE; set_current_kprobe(p); @@ -682,7 +685,6 @@ ss_probe: return 1; no_kprobe: - preempt_enable_no_resched(); return ret; } @@ -733,22 +735,26 @@ 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_BREAK: if (pre_kprobes_handler(args)) - return NOTIFY_STOP; + ret = NOTIFY_STOP; break; case DIE_SS: if (post_kprobes_handler(args->regs)) - return NOTIFY_STOP; + ret = NOTIFY_STOP; break; case DIE_PAGE_FAULT: if (kprobes_fault_handler(args->regs, args->trapnr)) - return NOTIFY_STOP; + ret = NOTIFY_STOP; default: break; } - return NOTIFY_DONE; + preempt_enable(); + return ret; } int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) |