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

1 files changed, 8 insertions, 10 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index ca92e01d0bd1..48604625ab31 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -96,7 +96,7 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
 {
 	return 0;
 }
-static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { }
+static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp) { }
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
 	return 0;
@@ -127,7 +127,7 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
 static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {}
-static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
+static inline void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
 
@@ -179,7 +179,7 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
  * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the
  * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER.
  */
-static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
+static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp)
 {
 	unsigned long mmcra = regs->dsisr;
 	bool sdar_valid;
@@ -204,8 +204,7 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
 		*addrp = mfspr(SPRN_SDAR);
 
-	if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) &&
-		is_kernel_addr(mfspr(SPRN_SDAR)))
+	if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0)
 		*addrp = 0;
 }
 
@@ -444,7 +443,7 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 }
 
 /* Processing BHRB entries */
-static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
+static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw)
 {
 	u64 val;
 	u64 addr;
@@ -472,8 +471,7 @@ static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
 			 * exporting it to userspace (avoid exposure of regions
 			 * where we could have speculative execution)
 			 */
-			if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) &&
-				is_kernel_addr(addr))
+			if (is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
 				continue;
 
 			/* Branches are read most recent first (ie. mfbhrb 0 is
@@ -2087,12 +2085,12 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		if (event->attr.sample_type &
 		    (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
-			perf_get_data_addr(regs, &data.addr);
+			perf_get_data_addr(event, regs, &data.addr);
 
 		if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) {
 			struct cpu_hw_events *cpuhw;
 			cpuhw = this_cpu_ptr(&cpu_hw_events);
-			power_pmu_bhrb_read(cpuhw);
+			power_pmu_bhrb_read(event, cpuhw);
 			data.br_stack = &cpuhw->bhrb_stack;
 		}