aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc
diff options
context:
space:
mode:
authorSrinivasa D S <srinivasa@in.ibm.com>2008-07-25 04:46:04 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2008-07-25 13:53:30 -0400
commitef53d9c5e4da147ecaa43c44c5e5945eb83970a2 (patch)
tree3b596445e5d0613fda4b33a4ae96e0e3fffdcf1e /arch/powerpc
parent53a9600c634e3bfd6230e0597aca159bf4d4d010 (diff)
kprobes: improve kretprobe scalability with hashed locking
Currently list of kretprobe instances are stored in kretprobe object (as used_instances,free_instances) and in kretprobe hash table. We have one global kretprobe lock to serialise the access to these lists. This causes only one kretprobe handler to execute at a time. Hence affects system performance, particularly on SMP systems and when return probe is set on lot of functions (like on all systemcalls). Solution proposed here gives fine-grain locks that performs better on SMP system compared to present kretprobe implementation. Solution: 1) Instead of having one global lock to protect kretprobe instances present in kretprobe object and kretprobe hash table. We will have two locks, one lock for protecting kretprobe hash table and another lock for kretporbe object. 2) We hold lock present in kretprobe object while we modify kretprobe instance in kretprobe object and we hold per-hash-list lock while modifying kretprobe instances present in that hash list. To prevent deadlock, we never grab a per-hash-list lock while holding a kretprobe lock. 3) We can remove used_instances from struct kretprobe, as we can track used instances of kretprobe instances using kretprobe hash table. Time duration for kernel compilation ("make -j 8") on a 8-way ppc64 system with return probes set on all systemcalls looks like this. cacheline non-cacheline Un-patched kernel aligned patch aligned patch =============================================================================== real 9m46.784s 9m54.412s 10m2.450s user 40m5.715s 40m7.142s 40m4.273s sys 2m57.754s 2m58.583s 3m17.430s =========================================================== Time duration for kernel compilation ("make -j 8) on the same system, when kernel is not probed. ========================= real 9m26.389s user 40m8.775s sys 2m7.283s ========================= Signed-off-by: Srinivasa DS <srinivasa@in.ibm.com> Signed-off-by: Jim Keniston <jkenisto@us.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Masami Hiramatsu <mhiramat@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/kernel/kprobes.c6
1 files changed, 2 insertions, 4 deletions
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 4ba2af125450..de79915452c8 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -144,7 +144,6 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
144 kcb->kprobe_saved_msr = regs->msr; 144 kcb->kprobe_saved_msr = regs->msr;
145} 145}
146 146
147/* Called with kretprobe_lock held */
148void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, 147void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
149 struct pt_regs *regs) 148 struct pt_regs *regs)
150{ 149{
@@ -312,8 +311,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
312 unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline; 311 unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
313 312
314 INIT_HLIST_HEAD(&empty_rp); 313 INIT_HLIST_HEAD(&empty_rp);
315 spin_lock_irqsave(&kretprobe_lock, flags); 314 kretprobe_hash_lock(current, &head, &flags);
316 head = kretprobe_inst_table_head(current);
317 315
318 /* 316 /*
319 * It is possible to have multiple instances associated with a given 317 * It is possible to have multiple instances associated with a given
@@ -352,7 +350,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
352 regs->nip = orig_ret_address; 350 regs->nip = orig_ret_address;
353 351
354 reset_current_kprobe(); 352 reset_current_kprobe();
355 spin_unlock_irqrestore(&kretprobe_lock, flags); 353 kretprobe_hash_unlock(current, &flags);
356 preempt_enable_no_resched(); 354 preempt_enable_no_resched();
357 355
358 hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { 356 hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {