Message ID | 1493742574-25955-1-git-send-email-ganapatrao.kulkarni@cavium.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Hi Will, if this patch looks good, can it go in 4.12-rc2 as bug fix? or can it be queued for 4.13? On Tue, May 2, 2017 at 9:59 PM, Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com> wrote: > commit d98ecdaca296 ("arm64: perf: Count EL2 events if the kernel is > running in HYP") returns -EINVAL when perf system call perf_event_open is > called with exclude_hv != exclude_kernel. This change breaks applications > on VHE enabled ARMv8.1 platforms. The issue was observed with HHVM > application, which calls perf_event_open with exclude_hv = 1 and > exclude_kernel = 0. > > There is no separate hypervisor privilege level when VHE is enabled, the > host kernel runs at EL2. So when VHE is enabled, we should ignore > exclude_hv from the application. This behaviour is consistent with PowerPC > where the exclude_hv is ignored when the hypervisor is not present and with > x86 where this flag is ignored. > > Signed-off-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com> > --- > > Changelog: > > V2/V3: > - Changes as per Will Deacon's suggestions. > > V1: Initial patch > > arch/arm64/kernel/perf_event.c | 16 +++++++++------- > 1 file changed, 9 insertions(+), 7 deletions(-) > > diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c > index 57ae9d9..f6748c0 100644 > --- a/arch/arm64/kernel/perf_event.c > +++ b/arch/arm64/kernel/perf_event.c > @@ -871,15 +871,17 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, > > if (attr->exclude_idle) > return -EPERM; > - if (is_kernel_in_hyp_mode() && > - attr->exclude_kernel != attr->exclude_hv) > - return -EINVAL; > + if (is_kernel_in_hyp_mode()) { > + if (!attr->exclude_kernel) > + config_base |= ARMV8_PMU_INCLUDE_EL2; > + } else { > + if (attr->exclude_kernel) > + config_base |= ARMV8_PMU_EXCLUDE_EL1; > + if (!attr->exclude_hv) > + config_base |= ARMV8_PMU_INCLUDE_EL2; > + } > if (attr->exclude_user) > config_base |= ARMV8_PMU_EXCLUDE_EL0; > - if (!is_kernel_in_hyp_mode() && attr->exclude_kernel) > - config_base |= ARMV8_PMU_EXCLUDE_EL1; > - if (!attr->exclude_hv) > - config_base |= ARMV8_PMU_INCLUDE_EL2; > > /* > * Install the filter into config_base as this is used to > -- > 1.8.1.4 > thanks Ganapat
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 57ae9d9..f6748c0 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -871,15 +871,17 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, if (attr->exclude_idle) return -EPERM; - if (is_kernel_in_hyp_mode() && - attr->exclude_kernel != attr->exclude_hv) - return -EINVAL; + if (is_kernel_in_hyp_mode()) { + if (!attr->exclude_kernel) + config_base |= ARMV8_PMU_INCLUDE_EL2; + } else { + if (attr->exclude_kernel) + config_base |= ARMV8_PMU_EXCLUDE_EL1; + if (!attr->exclude_hv) + config_base |= ARMV8_PMU_INCLUDE_EL2; + } if (attr->exclude_user) config_base |= ARMV8_PMU_EXCLUDE_EL0; - if (!is_kernel_in_hyp_mode() && attr->exclude_kernel) - config_base |= ARMV8_PMU_EXCLUDE_EL1; - if (!attr->exclude_hv) - config_base |= ARMV8_PMU_INCLUDE_EL2; /* * Install the filter into config_base as this is used to
commit d98ecdaca296 ("arm64: perf: Count EL2 events if the kernel is running in HYP") returns -EINVAL when perf system call perf_event_open is called with exclude_hv != exclude_kernel. This change breaks applications on VHE enabled ARMv8.1 platforms. The issue was observed with HHVM application, which calls perf_event_open with exclude_hv = 1 and exclude_kernel = 0. There is no separate hypervisor privilege level when VHE is enabled, the host kernel runs at EL2. So when VHE is enabled, we should ignore exclude_hv from the application. This behaviour is consistent with PowerPC where the exclude_hv is ignored when the hypervisor is not present and with x86 where this flag is ignored. Signed-off-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com> --- Changelog: V2/V3: - Changes as per Will Deacon's suggestions. V1: Initial patch arch/arm64/kernel/perf_event.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)