perf: Protect perf_guest_cbs with RCU

Protect perf_guest_cbs with RCU to fix multiple possible errors.  Luckily,
all paths that read perf_guest_cbs already require RCU protection, e.g. to
protect the callback chains, so only the direct perf_guest_cbs touchpoints
need to be modified.

Bug #1 is a simple lack of WRITE_ONCE/READ_ONCE behavior to ensure
perf_guest_cbs isn't reloaded between a !NULL check and a dereference.
Fixed via the READ_ONCE() in rcu_dereference().

Bug #2 is that on weakly-ordered architectures, updates to the callbacks
themselves are not guaranteed to be visible before the pointer is made
visible to readers.  Fixed by the smp_store_release() in
rcu_assign_pointer() when the new pointer is non-NULL.

Bug #3 is that, because the callbacks are global, it's possible for
readers to run in parallel with an unregisters, and thus a module
implementing the callbacks can be unloaded while readers are in flight,
resulting in a use-after-free.  Fixed by a synchronize_rcu() call when
unregistering callbacks.

Bug #1 escaped notice because it's extremely unlikely a compiler will
reload perf_guest_cbs in this sequence.  perf_guest_cbs does get reloaded
for future derefs, e.g. for ->is_user_mode(), but the ->is_in_guest()
guard all but guarantees the consumer will win the race, e.g. to nullify
perf_guest_cbs, KVM has to completely exit the guest and teardown down
all VMs before KVM start its module unload / unregister sequence.  This
also makes it all but impossible to encounter bug #3.

Bug #2 has not been a problem because all architectures that register
callbacks are strongly ordered and/or have a static set of callbacks.

But with help, unloading kvm_intel can trigger bug #1 e.g. wrapping
perf_guest_cbs with READ_ONCE in perf_misc_flags() while spamming
kvm_intel module load/unload leads to:

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] PREEMPT SMP
  CPU: 6 PID: 1825 Comm: stress Not tainted 5.14.0-rc2+ #459
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
  RIP: 0010:perf_misc_flags+0x1c/0x70
  Call Trace:
   perf_prepare_sample+0x53/0x6b0
   perf_event_output_forward+0x67/0x160
   __perf_event_overflow+0x52/0xf0
   handle_pmi_common+0x207/0x300
   intel_pmu_handle_irq+0xcf/0x410
   perf_event_nmi_handler+0x28/0x50
   nmi_handle+0xc7/0x260
   default_do_nmi+0x6b/0x170
   exc_nmi+0x103/0x130
   asm_exc_nmi+0x76/0xbf

Fixes: 39447b386c84 ("perf: Enhance perf to allow for guest statistic collection from host")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20211111020738.2512932-2-seanjc@google.com

2 files changed, 17 insertions, 9 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 38b2c779146f..32cec290d3ad 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2768,10 +2768,11 @@ static bool perf_hw_regs(struct pt_regs *regs)
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	struct unwind_state state;
 	unsigned long addr;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+	if (guest_cbs && guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
 	}
@@ -2871,10 +2872,11 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	struct stack_frame frame;
 	const struct stack_frame __user *fp;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+	if (guest_cbs && guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
 	}
@@ -2951,18 +2953,21 @@ static unsigned long code_segment_base(struct pt_regs *regs)
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+
+	if (guest_cbs && guest_cbs->is_in_guest())
+		return guest_cbs->get_guest_ip();
 
 	return regs->ip + code_segment_base(regs);
 }
 
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	int misc = 0;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
+	if (guest_cbs && guest_cbs->is_in_guest()) {
+		if (guest_cbs->is_user_mode())
 			misc |= PERF_RECORD_MISC_GUEST_USER;
 		else
 			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 42cf01ecdd13..2258e02ca350 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2837,6 +2837,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 {
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_guest_info_callbacks *guest_cbs;
 	int bit;
 	int handled = 0;
 	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
@@ -2903,9 +2904,11 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 */
 	if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) {
 		handled++;
-		if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() &&
-			perf_guest_cbs->handle_intel_pt_intr))
-			perf_guest_cbs->handle_intel_pt_intr();
+
+		guest_cbs = perf_get_guest_cbs();
+		if (unlikely(guest_cbs && guest_cbs->is_in_guest() &&
+			     guest_cbs->handle_intel_pt_intr))
+			guest_cbs->handle_intel_pt_intr();
 		else
 			intel_pt_interrupt();
 	}