From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Kamal Mostafa To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: Jed Davis , Will Deacon , Russell King , Luis Henriques Subject: [PATCH 030/145] ARM: 7765/1: perf: Record the user-mode PC in the call chain. Date: Wed, 17 Jul 2013 15:46:02 -0700 Message-Id: <1374101277-7915-31-git-send-email-kamal@canonical.com> In-Reply-To: <1374101277-7915-1-git-send-email-kamal@canonical.com> References: <1374101277-7915-1-git-send-email-kamal@canonical.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: 3.8.13.5 -stable review patch. If anyone has any objections, please let me know. ------------------ From: Jed Davis commit c5f927a6f62196226915f12194c9d0df4e2210d7 upstream. With this change, we no longer lose the innermost entry in the user-mode part of the call chain. See also the x86 port, which includes the ip. It's possible to partially work around this problem by post-processing the data to use the PERF_SAMPLE_IP value, but this works only if the CPU wasn't in the kernel when the sample was taken. Signed-off-by: Jed Davis Signed-off-by: Will Deacon Signed-off-by: Russell King Signed-off-by: Luis Henriques --- arch/arm/kernel/perf_event.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 23fa6a2..5da31bb 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -579,6 +579,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) return; } + perf_callchain_store(entry, regs->ARM_pc); tail = (struct frame_tail __user *)regs->ARM_fp - 1; while ((entry->nr < PERF_MAX_STACK_DEPTH) && -- 1.8.1.2