diff mbox series

[v4,5/5] perf: Correct perf sampling with guest VMs

Message ID 20240919190750.4163977-6-coltonlewis@google.com (mailing list archive)
State New, archived
Headers show
Series Correct perf sampling with Guest VMs | expand

Commit Message

Colton Lewis Sept. 19, 2024, 7:07 p.m. UTC
Previously any PMU overflow interrupt that fired while a VCPU was
loaded was recorded as a guest event whether it truly was or not. This
resulted in nonsense perf recordings that did not honor
perf_event_attr.exclude_guest and recorded guest IPs where it should
have recorded host IPs.

Rework the sampling logic to only record guest samples for events with
exclude_guest = 0. This way any host-only events with exclude_guest
set will never see unexpected guest samples. The behaviour of events
with exclude_guest = 0 is unchanged.

Note that events configured to sample both host and guest may still
misattribute a PMI that arrived in the host as a guest event depending
on KVM arch and vendor behavior.

Signed-off-by: Colton Lewis <coltonlewis@google.com>
---
 arch/arm64/include/asm/perf_event.h |  4 ----
 arch/arm64/kernel/perf_callchain.c  | 28 ----------------------------
 arch/x86/events/core.c              | 16 ++++------------
 include/linux/perf_event.h          | 21 +++++++++++++++++++--
 kernel/events/core.c                | 21 +++++++++++++++++----
 5 files changed, 40 insertions(+), 50 deletions(-)

Comments

kernel test robot Sept. 20, 2024, 6:52 a.m. UTC | #1
Hi Colton,

kernel test robot noticed the following build errors:

[auto build test ERROR on da3ea35007d0af457a0afc87e84fddaebc4e0b63]

url:    https://github.com/intel-lab-lkp/linux/commits/Colton-Lewis/arm-perf-Drop-unused-functions/20240920-031100
base:   da3ea35007d0af457a0afc87e84fddaebc4e0b63
patch link:    https://lore.kernel.org/r/20240919190750.4163977-6-coltonlewis%40google.com
patch subject: [PATCH v4 5/5] perf: Correct perf sampling with guest VMs
config: s390-allmodconfig (https://download.01.org/0day-ci/archive/20240920/202409201447.iQ8kNjxo-lkp@intel.com/config)
compiler: clang version 20.0.0git (https://github.com/llvm/llvm-project 8663a75fa2f31299ab8d1d90288d9df92aadee88)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240920/202409201447.iQ8kNjxo-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409201447.iQ8kNjxo-lkp@intel.com/

All errors (new ones prefixed by >>):

   In file included from kernel/events/core.c:12:
   In file included from include/linux/mm.h:2232:
   include/linux/vmstat.h:503:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     503 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     504 |                            item];
         |                            ~~~~
   include/linux/vmstat.h:510:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     510 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     511 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
   include/linux/vmstat.h:517:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
     517 |         return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
         |                               ~~~~~~~~~~~ ^ ~~~
   include/linux/vmstat.h:523:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     523 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     524 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
   In file included from kernel/events/core.c:20:
   In file included from include/linux/tick.h:8:
   In file included from include/linux/clockchips.h:14:
   In file included from include/linux/clocksource.h:22:
   In file included from arch/s390/include/asm/io.h:93:
   include/asm-generic/io.h:548:31: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     548 |         val = __raw_readb(PCI_IOBASE + addr);
         |                           ~~~~~~~~~~ ^
   include/asm-generic/io.h:561:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     561 |         val = __le16_to_cpu((__le16 __force)__raw_readw(PCI_IOBASE + addr));
         |                                                         ~~~~~~~~~~ ^
   include/uapi/linux/byteorder/big_endian.h:37:59: note: expanded from macro '__le16_to_cpu'
      37 | #define __le16_to_cpu(x) __swab16((__force __u16)(__le16)(x))
         |                                                           ^
   include/uapi/linux/swab.h:102:54: note: expanded from macro '__swab16'
     102 | #define __swab16(x) (__u16)__builtin_bswap16((__u16)(x))
         |                                                      ^
   In file included from kernel/events/core.c:20:
   In file included from include/linux/tick.h:8:
   In file included from include/linux/clockchips.h:14:
   In file included from include/linux/clocksource.h:22:
   In file included from arch/s390/include/asm/io.h:93:
   include/asm-generic/io.h:574:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     574 |         val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr));
         |                                                         ~~~~~~~~~~ ^
   include/uapi/linux/byteorder/big_endian.h:35:59: note: expanded from macro '__le32_to_cpu'
      35 | #define __le32_to_cpu(x) __swab32((__force __u32)(__le32)(x))
         |                                                           ^
   include/uapi/linux/swab.h:115:54: note: expanded from macro '__swab32'
     115 | #define __swab32(x) (__u32)__builtin_bswap32((__u32)(x))
         |                                                      ^
   In file included from kernel/events/core.c:20:
   In file included from include/linux/tick.h:8:
   In file included from include/linux/clockchips.h:14:
   In file included from include/linux/clocksource.h:22:
   In file included from arch/s390/include/asm/io.h:93:
   include/asm-generic/io.h:585:33: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     585 |         __raw_writeb(value, PCI_IOBASE + addr);
         |                             ~~~~~~~~~~ ^
   include/asm-generic/io.h:595:59: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     595 |         __raw_writew((u16 __force)cpu_to_le16(value), PCI_IOBASE + addr);
         |                                                       ~~~~~~~~~~ ^
   include/asm-generic/io.h:605:59: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     605 |         __raw_writel((u32 __force)cpu_to_le32(value), PCI_IOBASE + addr);
         |                                                       ~~~~~~~~~~ ^
   include/asm-generic/io.h:693:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     693 |         readsb(PCI_IOBASE + addr, buffer, count);
         |                ~~~~~~~~~~ ^
   include/asm-generic/io.h:701:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     701 |         readsw(PCI_IOBASE + addr, buffer, count);
         |                ~~~~~~~~~~ ^
   include/asm-generic/io.h:709:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     709 |         readsl(PCI_IOBASE + addr, buffer, count);
         |                ~~~~~~~~~~ ^
   include/asm-generic/io.h:718:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     718 |         writesb(PCI_IOBASE + addr, buffer, count);
         |                 ~~~~~~~~~~ ^
   include/asm-generic/io.h:727:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     727 |         writesw(PCI_IOBASE + addr, buffer, count);
         |                 ~~~~~~~~~~ ^
   include/asm-generic/io.h:736:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic]
     736 |         writesl(PCI_IOBASE + addr, buffer, count);
         |                 ~~~~~~~~~~ ^
>> kernel/events/core.c:6935:9: error: too few arguments to function call, expected 2, have 1
    6935 |         return perf_arch_misc_flags(regs);
         |                ^~~~~~~~~~~~~~~~~~~~~~~~~~
   arch/s390/include/asm/perf_event.h:42:56: note: expanded from macro 'perf_arch_misc_flags'
      42 | #define perf_arch_misc_flags(regs) perf_misc_flags(regs)
         |                                    ~~~~~~~~~~~~~~~     ^
   kernel/events/core.c:6929:15: note: 'perf_misc_flags' declared here
    6929 | unsigned long perf_misc_flags(struct perf_event *event,
         |               ^               ~~~~~~~~~~~~~~~~~~~~~~~~~
    6930 |                               struct pt_regs *regs)
         |                               ~~~~~~~~~~~~~~~~~~~~
   16 warnings and 1 error generated.


vim +6935 kernel/events/core.c

e01be2b9ba5700 Colton Lewis 2024-09-19  6928  
e01be2b9ba5700 Colton Lewis 2024-09-19  6929  unsigned long perf_misc_flags(struct perf_event *event,
e01be2b9ba5700 Colton Lewis 2024-09-19  6930  			      struct pt_regs *regs)
e01be2b9ba5700 Colton Lewis 2024-09-19  6931  {
e01be2b9ba5700 Colton Lewis 2024-09-19  6932  	if (should_sample_guest(event))
e01be2b9ba5700 Colton Lewis 2024-09-19  6933  		return perf_arch_guest_misc_flags(regs);
e01be2b9ba5700 Colton Lewis 2024-09-19  6934  
ae90a5329c331d Colton Lewis 2024-09-19 @6935  	return perf_arch_misc_flags(regs);
ae90a5329c331d Colton Lewis 2024-09-19  6936  }
ae90a5329c331d Colton Lewis 2024-09-19  6937
diff mbox series

Patch

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 31a5584ed423..ee45b4e77347 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -10,10 +10,6 @@ 
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_PERF_EVENTS
-struct pt_regs;
-extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
-extern unsigned long perf_arch_misc_flags(struct pt_regs *regs);
-#define perf_arch_misc_flags(regs)	perf_misc_flags(regs)
 #define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
 #endif
 
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 01a9d08fc009..9b7f26b128b5 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -38,31 +38,3 @@  void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 
 	arch_stack_walk(callchain_trace, entry, current, regs);
 }
-
-unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
-{
-	if (perf_guest_state())
-		return perf_guest_get_ip();
-
-	return instruction_pointer(regs);
-}
-
-unsigned long perf_arch_misc_flags(struct pt_regs *regs)
-{
-	unsigned int guest_state = perf_guest_state();
-	int misc = 0;
-
-	if (guest_state) {
-		if (guest_state & PERF_GUEST_USER)
-			misc |= PERF_RECORD_MISC_GUEST_USER;
-		else
-			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
-	} else {
-		if (user_mode(regs))
-			misc |= PERF_RECORD_MISC_USER;
-		else
-			misc |= PERF_RECORD_MISC_KERNEL;
-	}
-
-	return misc;
-}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d51e5d24802b..3c5f512d2bcf 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2942,9 +2942,6 @@  static unsigned long code_segment_base(struct pt_regs *regs)
 
 unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
-	if (perf_guest_state())
-		return perf_guest_get_ip();
-
 	return regs->ip + code_segment_base(regs);
 }
 
@@ -2971,17 +2968,12 @@  unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
 
 unsigned long perf_arch_misc_flags(struct pt_regs *regs)
 {
-	unsigned int guest_state = perf_guest_state();
 	unsigned long misc = common_misc_flags(regs);
 
-	if (guest_state) {
-		misc |= perf_arch_guest_misc_flags(regs);
-	} else {
-		if (user_mode(regs))
-			misc |= PERF_RECORD_MISC_USER;
-		else
-			misc |= PERF_RECORD_MISC_KERNEL;
-	}
+	if (user_mode(regs))
+		misc |= PERF_RECORD_MISC_USER;
+	else
+		misc |= PERF_RECORD_MISC_KERNEL;
 
 	return misc;
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d061e327ad54..968f3edd95e4 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1633,8 +1633,9 @@  extern void perf_tp_event(u16 event_type, u64 count, void *record,
 			  struct task_struct *task);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs);
+extern unsigned long perf_instruction_pointer(struct perf_event *event,
+					      struct pt_regs *regs);
 
 #ifndef perf_arch_misc_flags
 # define perf_arch_misc_flags(regs) \
@@ -1645,6 +1646,22 @@  extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 # define perf_arch_bpf_user_pt_regs(regs) regs
 #endif
 
+#ifndef perf_arch_guest_misc_flags
+static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
+{
+	unsigned long guest_state = perf_guest_state();
+
+	if (guest_state & PERF_GUEST_USER)
+		return PERF_RECORD_MISC_GUEST_USER;
+
+	if (guest_state & PERF_GUEST_ACTIVE)
+		return PERF_RECORD_MISC_GUEST_KERNEL;
+
+	return 0;
+}
+# define perf_arch_guest_misc_flags(regs)	perf_arch_guest_misc_flags(regs)
+#endif
+
 static inline bool has_branch_stack(struct perf_event *event)
 {
 	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index eeabbf791a8c..c5e57c024d9a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6921,13 +6921,26 @@  void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
 EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
 #endif
 
-unsigned long perf_misc_flags(struct pt_regs *regs)
+static bool should_sample_guest(struct perf_event *event)
 {
+	return !event->attr.exclude_guest && perf_guest_state();
+}
+
+unsigned long perf_misc_flags(struct perf_event *event,
+			      struct pt_regs *regs)
+{
+	if (should_sample_guest(event))
+		return perf_arch_guest_misc_flags(regs);
+
 	return perf_arch_misc_flags(regs);
 }
 
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_instruction_pointer(struct perf_event *event,
+				       struct pt_regs *regs)
 {
+	if (should_sample_guest(event))
+		return perf_guest_get_ip();
+
 	return perf_arch_instruction_pointer(regs);
 }
 
@@ -7743,7 +7756,7 @@  void perf_prepare_sample(struct perf_sample_data *data,
 	__perf_event_header__init_id(data, event, filtered_sample_type);
 
 	if (filtered_sample_type & PERF_SAMPLE_IP) {
-		data->ip = perf_instruction_pointer(regs);
+		data->ip = perf_instruction_pointer(event, regs);
 		data->sample_flags |= PERF_SAMPLE_IP;
 	}
 
@@ -7907,7 +7920,7 @@  void perf_prepare_header(struct perf_event_header *header,
 {
 	header->type = PERF_RECORD_SAMPLE;
 	header->size = perf_sample_data_size(data, event);
-	header->misc = perf_misc_flags(regs);
+	header->misc = perf_misc_flags(event, regs);
 
 	/*
 	 * If you're adding more sample types here, you likely need to do