[PATCH v8 0/5] Correct perf sampling with Guest VMs

[PATCH v8 0/5] Correct perf sampling with Guest VMs

[Colton Lewis]

v8:
* Improve patch 4 perf flags refactor
* Rebase to v6.12-rc7

v7:
https://lore.kernel.org/all/20241107190336.2963882-1-coltonlewis@google.com/

v6:
https://lore.kernel.org/all/20241105195603.2317483-1-coltonlewis@google.com/

v5:
https://lore.kernel.org/all/20240920174740.781614-1-coltonlewis@google.com/

v4:
https://lore.kernel.org/kvm/20240919190750.4163977-1-coltonlewis@google.com/

v3:
https://lore.kernel.org/kvm/20240912205133.4171576-1-coltonlewis@google.com/

v2:
https://lore.kernel.org/kvm/20240911222433.3415301-1-coltonlewis@google.com/

v1:
https://lore.kernel.org/kvm/20240904204133.1442132-1-coltonlewis@google.com/

This series cleans up perf recording around guest events and improves
the accuracy of the resulting perf reports.

Perf was incorrectly counting any PMU overflow interrupt that occurred
while a VCPU was loaded as a guest event even when the events were not
truely guest events. This lead to much less accurate and useful perf
recordings.

See as an example the below reports of `perf record
dirty_log_perf_test -m 2 -v 4` before and after the series on ARM64.

Without series:

Samples: 15K of event 'instructions', Event count (approx.): 31830580924
Overhead  Command          Shared Object        Symbol
  54.54%  dirty_log_perf_  dirty_log_perf_test  [.] run_test
   5.39%  dirty_log_perf_  dirty_log_perf_test  [.] vcpu_worker
   0.89%  dirty_log_perf_  [kernel.vmlinux]     [k] release_pages
   0.70%  dirty_log_perf_  [kernel.vmlinux]     [k] free_pcppages_bulk
   0.62%  dirty_log_perf_  dirty_log_perf_test  [.] userspace_mem_region_find
   0.49%  dirty_log_perf_  dirty_log_perf_test  [.] sparsebit_is_set
   0.46%  dirty_log_perf_  dirty_log_perf_test  [.] _virt_pg_map
   0.46%  dirty_log_perf_  dirty_log_perf_test  [.] node_add
   0.37%  dirty_log_perf_  dirty_log_perf_test  [.] node_reduce
   0.35%  dirty_log_perf_  [kernel.vmlinux]     [k] free_unref_page_commit
   0.33%  dirty_log_perf_  [kernel.vmlinux]     [k] __kvm_pgtable_walk
   0.31%  dirty_log_perf_  [kernel.vmlinux]     [k] stage2_attr_walker
   0.29%  dirty_log_perf_  [kernel.vmlinux]     [k] unmap_page_range
   0.29%  dirty_log_perf_  dirty_log_perf_test  [.] test_assert
   0.26%  dirty_log_perf_  [kernel.vmlinux]     [k] __mod_memcg_lruvec_state
   0.24%  dirty_log_perf_  [kernel.vmlinux]     [k] kvm_s2_put_page

With series:

Samples: 15K of event 'instructions', Event count (approx.): 31830580924
Samples: 15K of event 'instructions', Event count (approx.): 30898031385
Overhead  Command          Shared Object        Symbol
  54.05%  dirty_log_perf_  dirty_log_perf_test  [.] run_test
   5.48%  dirty_log_perf_  [kernel.kallsyms]    [k] kvm_arch_vcpu_ioctl_run
   4.70%  dirty_log_perf_  dirty_log_perf_test  [.] vcpu_worker
   3.11%  dirty_log_perf_  [kernel.kallsyms]    [k] kvm_handle_guest_abort
   2.24%  dirty_log_perf_  [kernel.kallsyms]    [k] up_read
   1.98%  dirty_log_perf_  [kernel.kallsyms]    [k] __kvm_tlb_flush_vmid_ipa_nsh
   1.97%  dirty_log_perf_  [kernel.kallsyms]    [k] __pi_clear_page
   1.30%  dirty_log_perf_  [kernel.kallsyms]    [k] down_read
   1.13%  dirty_log_perf_  [kernel.kallsyms]    [k] release_pages
   1.12%  dirty_log_perf_  [kernel.kallsyms]    [k] __kvm_pgtable_walk
   1.08%  dirty_log_perf_  [kernel.kallsyms]    [k] folio_batch_move_lru
   1.06%  dirty_log_perf_  [kernel.kallsyms]    [k] __srcu_read_lock
   1.03%  dirty_log_perf_  [kernel.kallsyms]    [k] get_page_from_freelist
   1.01%  dirty_log_perf_  [kernel.kallsyms]    [k] __pte_offset_map_lock
   0.82%  dirty_log_perf_  [kernel.kallsyms]    [k] handle_mm_fault
   0.74%  dirty_log_perf_  [kernel.kallsyms]    [k] mas_state_walk

Colton Lewis (5):
  arm: perf: Drop unused functions
  perf: Hoist perf_instruction_pointer() and perf_misc_flags()
  powerpc: perf: Use perf_arch_instruction_pointer()
  x86: perf: Refactor misc flag assignments
  perf: Correct perf sampling with guest VMs

 arch/arm/include/asm/perf_event.h            |  7 ---
 arch/arm/kernel/perf_callchain.c             | 17 ------
 arch/arm64/include/asm/perf_event.h          |  4 --
 arch/arm64/kernel/perf_callchain.c           | 28 ---------
 arch/powerpc/include/asm/perf_event_server.h |  6 +-
 arch/powerpc/perf/callchain.c                |  2 +-
 arch/powerpc/perf/callchain_32.c             |  2 +-
 arch/powerpc/perf/callchain_64.c             |  2 +-
 arch/powerpc/perf/core-book3s.c              |  4 +-
 arch/s390/include/asm/perf_event.h           |  6 +-
 arch/s390/kernel/perf_event.c                |  4 +-
 arch/x86/events/core.c                       | 64 +++++++++++++-------
 arch/x86/include/asm/perf_event.h            | 12 ++--
 include/linux/perf_event.h                   | 26 +++++++-
 kernel/events/core.c                         | 27 ++++++++-
 15 files changed, 111 insertions(+), 100 deletions(-)


base-commit: 2d5404caa8c7bb5c4e0435f94b28834ae5456623
--
2.47.0.338.g60cca15819-goog

[PATCH v8 1/5] arm: perf: Drop unused functions

[Colton Lewis]

For arm's implementation, perf_instruction_pointer() and
perf_misc_flags() are equivalent to the generic versions in
include/linux/perf_event.h so arch/arm doesn't need to provide its
own versions. Drop them here.

Signed-off-by: Colton Lewis <coltonlewis@google.com>
Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm/include/asm/perf_event.h |  7 -------
 arch/arm/kernel/perf_callchain.c  | 17 -----------------
 2 files changed, 24 deletions(-)

diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index bdbc1e590891e..c08f16f2e2435 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -8,13 +8,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-#ifdef CONFIG_PERF_EVENTS
-struct pt_regs;
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-#define perf_misc_flags(regs)	perf_misc_flags(regs)
-#endif
-
 #define perf_arch_fetch_caller_regs(regs, __ip) { \
 	(regs)->ARM_pc = (__ip); \
 	frame_pointer((regs)) = (unsigned long) __builtin_frame_address(0); \
diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index 1d230ac9d0eb5..a2601b1ef3182 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -96,20 +96,3 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	arm_get_current_stackframe(regs, &fr);
 	walk_stackframe(&fr, callchain_trace, entry);
 }
-
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
-{
-	return instruction_pointer(regs);
-}
-
-unsigned long perf_misc_flags(struct pt_regs *regs)
-{
-	int misc = 0;
-
-	if (user_mode(regs))
-		misc |= PERF_RECORD_MISC_USER;
-	else
-		misc |= PERF_RECORD_MISC_KERNEL;
-
-	return misc;
-}
-- 
2.47.0.338.g60cca15819-goog

[PATCH v8 2/5] perf: Hoist perf_instruction_pointer() and perf_misc_flags()

[Colton Lewis]

For clarity, rename the arch-specific definitions of these functions
to perf_arch_* to denote they are arch-specifc. Define the
generic-named functions in one place where they can call the
arch-specific ones as needed.

Signed-off-by: Colton Lewis <coltonlewis@google.com>
Acked-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/perf_event.h          |  6 +++---
 arch/arm64/kernel/perf_callchain.c           |  4 ++--
 arch/powerpc/include/asm/perf_event_server.h |  6 +++---
 arch/powerpc/perf/core-book3s.c              |  4 ++--
 arch/s390/include/asm/perf_event.h           |  6 +++---
 arch/s390/kernel/perf_event.c                |  4 ++--
 arch/x86/events/core.c                       |  4 ++--
 arch/x86/include/asm/perf_event.h            | 10 +++++-----
 include/linux/perf_event.h                   |  9 ++++++---
 kernel/events/core.c                         | 10 ++++++++++
 10 files changed, 38 insertions(+), 25 deletions(-)

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index eb7071c9eb343..31a5584ed4232 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -11,9 +11,9 @@
 
 #ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-#define perf_misc_flags(regs)	perf_misc_flags(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 e8ed5673f4817..01a9d08fc0090 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -39,7 +39,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 	arch_stack_walk(callchain_trace, entry, current, regs);
 }
 
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
 	if (perf_guest_state())
 		return perf_guest_get_ip();
@@ -47,7 +47,7 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs)
 	return instruction_pointer(regs);
 }
 
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
 {
 	unsigned int guest_state = perf_guest_state();
 	int misc = 0;
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 5995614e90629..af0f46e2373bd 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -102,8 +102,8 @@ struct power_pmu {
 int __init register_power_pmu(struct power_pmu *pmu);
 
 struct pt_regs;
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_arch_misc_flags(struct pt_regs *regs);
+extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
 extern unsigned long int read_bhrb(int n);
 
 /*
@@ -111,7 +111,7 @@ extern unsigned long int read_bhrb(int n);
  * if we have hardware PMU support.
  */
 #ifdef CONFIG_PPC_PERF_CTRS
-#define perf_misc_flags(regs)	perf_misc_flags(regs)
+#define perf_arch_misc_flags(regs)	perf_arch_misc_flags(regs)
 #endif
 
 /*
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 42867469752d7..dc01aa604cc1e 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2332,7 +2332,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
  * Called from generic code to get the misc flags (i.e. processor mode)
  * for an event_id.
  */
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
 {
 	u32 flags = perf_get_misc_flags(regs);
 
@@ -2346,7 +2346,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  * Called from generic code to get the instruction pointer
  * for an event_id.
  */
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long siar = mfspr(SPRN_SIAR);
 
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 29ee289108c56..e53894cedf088 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -37,9 +37,9 @@ extern ssize_t cpumf_events_sysfs_show(struct device *dev,
 
 /* Perf callbacks */
 struct pt_regs;
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-#define perf_misc_flags(regs) perf_misc_flags(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_arch_misc_flags(regs)
 #define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
 
 /* Perf pt_regs extension for sample-data-entry indicators */
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 5fff629b1a898..f9000ab49f4ad 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -57,7 +57,7 @@ static unsigned long instruction_pointer_guest(struct pt_regs *regs)
 	return sie_block(regs)->gpsw.addr;
 }
 
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
 	return is_in_guest(regs) ? instruction_pointer_guest(regs)
 				 : instruction_pointer(regs);
@@ -84,7 +84,7 @@ static unsigned long perf_misc_flags_sf(struct pt_regs *regs)
 	return flags;
 }
 
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
 {
 	/* Check if the cpum_sf PMU has created the pt_regs structure.
 	 * In this case, perf misc flags can be easily extracted.  Otherwise,
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 65ab6460aed4d..d19e939f39983 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -3003,7 +3003,7 @@ static unsigned long code_segment_base(struct pt_regs *regs)
 	return 0;
 }
 
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
 	if (perf_guest_state())
 		return perf_guest_get_ip();
@@ -3011,7 +3011,7 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs)
 	return regs->ip + code_segment_base(regs);
 }
 
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
 {
 	unsigned int guest_state = perf_guest_state();
 	int misc = 0;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 91b73571412f1..feb87bf3d2e9c 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -536,15 +536,15 @@ struct x86_perf_regs {
 	u64		*xmm_regs;
 };
 
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-#define perf_misc_flags(regs)	perf_misc_flags(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_arch_misc_flags(regs)
 
 #include <asm/stacktrace.h>
 
 /*
- * We abuse bit 3 from flags to pass exact information, see perf_misc_flags
- * and the comment with PERF_EFLAGS_EXACT.
+ * We abuse bit 3 from flags to pass exact information, see
+ * perf_arch_misc_flags() and the comment with PERF_EFLAGS_EXACT.
  */
 #define perf_arch_fetch_caller_regs(regs, __ip)		{	\
 	(regs)->ip = (__ip);					\
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fb908843f2092..772ad352856b6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1655,10 +1655,13 @@ 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);
 
-#ifndef perf_misc_flags
-# define perf_misc_flags(regs) \
+extern unsigned long perf_misc_flags(struct pt_regs *regs);
+extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+
+#ifndef perf_arch_misc_flags
+# define perf_arch_misc_flags(regs) \
 		(user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL)
-# define perf_instruction_pointer(regs)	instruction_pointer(regs)
+# define perf_arch_instruction_pointer(regs)	instruction_pointer(regs)
 #endif
 #ifndef perf_arch_bpf_user_pt_regs
 # define perf_arch_bpf_user_pt_regs(regs) regs
diff --git a/kernel/events/core.c b/kernel/events/core.c
index df27d08a72326..2c44ffd6f4d80 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7022,6 +7022,16 @@ 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)
+{
+	return perf_arch_misc_flags(regs);
+}
+
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
+	return perf_arch_instruction_pointer(regs);
+}
+
 static void
 perf_output_sample_regs(struct perf_output_handle *handle,
 			struct pt_regs *regs, u64 mask)
-- 
2.47.0.338.g60cca15819-goog

[PATCH v8 3/5] powerpc: perf: Use perf_arch_instruction_pointer()

[Colton Lewis]

Make sure powerpc uses the arch-specific function now that those have
been reorganized.

Signed-off-by: Colton Lewis <coltonlewis@google.com>
Acked-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/powerpc/perf/callchain.c    | 2 +-
 arch/powerpc/perf/callchain_32.c | 2 +-
 arch/powerpc/perf/callchain_64.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 6b4434dd0ff30..26aa26482c9ac 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -51,7 +51,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, perf_instruction_pointer(regs));
+	perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
 
 	if (!validate_sp(sp, current))
 		return;
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index ea8cfe3806dce..ddcc2d8aa64a5 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -139,7 +139,7 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 	long level = 0;
 	unsigned int __user *fp, *uregs;
 
-	next_ip = perf_instruction_pointer(regs);
+	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 488e8a21a11ea..115d1c105e8a8 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -74,7 +74,7 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 	struct signal_frame_64 __user *sigframe;
 	unsigned long __user *fp, *uregs;
 
-	next_ip = perf_instruction_pointer(regs);
+	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
-- 
2.47.0.338.g60cca15819-goog

[PATCH v8 4/5] x86: perf: Refactor misc flag assignments

[Colton Lewis]

Break the assignment logic for misc flags into their own respective
functions to reduce the complexity of the nested logic.

Signed-off-by: Colton Lewis <coltonlewis@google.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/x86/events/core.c            | 59 ++++++++++++++++++++++---------
 arch/x86/include/asm/perf_event.h |  2 ++
 2 files changed, 44 insertions(+), 17 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index d19e939f39983..bfc0a35fe3993 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -3011,27 +3011,52 @@ unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 	return regs->ip + code_segment_base(regs);
 }
 
-unsigned long perf_arch_misc_flags(struct pt_regs *regs)
+static unsigned long common_misc_flags(struct pt_regs *regs)
 {
-	unsigned int guest_state = perf_guest_state();
-	int misc = 0;
+	if (regs->flags & PERF_EFLAGS_EXACT)
+		return PERF_RECORD_MISC_EXACT_IP;
 
-	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 0;
+}
 
-	if (regs->flags & PERF_EFLAGS_EXACT)
-		misc |= PERF_RECORD_MISC_EXACT_IP;
+static unsigned long guest_misc_flags(struct pt_regs *regs)
+{
+	unsigned long guest_state = perf_guest_state();
+
+	if (!(guest_state & PERF_GUEST_ACTIVE))
+		return 0;
+
+	if (guest_state & PERF_GUEST_USER)
+		return PERF_RECORD_MISC_GUEST_USER;
+	else
+		return PERF_RECORD_MISC_GUEST_KERNEL;
+
+}
+
+static unsigned long host_misc_flags(struct pt_regs *regs)
+{
+	if (user_mode(regs))
+		return PERF_RECORD_MISC_USER;
+	else
+		return PERF_RECORD_MISC_KERNEL;
+}
+
+unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
+{
+	unsigned long flags = common_misc_flags(regs);
+
+	flags |= guest_misc_flags(regs);
+
+	return flags;
+}
+
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
+{
+	unsigned long flags = common_misc_flags(regs);
+
+	flags |= host_misc_flags(regs);
 
-	return misc;
+	return flags;
 }
 
 void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index feb87bf3d2e9c..d95f902acc521 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -538,7 +538,9 @@ struct x86_perf_regs {
 
 extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_arch_misc_flags(struct pt_regs *regs);
+extern unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs);
 #define perf_arch_misc_flags(regs)	perf_arch_misc_flags(regs)
+#define perf_arch_guest_misc_flags(regs)	perf_arch_guest_misc_flags(regs)
 
 #include <asm/stacktrace.h>
 
-- 
2.47.0.338.g60cca15819-goog

[PATCH v8 5/5] perf: Correct perf sampling with guest VMs

[Colton Lewis]

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>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/perf_event.h |  4 ----
 arch/arm64/kernel/perf_callchain.c  | 28 ----------------------------
 arch/x86/events/core.c              |  3 ---
 include/linux/perf_event.h          | 21 +++++++++++++++++++--
 kernel/events/core.c                | 21 +++++++++++++++++----
 5 files changed, 36 insertions(+), 41 deletions(-)

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 31a5584ed4232..ee45b4e773470 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 01a9d08fc0090..9b7f26b128b51 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 bfc0a35fe3993..c75c482d4c52f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -3005,9 +3005,6 @@ 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);
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 772ad352856b6..368ea0e9577c7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1655,8 +1655,9 @@ 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) \
@@ -1667,6 +1668,22 @@ 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_ACTIVE))
+		return 0;
+
+	if (guest_state & PERF_GUEST_USER)
+		return PERF_RECORD_MISC_GUEST_USER;
+	else
+		return PERF_RECORD_MISC_GUEST_KERNEL;
+}
+# 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 2c44ffd6f4d80..c62164a2ff23a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7022,13 +7022,26 @@ 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);
 }
 
@@ -7849,7 +7862,7 @@ 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;
 	}
 
@@ -8013,7 +8026,7 @@ 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
-- 
2.47.0.338.g60cca15819-goog