perf/x86: Add /sys/devices/cpu/rdpmc=2 to allow rdpmc for all tasks

While perfmon2 is a sufficiently evil library (it pokes MSRs
directly) that breaking it is fair game, it's still useful, so we
might as well try to support it.  This allows users to write 2 to
/sys/devices/cpu/rdpmc to disable all rdpmc protection so that hack
like perfmon2 can continue to work.

At some point, if perf_event becomes fast enough to replace
perfmon2, then this can go.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Vince Weaver <vince@deater.net>
Cc: "hillf.zj" <hillf.zj@alibaba-inc.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/caac3c1c707dcca48ecbc35f4def21495856f479.1414190806.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 24 insertions, 2 deletions

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 89c1fece224e..883f6b933fa4 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -19,9 +19,12 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
 #endif  /* !CONFIG_PARAVIRT */
 
 #ifdef CONFIG_PERF_EVENTS
+extern struct static_key rdpmc_always_available;
+
 static inline void load_mm_cr4(struct mm_struct *mm)
 {
-        if (atomic_read(&mm->context.perf_rdpmc_allowed))
+        if (static_key_true(&rdpmc_always_available) ||
+            atomic_read(&mm->context.perf_rdpmc_allowed))
                 cr4_set_bits(X86_CR4_PCE);
         else
                 cr4_clear_bits(X86_CR4_PCE);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index bec5cff7dc80..b71a7f86d68a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -45,6 +45,8 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
         .enabled = 1,
 };
 
+struct static_key rdpmc_always_available = STATIC_KEY_INIT_FALSE;
+
 u64 __read_mostly hw_cache_event_ids
                                 [PERF_COUNT_HW_CACHE_MAX]
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
@@ -1870,10 +1872,27 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
         if (ret)
                 return ret;
 
+        if (val > 2)
+                return -EINVAL;
+
         if (x86_pmu.attr_rdpmc_broken)
                 return -ENOTSUPP;
 
-        x86_pmu.attr_rdpmc = !!val;
+        if ((val == 2) != (x86_pmu.attr_rdpmc == 2)) {
+                /*
+                 * Changing into or out of always available, aka
+                 * perf-event-bypassing mode.  This path is extremely slow,
+                 * but only root can trigger it, so it's okay.
+                 */
+                if (val == 2)
+                        static_key_slow_inc(&rdpmc_always_available);
+                else
+                        static_key_slow_dec(&rdpmc_always_available);
+                on_each_cpu(refresh_pce, NULL, 1);
+        }
+
+        x86_pmu.attr_rdpmc = val;
+
         return count;
 }