[PATCH] perf/x86/intel: Drop kernel samples even though :u is specified

[Jin Yao]

When doing sampling without PEBS

perf record -e cycles:u ...

On workloads that do a lot of kernel entry/exits we see kernel
samples, even though :u is specified. This is due to skid existing.

This is a security issue because it can leak kernel addresses even
though kernel sampling support is disabled.

The patch drops the kernel samples if exclude_kernel is specified.

For example, test on Haswell desktop.

perf record -e cycles:u <mgen>
perf report --stdio

Before patch applied:

    99.77%  mgen     mgen              [.] buf_read
     0.20%  mgen     mgen              [.] rand_buf_init
     0.01%  mgen     [kernel.vmlinux]  [k] apic_timer_interrupt
     0.00%  mgen     mgen              [.] last_free_elem
     0.00%  mgen     libc-2.23.so      [.] __random_r
     0.00%  mgen     libc-2.23.so      [.] _int_malloc
     0.00%  mgen     mgen              [.] rand_array_init
     0.00%  mgen     [kernel.vmlinux]  [k] page_fault
     0.00%  mgen     libc-2.23.so      [.] __random
     0.00%  mgen     libc-2.23.so      [.] __strcasestr
     0.00%  mgen     ld-2.23.so        [.] strcmp
     0.00%  mgen     ld-2.23.so        [.] _dl_start
     0.00%  mgen     libc-2.23.so      [.] sched_setaffinity@@GLIBC_2.3.4
     0.00%  mgen     ld-2.23.so        [.] _start

We can see kernel symbols apic_timer_interrupt and page_fault.

After patch applied:

    99.79%  mgen     mgen           [.] buf_read
     0.19%  mgen     mgen           [.] rand_buf_init
     0.00%  mgen     libc-2.23.so   [.] __random_r
     0.00%  mgen     mgen           [.] rand_array_init
     0.00%  mgen     mgen           [.] last_free_elem
     0.00%  mgen     libc-2.23.so   [.] vfprintf
     0.00%  mgen     libc-2.23.so   [.] rand
     0.00%  mgen     libc-2.23.so   [.] __random
     0.00%  mgen     libc-2.23.so   [.] _int_malloc
     0.00%  mgen     libc-2.23.so   [.] _IO_doallocbuf
     0.00%  mgen     ld-2.23.so     [.] do_lookup_x
     0.00%  mgen     ld-2.23.so     [.] open_verify.constprop.7
     0.00%  mgen     ld-2.23.so     [.] _dl_important_hwcaps
     0.00%  mgen     libc-2.23.so   [.] sched_setaffinity@@GLIBC_2.3.4
     0.00%  mgen     ld-2.23.so     [.] _start

There are only userspace symbols.

Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
 arch/x86/events/core.c       | 24 ++++++++++++++++++++++++
 arch/x86/events/intel/core.c |  6 ++++++
 arch/x86/events/perf_event.h |  2 ++
 3 files changed, 32 insertions(+)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 580b60f..e6745e1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1463,6 +1463,12 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 
+		/*
+		 * For security, drop the skid kernel samples.
+		 */
+		if (skid_kernel_samples(event, regs))
+			continue;
+
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
@@ -1679,6 +1685,24 @@ ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
 			pmu_attr->event_str_noht);
 }
 
+bool skid_kernel_samples(struct perf_event *event, struct pt_regs *regs)
+{
+	u64 ip;
+
+	/*
+	 * Without PEBS, we may get kernel samples even though
+	 * exclude_kernel is specified due to skid in sampling.
+	 */
+	if ((event->attr.exclude_kernel) &&
+	    (event->attr.sample_type & PERF_SAMPLE_IP)) {
+		ip = perf_instruction_pointer(regs);
+		if (kernel_ip(ip))
+			return true;
+	}
+
+	return false;
+}
+
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
 EVENT_ATTR(cache-references,		CACHE_REFERENCES	);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a6d91d4..8e9c9e8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2193,6 +2193,12 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 		if (has_branch_stack(event))
 			data.br_stack = &cpuc->lbr_stack;
 
+		/*
+		 * For security, drop the skid kernel samples.
+		 */
+		if (skid_kernel_samples(event, regs))
+			continue;
+
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
 	}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index be3d362..73fe023 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -818,6 +818,8 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page);
 
+bool skid_kernel_samples(struct perf_event *event, struct pt_regs *regs);
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
-- 
2.7.4