From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@elte.hu>,
Andrew Morton <akpm@linux-foundation.org>,
Frederic Weisbecker <fweisbec@gmail.com>,
Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>,
"H. Peter Anvin" <hpa@zytor.com>
Subject: [PATCH 3/9][RFC] ftrace: Speed up search by skipping pages by address
Date: Wed, 02 May 2012 15:24:21 -0400 [thread overview]
Message-ID: <20120502193236.535319046@goodmis.org> (raw)
In-Reply-To: 20120502192418.024103772@goodmis.org
[-- Attachment #1: 0003-ftrace-Speed-up-search-by-skipping-pages-by-address.patch --]
[-- Type: text/plain, Size: 1977 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
As all records in a page of the ftrace table are sorted, we can
speed up the search algorithm by checking if the address to look for
falls in between the first and last record ip on the page.
This speeds up both the ftrace_location() and ftrace_text_reserved()
algorithms, as it can skip full pages when the search address is
not in them.
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
kernel/trace/ftrace.c | 22 ++++++++++++++++------
1 file changed, 16 insertions(+), 6 deletions(-)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4e608f8..333f890 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1411,6 +1411,8 @@ int ftrace_location(unsigned long ip)
key.ip = ip;
for (pg = ftrace_pages_start; pg; pg = pg->next) {
+ if (ip < pg->records[0].ip || ip > pg->records[pg->index - 1].ip)
+ continue;
rec = bsearch(&key, pg->records, pg->index,
sizeof(struct dyn_ftrace),
ftrace_cmp_recs);
@@ -1571,16 +1573,24 @@ void ftrace_bug(int failed, unsigned long ip)
/* Return 1 if the address range is reserved for ftrace */
-int ftrace_text_reserved(void *start, void *end)
+int ftrace_text_reserved(void *s, void *e)
{
struct dyn_ftrace *rec;
struct ftrace_page *pg;
+ unsigned long start = (unsigned long)s;
+ unsigned long end = (unsigned long)e;
+ int i;
- do_for_each_ftrace_rec(pg, rec) {
- if (rec->ip <= (unsigned long)end &&
- rec->ip + MCOUNT_INSN_SIZE > (unsigned long)start)
- return 1;
- } while_for_each_ftrace_rec();
+ for (pg = ftrace_pages_start; pg; pg = pg->next) {
+ if (end < pg->records[0].ip ||
+ start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE))
+ continue;
+ for (i = 0; i < pg->index; i++) {
+ rec = &pg->records[i];
+ if (rec->ip <= end && rec->ip + MCOUNT_INSN_SIZE > start)
+ return 1;
+ }
+ }
return 0;
}
--
1.7.9.5
next prev parent reply other threads:[~2012-05-02 19:32 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-02 19:24 [PATCH 0/9][RFC] ftrace: ftrace location lookup speedup, and clean ups Steven Rostedt
2012-05-02 19:24 ` [PATCH 1/9][RFC] ftrace: Sort all function addresses, not just per page Steven Rostedt
2012-05-02 19:24 ` [PATCH 2/9][RFC] ftrace: Remove extra helper functions Steven Rostedt
2012-05-02 19:24 ` Steven Rostedt [this message]
2012-05-02 19:24 ` [PATCH 4/9][RFC] ftrace: Consolidate ftrace_location() and ftrace_text_reserved() Steven Rostedt
2012-05-02 19:24 ` [PATCH 5/9][RFC] ftrace: Return record ip addr for ftrace_location() Steven Rostedt
2012-05-02 19:24 ` [PATCH 6/9][RFC] kprobes: Allow probe on ftrace reserved text (but move it) Steven Rostedt
2012-05-02 20:40 ` Frank Ch. Eigler
2012-05-02 23:40 ` Steven Rostedt
2012-05-07 11:37 ` Masami Hiramatsu
2012-05-07 11:59 ` Masami Hiramatsu
2012-05-07 12:44 ` Steven Rostedt
2012-05-07 12:51 ` Steven Rostedt
2012-05-07 12:43 ` Steven Rostedt
2012-05-08 3:08 ` Masami Hiramatsu
2012-05-08 13:04 ` Steven Rostedt
2012-05-09 5:53 ` Masami Hiramatsu
2012-05-09 8:12 ` Masami Hiramatsu
2012-05-09 9:02 ` Masami Hiramatsu
2012-05-09 14:50 ` Steven Rostedt
2012-05-10 11:54 ` [RFC PATCH -tip ] x86/kprobes: kprobes call optimization Masami Hiramatsu
2012-05-11 8:29 ` Masami Hiramatsu
2012-05-02 19:24 ` [PATCH 7/9][RFC] ftrace: Make ftrace_modify_all_code() global for archs to use Steven Rostedt
2012-05-02 19:24 ` [PATCH 8/9][RFC] ftrace/x86: Have x86 ftrace use the ftrace_modify_all_code() Steven Rostedt
2012-05-02 19:24 ` [PATCH 9/9][RFC] ftrace: Remove selecting FRAME_POINTER with FUNCTION_TRACER Steven Rostedt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20120502193236.535319046@goodmis.org \
--to=rostedt@goodmis.org \
--cc=akpm@linux-foundation.org \
--cc=fweisbec@gmail.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=masami.hiramatsu.pt@hitachi.com \
--cc=mingo@elte.hu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.