@@ -62,9 +62,10 @@ user_backtrace(struct frame_tail __user *tail,
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 frame_tail __user *tail;
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ if (guest_cbs && guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
@@ -98,9 +99,10 @@ callchain_trace(struct stackframe *fr,
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 stackframe fr;
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ if (guest_cbs && guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
@@ -111,18 +113,21 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
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 instruction_pointer(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;
@@ -102,7 +102,9 @@ compat_user_backtrace(struct compat_frame_tail __user *tail,
void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
struct pt_regs *regs)
{
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+
+ if (guest_cbs && guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
@@ -147,9 +149,10 @@ static bool callchain_trace(void *data, unsigned long pc)
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 stackframe frame;
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ if (guest_cbs && guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
@@ -160,18 +163,21 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
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 instruction_pointer(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;
@@ -86,10 +86,11 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
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();
unsigned long fp = 0;
/* C-SKY does not support virtualization. */
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+ if (guest_cbs && guest_cbs->is_in_guest())
return;
fp = regs->regs[4];
@@ -110,10 +111,11 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
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 stackframe fr;
/* C-SKY does not support virtualization. */
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ if (guest_cbs && guest_cbs->is_in_guest()) {
pr_warn("C-SKY does not support perf in guest mode!");
return;
}
@@ -1363,6 +1363,7 @@ 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();
unsigned long fp = 0;
unsigned long gp = 0;
unsigned long lp = 0;
@@ -1371,7 +1372,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry,
leaf_fp = 0;
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ if (guest_cbs && guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
@@ -1479,9 +1480,10 @@ 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 stackframe fr;
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ if (guest_cbs && guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
@@ -1493,20 +1495,23 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
unsigned long perf_instruction_pointer(struct pt_regs *regs)
{
+ struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+
/* However, NDS32 does not support virtualization */
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
- return perf_guest_cbs->get_guest_ip();
+ if (guest_cbs && guest_cbs->is_in_guest())
+ return guest_cbs->get_guest_ip();
return instruction_pointer(regs);
}
unsigned long perf_misc_flags(struct pt_regs *regs)
{
+ struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
int misc = 0;
/* However, NDS32 does not support virtualization */
- 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;
@@ -56,10 +56,11 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry,
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();
unsigned long fp = 0;
/* RISC-V does not support perf in guest mode. */
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
+ if (guest_cbs && guest_cbs->is_in_guest())
return;
fp = regs->s0;
@@ -78,8 +79,10 @@ static bool fill_callchain(void *entry, unsigned long pc)
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();
+
/* RISC-V does not support perf in guest mode. */
- if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+ if (guest_cbs && guest_cbs->is_in_guest()) {
pr_warn("RISC-V does not support perf in guest mode!");
return;
}
@@ -2761,10 +2761,11 @@ 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;
}
@@ -2864,10 +2865,11 @@ 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;
}
@@ -2944,18 +2946,21 @@ 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;
@@ -2786,6 +2786,7 @@ 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);
@@ -2852,9 +2853,11 @@ 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();
}
@@ -1237,6 +1237,14 @@ extern void perf_event_bpf_event(struct bpf_prog *prog,
u16 flags);
extern struct perf_guest_info_callbacks *perf_guest_cbs;
+static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void)
+{
+ /* Reg/unreg perf_guest_cbs waits for readers via synchronize_rcu(). */
+ lockdep_assert_preemption_disabled();
+
+ /* Prevent reloading between a !NULL check and dereferences. */
+ return READ_ONCE(perf_guest_cbs);
+}
extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
@@ -6491,14 +6491,19 @@ struct perf_guest_info_callbacks *perf_guest_cbs;
int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
{
- perf_guest_cbs = cbs;
+ if (WARN_ON_ONCE(perf_guest_cbs))
+ return -EBUSY;
+
+ WRITE_ONCE(perf_guest_cbs, cbs);
+ synchronize_rcu();
return 0;
}
EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
{
- perf_guest_cbs = NULL;
+ WRITE_ONCE(perf_guest_cbs, NULL);
+ synchronize_rcu();
return 0;
}
EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
Protect perf_guest_cbs with READ_ONCE/WRITE_ONCE to ensure it's not reloaded between a !NULL check and a dereference, and wait for all readers via syncrhonize_rcu() to prevent use-after-free, e.g. if the callbacks are being unregistered during module unload. Because the callbacks are global, it's possible for readers to run in parallel with an unregister operation. The bug has escaped notice because all dereferences of perf_guest_cbs follow the same "perf_guest_cbs && perf_guest_cbs->is_in_guest()" pattern, and it's extremely unlikely a compiler will reload perf_guest_cbs in this sequence. Compilers do reload perf_guest_cbs for future derefs, e.g. for ->is_user_mode(), but the ->is_in_guest() guard all but guarantees the PMI handler 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. But with help, unloading kvm_intel can trigger a NULL pointer derference, 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") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson <seanjc@google.com> --- arch/arm/kernel/perf_callchain.c | 17 +++++++++++------ arch/arm64/kernel/perf_callchain.c | 18 ++++++++++++------ arch/csky/kernel/perf_callchain.c | 6 ++++-- arch/nds32/kernel/perf_event_cpu.c | 17 +++++++++++------ arch/riscv/kernel/perf_callchain.c | 7 +++++-- arch/x86/events/core.c | 17 +++++++++++------ arch/x86/events/intel/core.c | 9 ++++++--- include/linux/perf_event.h | 8 ++++++++ kernel/events/core.c | 9 +++++++-- 9 files changed, 75 insertions(+), 33 deletions(-)