summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
authorSrinivasa D S <srinivasa@in.ibm.com>2008-07-25 12:46:04 +0400
committerLinus Torvalds <torvalds@linux-foundation.org>2008-07-25 21:53:30 +0400
commitef53d9c5e4da147ecaa43c44c5e5945eb83970a2 (patch)
tree3b596445e5d0613fda4b33a4ae96e0e3fffdcf1e /arch/x86
parent53a9600c634e3bfd6230e0597aca159bf4d4d010 (diff)
downloadlinux-ef53d9c5e4da147ecaa43c44c5e5945eb83970a2.tar.xz
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/x86')
-rw-r--r--arch/x86/kernel/kprobes.c6
1 files changed, 2 insertions, 4 deletions
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 43c019f85f0d..6c27679ec6aa 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -431,7 +431,6 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
regs->ip = (unsigned long)p->ainsn.insn;
}
-/* Called with kretprobe_lock held */
void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
@@ -682,8 +681,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
INIT_HLIST_HEAD(&empty_rp);
- spin_lock_irqsave(&kretprobe_lock, flags);
- head = kretprobe_inst_table_head(current);
+ kretprobe_hash_lock(current, &head, &flags);
/* fixup registers */
#ifdef CONFIG_X86_64
regs->cs = __KERNEL_CS;
@@ -732,7 +730,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
kretprobe_assert(ri, orig_ret_address, trampoline_address);
- spin_unlock_irqrestore(&kretprobe_lock, flags);
+ kretprobe_hash_unlock(current, &flags);
hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
hlist_del(&ri->hlist);