All of lore.kernel.org
 help / color / mirror / Atom feed
From: Masami Hiramatsu <mhiramat@redhat.com>
To: Ananth N Mavinakayanahalli <ananth@in.ibm.com>,
	Jim Keniston <jkenisto@us.ibm.com>, Ingo Molnar <mingo@elte.hu>,
	Andrew Morton <akpm@linux-foundation.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
	systemtap-ml <systemtap@sources.redhat.com>,
	Vegard Nossum <vegard.nossum@gmail.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Andi Kleen <andi@firstfloor.org>, Avi Kivity <avi@redhat.com>,
	"Frank Ch. Eigler" <fche@redhat.com>,
	Satoshi Oshima <satoshi.oshima.fk@hitachi.com>
Subject: [RFC][PROTO][PATCH -tip 7/7] kprobes: x86: check specified probe can be optimized
Date: Mon, 06 Apr 2009 17:43:45 -0400	[thread overview]
Message-ID: <49DA7791.7030603@redhat.com> (raw)

Introduce can_optimize() function for ensuring that user specified probe
address can be jump optimized by decoding instructions.
This function decodes whole of a function in which probe is inserted, and
checks following condition:
 - There is no indirect jump instruction, because it will jumps into
   the address range which is replaced by jump oprand.
 - There is no jump/loop instruction which jumps into the address range
   which is replaced by jump oprand.

Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
---

 arch/x86/kernel/kprobes.c |   75 +++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 75 insertions(+), 0 deletions(-)


diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 5635e02..1386e34 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -1253,6 +1253,78 @@ static int __kprobes prepare_copied_insn(u8 *buf, struct optimized_kprobe *op)
 	return len;
 }

+/* Dummy buffers for lookup_symbol_attrs */
+static char __dummy_buf[KSYM_NAME_LEN];
+
+/* Check whether insn is indirect jump */
+static int insn_is_indirect_jump(struct insn *insn)
+{
+	return (OPCODE1(insn) == 0xff || OPCODE1(insn) == 0xea);
+}
+
+/* Check whether insn jumps into specified address range */
+static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
+{
+	unsigned long target = 0;
+	switch (OPCODE1(insn)) {
+	case 0xe0:	/* loopne */
+	case 0xe1:	/* loope */
+	case 0xe2:	/* loop */
+	case 0xe3:	/* jcxz */
+	case 0xe9:	/* near relative jump */
+	case 0xeb:	/* short relative jump */
+		break;
+	case 0x0f:
+		if ((OPCODE2(insn) & 0xf0) == 0x80) /* jcc near */
+			break;
+		return 0;
+	default:
+		if ((OPCODE1(insn) & 0xf0) == 0x70) /* jcc short */
+			break;
+		return 0;
+	}
+	target = (unsigned long)insn->next_byte + insn->immediate.value;
+	return (start <= target && target <= start + len);
+}
+
+/* Decode whole function to ensure any instructions don't jump into target */
+static int __kprobes can_optimize(unsigned long paddr)
+{
+	int ret;
+	unsigned long addr, size = 0, offset = 0;
+	struct insn insn;
+	kprobe_opcode_t buf[MAX_INSN_SIZE];
+
+	/* Lookup symbol including addr */
+	if (!kallsyms_lookup(paddr, &size, &offset, NULL, __dummy_buf))
+		return 0;
+
+	/* Decode instructions */
+	addr = paddr - offset;
+	while (addr < paddr - offset + size) { /* Decode until function end */
+		insn_init_kernel(&insn, (void *)addr);
+		insn_get_opcode(&insn);
+		if (OPCODE1(&insn) == BREAKPOINT_INSTRUCTION) {
+			ret = recover_probed_instruction(buf, addr);
+			if (ret)
+				return 0;
+			insn_init_kernel(&insn, buf);
+		}
+		insn_get_length(&insn);
+		/* Recover address */
+		insn.kaddr = (void *)addr;
+		insn.next_byte = (void *)(addr + insn.length);
+		/* Check any instructions don't jump into target */
+		if (insn_is_indirect_jump(&insn) ||
+		    insn_jump_into_range(&insn, addr + INT3_SIZE,
+					 RELATIVE_ADDR_SIZE))
+			return 0;
+		addr += insn.length;
+	}
+
+	return 1;
+}
+
 int arch_optimized_kprobe_address(struct optimized_kprobe *op,
 				  unsigned long addr)
 {
@@ -1269,6 +1341,9 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
 	u8 *buf;
 	int ret, i;

+	if (!can_optimize((unsigned long)op->kp.addr))
+		return -EINVAL;
+
 	op->optinsn.insn = get_optinsn_slot();
 	if (!op->optinsn.insn)
 		return -ENOMEM;
-- 
Masami Hiramatsu

Software Engineer
Hitachi Computer Products (America) Inc.
Software Solutions Division

e-mail: mhiramat@redhat.com


                 reply	other threads:[~2009-04-06 21:43 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=49DA7791.7030603@redhat.com \
    --to=mhiramat@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=ananth@in.ibm.com \
    --cc=andi@firstfloor.org \
    --cc=avi@redhat.com \
    --cc=fche@redhat.com \
    --cc=fweisbec@gmail.com \
    --cc=hpa@zytor.com \
    --cc=jkenisto@us.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=rostedt@goodmis.org \
    --cc=satoshi.oshima.fk@hitachi.com \
    --cc=systemtap@sources.redhat.com \
    --cc=vegard.nossum@gmail.com \
    /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.