perf_event: Add support for LSM and SELinux checks

In current mainline, the degree of access to perf_event_open(2) system
call depends on the perf_event_paranoid sysctl.  This has a number of
limitations:

1. The sysctl is only a single value. Many types of accesses are controlled
   based on the single value thus making the control very limited and
   coarse grained.
2. The sysctl is global, so if the sysctl is changed, then that means
   all processes get access to perf_event_open(2) opening the door to
   security issues.

This patch adds LSM and SELinux access checking which will be used in
Android to access perf_event_open(2) for the purposes of attaching BPF
programs to tracepoints, perf profiling and other operations from
userspace. These operations are intended for production systems.

5 new LSM hooks are added:
1. perf_event_open: This controls access during the perf_event_open(2)
   syscall itself. The hook is called from all the places that the
   perf_event_paranoid sysctl is checked to keep it consistent with the
   systctl. The hook gets passed a 'type' argument which controls CPU,
   kernel and tracepoint accesses (in this context, CPU, kernel and
   tracepoint have the same semantics as the perf_event_paranoid sysctl).
   Additionally, I added an 'open' type which is similar to
   perf_event_paranoid sysctl == 3 patch carried in Android and several other
   distros but was rejected in mainline [1] in 2016.

2. perf_event_alloc: This allocates a new security object for the event
   which stores the current SID within the event. It will be useful when
   the perf event's FD is passed through IPC to another process which may
   try to read the FD. Appropriate security checks will limit access.

3. perf_event_free: Called when the event is closed.

4. perf_event_read: Called from the read(2) and mmap(2) syscalls for the event.

5. perf_event_write: Called from the ioctl(2) syscalls for the event.

[1] https://lwn.net/Articles/696240/

Since Peter had suggest LSM hooks in 2016 [1], I am adding his
Suggested-by tag below.

To use this patch, we set the perf_event_paranoid sysctl to -1 and then
apply selinux checking as appropriate (default deny everything, and then
add policy rules to give access to domains that need it). In the future
we can remove the perf_event_paranoid sysctl altogether.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Co-developed-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: James Morris <jmorris@namei.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: rostedt@goodmis.org
Cc: Yonghong Song <yhs@fb.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: jeffv@google.com
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: primiano@google.com
Cc: Song Liu <songliubraving@fb.com>
Cc: rsavitski@google.com
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Matthew Garrett <matthewgarrett@google.com>
Link: https://lkml.kernel.org/r/20191014170308.70668-1-joel@joelfernandes.org

2 files changed, 56 insertions, 16 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9ec0b0bfddbd..f9a5d4356562 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4229,8 +4229,9 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 
 	if (!task) {
 		/* Must be root to operate on a CPU event: */
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return ERR_PTR(-EACCES);
+		err = perf_allow_cpu(&event->attr);
+		if (err)
+			return ERR_PTR(err);
 
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
@@ -4539,6 +4540,8 @@ static void _free_event(struct perf_event *event)
 
 	unaccount_event(event);
 
+	security_perf_event_free(event);
+
 	if (event->rb) {
 		/*
 		 * Can happen when we close an event with re-directed output.
@@ -4992,6 +4995,10 @@ perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	struct perf_event_context *ctx;
 	int ret;
 
+	ret = security_perf_event_read(event);
+	if (ret)
+		return ret;
+
 	ctx = perf_event_ctx_lock(event);
 	ret = __perf_read(event, buf, count);
 	perf_event_ctx_unlock(event, ctx);
@@ -5256,6 +5263,11 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct perf_event_context *ctx;
 	long ret;
 
+	/* Treat ioctl like writes as it is likely a mutating operation. */
+	ret = security_perf_event_write(event);
+	if (ret)
+		return ret;
+
 	ctx = perf_event_ctx_lock(event);
 	ret = _perf_ioctl(event, cmd, arg);
 	perf_event_ctx_unlock(event, ctx);
@@ -5719,6 +5731,10 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
+	ret = security_perf_event_read(event);
+	if (ret)
+		return ret;
+
 	vma_size = vma->vm_end - vma->vm_start;
 
 	if (vma->vm_pgoff == 0) {
@@ -5844,7 +5860,7 @@ accounting:
 	lock_limit >>= PAGE_SHIFT;
 	locked = atomic64_read(&vma->vm_mm->pinned_vm) + extra;
 
-	if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() &&
+	if ((locked > lock_limit) && perf_is_paranoid() &&
 		!capable(CAP_IPC_LOCK)) {
 		ret = -EPERM;
 		goto unlock;
@@ -10578,11 +10594,20 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		}
 	}
 
+	err = security_perf_event_alloc(event);
+	if (err)
+		goto err_callchain_buffer;
+
 	/* symmetric to unaccount_event() in _free_event() */
 	account_event(event);
 
 	return event;
 
+err_callchain_buffer:
+	if (!event->parent) {
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			put_callchain_buffers();
+	}
 err_addr_filters:
 	kfree(event->addr_filter_ranges);
 
@@ -10671,9 +10696,11 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			attr->branch_sample_type = mask;
 		}
 		/* privileged levels capture (kernel, hv): check permissions */
-		if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
-		    && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+		if (mask & PERF_SAMPLE_BRANCH_PERM_PLM) {
+			ret = perf_allow_kernel(attr);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
@@ -10886,13 +10913,19 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
+	/* Do we allow access to perf_event_open(2) ? */
+	err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
+	if (err)
+		return err;
+
 	err = perf_copy_attr(attr_uptr, &attr);
 	if (err)
 		return err;
 
 	if (!attr.exclude_kernel) {
-		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+		err = perf_allow_kernel(&attr);
+		if (err)
+			return err;
 	}
 
 	if (attr.namespaces) {
@@ -10909,9 +10942,11 @@ SYSCALL_DEFINE5(perf_event_open,
 	}
 
 	/* Only privileged users can get physical addresses */
-	if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR) &&
-	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR)) {
+		err = perf_allow_kernel(&attr);
+		if (err)
+			return err;
+	}
 
 	err = security_locked_down(LOCKDOWN_PERF);
 	if (err && (attr.sample_type & PERF_SAMPLE_REGS_INTR))
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 0892e38ed6fb..0917fee6ee7c 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -8,6 +8,7 @@
 
 #include <linux/module.h>
 #include <linux/kprobes.h>
+#include <linux/security.h>
 #include "trace.h"
 #include "trace_probe.h"
 
@@ -26,8 +27,10 @@ static int	total_ref_count;
 static int perf_trace_event_perm(struct trace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
+	int ret;
+
 	if (tp_event->perf_perm) {
-		int ret = tp_event->perf_perm(tp_event, p_event);
+		ret = tp_event->perf_perm(tp_event, p_event);
 		if (ret)
 			return ret;
 	}
@@ -46,8 +49,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event,
 
 	/* The ftrace function trace is allowed only for root. */
 	if (ftrace_event_is_function(tp_event)) {
-		if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
-			return -EPERM;
+		ret = perf_allow_tracepoint(&p_event->attr);
+		if (ret)
+			return ret;
 
 		if (!is_sampling_event(p_event))
 			return 0;
@@ -82,8 +86,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event,
 	 * ...otherwise raw tracepoint data can be a severe data leak,
 	 * only allow root to have these.
 	 */
-	if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	ret = perf_allow_tracepoint(&p_event->attr);
+	if (ret)
+		return ret;
 
 	return 0;
 }